Creator · haorantang97
Last updated · Sep 3, 2026
Create original relaxed black-pen graphics from concepts or visual references, including sparse illustrations, narrative scenes, animals, objects, abstract relationships, icons, and logo marks. Use when the user wants quick hand-drawn line energy, causal story staging, non-equili
Creator · haorantang97
Last updated · Sep 3, 2026
Create original relaxed black-pen graphics from concepts or visual references, including sparse illustrations, narrative scenes, animals, objects, abstract relationships, icons, and logo marks. Use when the user wants quick hand-drawn line energy, causal story staging, non-equili
Creator · haorantang97
Last updated · Sep 3, 2026
Create original relaxed black-pen graphics from concepts or visual references, including sparse illustrations, narrative scenes, animals, objects, abstract relationships, icons, and logo marks. Use when the user wants quick hand-drawn line energy, causal story staging, non-equili
Creator · haorantang97
Last updated · Sep 3, 2026
Create original relaxed black-pen graphics from concepts or visual references, including sparse illustrations, narrative scenes, animals, objects, abstract relationships, icons, and logo marks. Use when the user wants quick hand-drawn line energy, causal story staging, non-equili
Sandbox only
Install targets
Codex install prompt
Install the "antibes-holiday" agent skill from https://github.com/haorantang97/LabArt/tree/main/plugins/antibes-holiday/skills/antibes-holiday. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Create original relaxed black-pen graphics from concepts or visual references, including sparse illustrations, narrative scenes, animals, objects, abstract relationships, icons, and logo marks. Use when the user wants quick hand-drawn line energy, causal story staging, non-equilibrium proportion, shorthand forms, open contours, structural line drift, misregistered junctions, selective retracing, physical pen texture, or a transferable illustration system that must not collapse into clean vector minimalism or polished period-sketch drawing. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"haorantang97-antibes-holiday","task":"Install antibes-holiday","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.Supply asset profile
Design assets, images, video, audio, multimodal media, presentation, and creative production skills.
Scenario
Design and creative
I need my agent to produce design assets, UI directions, presentations, or creative media workflows.
Agent fit
Claude Code + OpenAI Agents + CLI
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add haorantang97/LabArt --skill antibes-holiday
Maintenance
fresh
9d since push
Risk
Needs review
Dependency or permission surface needs review
GitHub quality
282
71/100 Quality · 72/100 Trust
Coverage tags
Review notes
Dependency or permission surface needs review · Permission surface may require sandboxing
Agent adoption scorecard
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
StrongSolid option that is likely worth shortlisting for production workflows.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Needs reviewA machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
OpenAgentSkill Trust Score v5
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
282 GitHub stars
Repo activity
282 stars, 16 forks
Maintenance
9d since push
License
PolyForm-Noncommercial-1.0.0
Install
npx skills add haorantang97/LabArt --skill antibes-holiday
Install safety
Agent-readable metadata
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
Suited agents
Install decision
Trust and risk
Outcome loop
Install command
npx skills add haorantang97/LabArt --skill antibes-holidayDo not use when
Alternative
174.2K Stars
npx skills add anthropics/skills --skill frontend-design
Alternative
84.4K Stars
npx skills add Leonxlnx/taste-skill --skill design-taste-frontend
Alternative
174.2K Stars
npx skills add anthropics/skills --skill canvas-design
Alternative
174.2K Stars
npx skills add anthropics/skills --skill brand-guidelines
Agent safety v2
This skill should not be selected by an agent without explicit human security review.
Do not auto-install. Inspect the source, dependencies, and permission surface first.
high
Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.
medium
Skill may drive a browser or interact with web pages.
medium
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Skill may read or write project files, documents, generated artifacts, or local workspace state.
Agent resolve plan
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Open JSON
/api/agent/resolve?task=Use%20antibes-holiday%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20antibes-holiday%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/haorantang97-antibes-holiday/install
Agent should check
Copy prompt
Task: Use antibes-holiday in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20antibes-holiday%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/haorantang97-antibes-holiday/install
Install command: npx skills add haorantang97/LabArt --skill antibes-holiday
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/haorantang97-antibes-holiday/install
LLM text format
/api/skills/haorantang97-antibes-holiday/install?format=text
Find alternatives
/api/skills/search?q=antibes-holiday&limit=3
Agent prompt
Use antibes-holiday for this task. Review https://www.openagentskill.com/api/skills/haorantang97-antibes-holiday/install, then install with: npx skills add haorantang97/LabArt --skill antibes-holidayRegistry metadata
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/haorantang97-antibes-holiday
LLM text
/api/registry/manifest/haorantang97-antibes-holiday?format=text
Install alias
/api/registry/install/haorantang97-antibes-holiday
Recommend
/api/registry/recommend?task=Use%20antibes-holiday%20in%20an%20agent%20workflow&limit=3
Agent fit
Local desktop
Use-case tags
Platforms
Claude Code, OpenAI Agents
Audit report
A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
Agent decision cockpit
Prototype with this skill first; keep a fallback candidate ready.
Role in stack
Fallback candidate
Primary fit
Local desktop
Trust label
Prototype first
Install path
Command ready
Use when
Evidence
review first
Implementation path
Trust profile
Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
GitHub adoption
INFO282 GitHub stars
Stars/forks activity
CHECK282 stars, 16 forks; issue activity unavailable in current metadata
Recent maintenance
PASS9d since push
License clarity
CHECKPolyForm-Noncommercial-1.0.0 - confirm commercial-use terms
Good signals
Review before install
Recommended action
Run only in a sandbox and compare close alternatives before using it for real work.
Quality profile
Solid option that is likely worth shortlisting for production workflows.
Workflow fit
Operate local tools
I need my agent to operate local files and desktop apps in a repeatable workflow.
Create assets
I need my agent to produce design assets, UI directions, presentations, or creative media workflows.
Search private knowledge
I need my agent to build a RAG workflow over documents and retrieve reliable context.
Workflow fit
Design, build, test, and ship interfaces
A practical workflow for agents that turn product briefs or Figma designs into polished frontend code, review the result, test it in a browser, and prepare a safe deployment.
Operate and verify web apps
A workflow for agents that navigate products, fill forms, take screenshots, and verify real user flows across web applications.
Ingest, retrieve, and cite
A workflow for document-heavy agents that ingest files, create searchable knowledge, retrieve relevant context, and answer with grounded sources.
Alternative shortlist
Similar skills that may fit this task.
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related artifacts.
--- name: antibes-holiday description: Create original relaxed black-pen graphics from concepts or visual references, including sparse illustrations, narrative scenes, animals, objects, abstract relationships, icons, and logo marks. Use when the user wants quick hand-drawn line energy, causal story staging, non-equilibrium proportion, shorthand forms, open contours, structural line drift, misregistered junctions, selective retracing, physical pen texture, or a transferable illustration system that must not collapse into clean vector minimalism or polished period-sketch drawing. license: PolyForm-Noncommercial-1.0.0 ---
# Antibes Holiday
Create original graphics that feel drawn in one alert but lightly unsteady sitting with a real black pen. Prioritize stroke life, tempo, shorthand, structural instability, and the courage to stop. Semantic compression remains useful, but a clean concept never compensates for lines that look professionally controlled.
## Start With Evidence
When references are supplied:
1. Define the target style cluster from stroke material, tempo, omission, density, and composition. 2. Exclude unrelated style clusters from the same reference body. 3. Record dates inside the cluster and weight recent mature work most heavily. 4. Inspect at least three high-weight images at actual size. 5. Separate stroke behavior from recurring subjects and accessories. 6. Use references for line material and gesture only. Never reuse their subject, pose, composition, or signature motif.
Default evidence weighting:
- newest mature same-cluster works: `60%`; - recent supporting same-cluster works: `30%`; - early same-cluster works: `10%`; - different styles or experiments: `0%`.
Read [style-system.md](references/style-system.md) before drawing. Read [prompt-recipes.md](references/prompt-recipes.md) before using an image-generation model.
## Define The Drawing
1. Classify the deliverable: `illustration`, `series`, `icon/badge`, or `logo`. 2. State what must be felt or recognized in one sentence. 3. Choose the subject's most telling action, mass, edge, joint, or relationship. 4. Decide where the drawing should move quickly and where the pen should briefly slow down. 5. Select one dominant sweep and one compact recognition knot. 6. For a scene, identify the `principal actor`, `counterforce`, `narrative hinge`, and the causal path between them. 7. Choose one deliberate scale distortion and one quiet region that carries distance, pause, anticipation, or release. 8. Choose one controlled structural failure: a drifting contour, missed junction, overshoot, displaced restart, incompatible pair of fragments, or abandoned path.
Do not default to a person, face, unrequested character traits, accessories, or anthropomorphism.
## Draw In Three Passes
### Pass 1: Gesture
Draw three fast structural variants.
- Use one to three long sweeps. - Do not close shapes for neatness. - Do not correct proportions yet. - Let at least one sweep drift, lurch, overshoot, or stop before reaching its expected destination. - Permit one to four residual or corrective fragments across an expressive illustration. They must record discovery, not decorate the page. - Reject the prettiest or most anatomically competent variant if it feels designed, trained, or gracefully sketched rather than found while drawing.
### Pass 2: Recognition
Add only the shorthand needed to make the subject legible.
- Use short angular, hooked, wavy, or looping fragments. - Concentrate fragments at the action, contact, or identity knot. - Let large regions remain unnamed. - Omit any boundary the viewer can infer. Do not let one connected contour competently explain the whole form. - Spend conventional detail only when it carries recognition or action. Do not delete so aggressively that the result collapses into a stick symbol. - Distort scale when a hand, tool, opening, joint, shell, edge, or movement carries the idea. - Prefer an implied boundary over a complete outline.
### Pass 3: Pen Life
Restore the physical behavior that image models and vector tools remove.
- Vary pressure and direction unevenly along long sweeps. - Let selected terminals taper, dry out, or stop bluntly. - Add one local retrace or ink-darkened overlap at the recognition knot. - Preserve one broad drift or visible lurch plus smaller speed kinks. - Let one intended junction miss, overlap, or restart slightly displaced. - Keep useful false starts and competing fragments when they show the hand losing and recovering the form. - Concentrate repeated correction and scribbled density at one recognition knot. Outside it, prefer one imperfect attempt over several sketchy alternatives. - Stop before the result becomes clean, balanced, or fully explained.
## Adapt Without Humanizing
- `Living form`: use posture, mass distribution, locomotion, and distinctive anatomy. - `Object`: exaggerate the operational edge, opening, handle, joint, contact, or material path. - `Place`: use one boundary, route, threshold, and scale cue. - `Abstract relationship`: first choose an observable physical metaphor, then express tension, exchange, interruption, growth, or separation through its gesture. Do not draw free-floating lines when the meaning depends on explanation. - `Logo`: begin with a relaxed pen master; derive a separate production vector only after the gesture works.
Do not transfer human facial shorthand to non-human subjects. For human figures, preserve posture and character while withholding clean anatomy. Build the figure from unequal, partially incompatible fragments, with enough local specificity to remain observed rather than diagrammatic.
## Compose Story Scenes
Treat complexity as relationships, not line count.
1. Reduce the event to two or three readable beats. 2. Give each actor a different narrative weight. Scale, crop, and detail may violate realistic perspective when that makes the event clearer. 3. Place one compact `narrative hinge` where intention becomes consequence: contact, exchange, reveal, interruption, impact, or release. 4. Connect the beats with one causal sweep, shared baseline, reach, gaze, object path, or directional gap. Do not add arrows or motion icons. 5. Use unequal information density: describe the principal action, abbreviate supporting actors, and leave the setting largely unstated. 6. Break balance deliberately with one dominant mass, off-center crop, oversized operational feature, displaced small actor, or edge-reaching contour. 7. Let blank paper separate time and distance. Do not fill it with scenery. 8. Stop when the viewer can infer what just happened or is about to happen.
When a scene is humorous, put the humor in disproportion, posture, timing, and physical consequence. Do not explain it with sweat drops, surprise ticks, exclamation marks, speed marks, or other cartoon punctuation unless requested.
Choose a composition family from [style-system.md](references/style-system.md) according to the event. Do not repeat one family across a series by default.
## Select Rendering Capability
Inspect the tools available in the current environment before rendering:
1. In Codex, prefer the system `imagegen` workflow and built-in `image_gen` tool. 2. On another platform, use its native raster generation or editing capability while preserving the reference roles, prompt rules, and validation gates here. 3. If the available tool cannot receive local reference files, use the textual stroke specification and state that the calibration image was not applied. 4. If no image-generation capability exists, do not claim to have rendered an image. Deliver a renderer-ready prompt, the intended reference roles, and the complete validation checklist instead. 5. Never require an API key, install a dependency, or switch to an external service without the user's explicit approval.
## Use Image Generation
Use the selected raster capability for exploration and illustration.
When recent reference crops are available:
1. Supply two or three as line-material references. 2. State that their subjects and compositions must be ignored. 3. Generate one direction per call. 4. Compare the result at actual size, not only as a thumbnail. 5. Edit one stroke problem at a time.
When no user references are available, supply the bundled [stroke-calibration.png](assets/stroke-calibration.png). It controls physical pen instability: pressure, drift, missed junctions, overshoots, displaced restarts, broad lurches, retracing, ink deposition, dry breaks, and abrupt terminals. Ignore every shape and layout in the asset. Never copy a swatch as an object, symbol, border, motif, or composition. Keep structural assembly in the text prompt; do not add a second visual reference whose cleaner lines could dilute the material.
Use a bounded decontrol pass when the first readable render remains too competent:
1. Preserve the subject, action, text, composition, hierarchy, and blank space. 2. Change only line construction: break a clean contour, displace one restart, remove conventional detail, and let one structural drift alter the silhouette. 3. Compare before and after at actual size. 4. Keep the edit only when readability survives and the line no longer resembles trained editorial, fashion, or period sketching. Otherwise keep the readable draft and edit one region at a time.
Ask for a photographed or scanned black-pen drawing only when physical stroke texture matters. Keep paper texture subtle and never use it to fake quality.
## Build Logos
1. Explore the mark as a relaxed pen gesture first. 2. Remove narrative detail without sterilizing the line. 3. Create two masters when appropriate: - `expressive master`: preserves pen irregularity for display use; - `production master`: optically tuned SVG for small sizes. 4. Treat generated raster marks as sketches, not finished logos. 5. Reconstruct deliberate vector paths; never auto-trace paper noise. 6. Test one color, reversed color, 24 px, 48 px, and print-size black.
Do not force an illustration line to survive at favicon size by making every stroke thick and geometric.
## Comparative Validation
Validate against at least three recent, same-cluster references. The candidate must pass every primary gate:
- `Physicality`: reads as real pen movement, not a Bézier outline or generic sketch filter. - `Tempo`: contains visible contrast between fast sweeps and slower recognition marks. - `Instability`: at least one structural line visibly loses and recovers control; intended meetings are not all perfectly registered. - `Shorthand`: forms are inferred from decisive fragments rather than fully described. - `Relaxation`: proportions, spacing, anatomy, and terminals feel unforced without turning into uniform noise. - `Transfer`: the line behavior survives the new subject without importing human accessories or source motifs. - `Originality`: no source composition, character, or signature device is reproduced.
For story scenes, add two primary gates:
- `Causality`: the spatial arrangement makes the action and consequence inferable. - `Hierarchy`: scale, crop, density, and empty space clearly prioritize the story without defaulting to balanced staging or realistic perspective.
Secondary gates:
- the intended subject or relationship is inferable; - the composition has a clear movement and quiet release; - texture does not dominate; - the output fits its intended reproduction size.
Fail the result immediately if it is vector-clean, diagrammatic, evenly polished, uniformly wobbly, decoratively distressed, or only recognizable because of labels. Also fail it when most contours arrive exactly where expected, figures read as competent fashion or period illustration, faces and hands are cleanly resolved, or the image could pass as a professional quick sketch with texture added afterward. Visible shoelaces, fingers, pockets, complete facial features,
Source provenance
Decision snapshot
recent repository activity
Audit
Install and adoption review
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Free and open source. Review the report before installing into production agents.
Growth loop
Scenario-led draft for antibes-holiday, ready for a manual X post.
antibes-holiday: Create original relaxed black-pen graphics from concepts or visual references, including spar... 282 stars https://www.openagentskill.com/skills/haorantang97-antibes-holiday?ref=x
Listing + install path for antibes-holiday: https://www.openagentskill.com/skills/haorantang97-antibes-holiday?ref=x Install: npx skills add haorantang97/LabArt --skill antibes-holiday
Listing source
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
This Registry indexed listing is attributed to haorantang97 but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/haorantang97-antibes-holiday?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/haorantang97-antibes-holiday?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/haorantang97-antibes-holiday/audit)
[](https://www.openagentskill.com/skills/haorantang97-antibes-holiday?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)haorantang97
@haorantang97
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Sandbox only
Frontend Design
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
174.2K StarsTaste Skill: Anti-Slop Frontend
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
84.4K StarsCanvas Design
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
174.2K StarsAnthropic Brand Guidelines
Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related artifacts.
174.2K StarsSandbox only
Install targets
Codex install prompt
Install the "antibes-holiday" agent skill from https://github.com/haorantang97/LabArt/tree/main/plugins/antibes-holiday/skills/antibes-holiday. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Create original relaxed black-pen graphics from concepts or visual references, including sparse illustrations, narrative scenes, animals, objects, abstract relationships, icons, and logo marks. Use when the user wants quick hand-drawn line energy, causal story staging, non-equilibrium proportion, shorthand forms, open contours, structural line drift, misregistered junctions, selective retracing, physical pen texture, or a transferable illustration system that must not collapse into clean vector minimalism or polished period-sketch drawing. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"haorantang97-antibes-holiday","task":"Install antibes-holiday","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.Supply asset profile
Design assets, images, video, audio, multimodal media, presentation, and creative production skills.
Scenario
Design and creative
I need my agent to produce design assets, UI directions, presentations, or creative media workflows.
Agent fit
Claude Code + OpenAI Agents + CLI
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add haorantang97/LabArt --skill antibes-holiday
Maintenance
fresh
9d since push
Risk
Needs review
Dependency or permission surface needs review
GitHub quality
282
71/100 Quality · 72/100 Trust
Coverage tags
Review notes
Dependency or permission surface needs review · Permission surface may require sandboxing
Agent adoption scorecard
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
StrongSolid option that is likely worth shortlisting for production workflows.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Needs reviewA machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
OpenAgentSkill Trust Score v5
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
282 GitHub stars
Repo activity
282 stars, 16 forks
Maintenance
9d since push
License
PolyForm-Noncommercial-1.0.0
Install
npx skills add haorantang97/LabArt --skill antibes-holiday
Install safety
Agent-readable metadata
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
Suited agents
Install decision
Trust and risk
Outcome loop
Install command
npx skills add haorantang97/LabArt --skill antibes-holidayDo not use when
Alternative
174.2K Stars
npx skills add anthropics/skills --skill frontend-design
Alternative
84.4K Stars
npx skills add Leonxlnx/taste-skill --skill design-taste-frontend
Alternative
174.2K Stars
npx skills add anthropics/skills --skill canvas-design
Alternative
174.2K Stars
npx skills add anthropics/skills --skill brand-guidelines
Agent safety v2
This skill should not be selected by an agent without explicit human security review.
Do not auto-install. Inspect the source, dependencies, and permission surface first.
high
Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.
medium
Skill may drive a browser or interact with web pages.
medium
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Skill may read or write project files, documents, generated artifacts, or local workspace state.
Agent resolve plan
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Open JSON
/api/agent/resolve?task=Use%20antibes-holiday%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20antibes-holiday%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/haorantang97-antibes-holiday/install
Agent should check
Copy prompt
Task: Use antibes-holiday in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20antibes-holiday%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/haorantang97-antibes-holiday/install
Install command: npx skills add haorantang97/LabArt --skill antibes-holiday
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/haorantang97-antibes-holiday/install
LLM text format
/api/skills/haorantang97-antibes-holiday/install?format=text
Find alternatives
/api/skills/search?q=antibes-holiday&limit=3
Agent prompt
Use antibes-holiday for this task. Review https://www.openagentskill.com/api/skills/haorantang97-antibes-holiday/install, then install with: npx skills add haorantang97/LabArt --skill antibes-holidayRegistry metadata
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/haorantang97-antibes-holiday
LLM text
/api/registry/manifest/haorantang97-antibes-holiday?format=text
Install alias
/api/registry/install/haorantang97-antibes-holiday
Recommend
/api/registry/recommend?task=Use%20antibes-holiday%20in%20an%20agent%20workflow&limit=3
Agent fit
Local desktop
Use-case tags
Platforms
Claude Code, OpenAI Agents
Audit report
A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
Agent decision cockpit
Prototype with this skill first; keep a fallback candidate ready.
Role in stack
Fallback candidate
Primary fit
Local desktop
Trust label
Prototype first
Install path
Command ready
Use when
Evidence
review first
Implementation path
Trust profile
Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
GitHub adoption
INFO282 GitHub stars
Stars/forks activity
CHECK282 stars, 16 forks; issue activity unavailable in current metadata
Recent maintenance
PASS9d since push
License clarity
CHECKPolyForm-Noncommercial-1.0.0 - confirm commercial-use terms
Good signals
Review before install
Recommended action
Run only in a sandbox and compare close alternatives before using it for real work.
Quality profile
Solid option that is likely worth shortlisting for production workflows.
Workflow fit
Operate local tools
I need my agent to operate local files and desktop apps in a repeatable workflow.
Create assets
I need my agent to produce design assets, UI directions, presentations, or creative media workflows.
Search private knowledge
I need my agent to build a RAG workflow over documents and retrieve reliable context.
Workflow fit
Design, build, test, and ship interfaces
A practical workflow for agents that turn product briefs or Figma designs into polished frontend code, review the result, test it in a browser, and prepare a safe deployment.
Operate and verify web apps
A workflow for agents that navigate products, fill forms, take screenshots, and verify real user flows across web applications.
Ingest, retrieve, and cite
A workflow for document-heavy agents that ingest files, create searchable knowledge, retrieve relevant context, and answer with grounded sources.
Alternative shortlist
Similar skills that may fit this task.
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related artifacts.
--- name: antibes-holiday description: Create original relaxed black-pen graphics from concepts or visual references, including sparse illustrations, narrative scenes, animals, objects, abstract relationships, icons, and logo marks. Use when the user wants quick hand-drawn line energy, causal story staging, non-equilibrium proportion, shorthand forms, open contours, structural line drift, misregistered junctions, selective retracing, physical pen texture, or a transferable illustration system that must not collapse into clean vector minimalism or polished period-sketch drawing. license: PolyForm-Noncommercial-1.0.0 ---
# Antibes Holiday
Create original graphics that feel drawn in one alert but lightly unsteady sitting with a real black pen. Prioritize stroke life, tempo, shorthand, structural instability, and the courage to stop. Semantic compression remains useful, but a clean concept never compensates for lines that look professionally controlled.
## Start With Evidence
When references are supplied:
1. Define the target style cluster from stroke material, tempo, omission, density, and composition. 2. Exclude unrelated style clusters from the same reference body. 3. Record dates inside the cluster and weight recent mature work most heavily. 4. Inspect at least three high-weight images at actual size. 5. Separate stroke behavior from recurring subjects and accessories. 6. Use references for line material and gesture only. Never reuse their subject, pose, composition, or signature motif.
Default evidence weighting:
- newest mature same-cluster works: `60%`; - recent supporting same-cluster works: `30%`; - early same-cluster works: `10%`; - different styles or experiments: `0%`.
Read [style-system.md](references/style-system.md) before drawing. Read [prompt-recipes.md](references/prompt-recipes.md) before using an image-generation model.
## Define The Drawing
1. Classify the deliverable: `illustration`, `series`, `icon/badge`, or `logo`. 2. State what must be felt or recognized in one sentence. 3. Choose the subject's most telling action, mass, edge, joint, or relationship. 4. Decide where the drawing should move quickly and where the pen should briefly slow down. 5. Select one dominant sweep and one compact recognition knot. 6. For a scene, identify the `principal actor`, `counterforce`, `narrative hinge`, and the causal path between them. 7. Choose one deliberate scale distortion and one quiet region that carries distance, pause, anticipation, or release. 8. Choose one controlled structural failure: a drifting contour, missed junction, overshoot, displaced restart, incompatible pair of fragments, or abandoned path.
Do not default to a person, face, unrequested character traits, accessories, or anthropomorphism.
## Draw In Three Passes
### Pass 1: Gesture
Draw three fast structural variants.
- Use one to three long sweeps. - Do not close shapes for neatness. - Do not correct proportions yet. - Let at least one sweep drift, lurch, overshoot, or stop before reaching its expected destination. - Permit one to four residual or corrective fragments across an expressive illustration. They must record discovery, not decorate the page. - Reject the prettiest or most anatomically competent variant if it feels designed, trained, or gracefully sketched rather than found while drawing.
### Pass 2: Recognition
Add only the shorthand needed to make the subject legible.
- Use short angular, hooked, wavy, or looping fragments. - Concentrate fragments at the action, contact, or identity knot. - Let large regions remain unnamed. - Omit any boundary the viewer can infer. Do not let one connected contour competently explain the whole form. - Spend conventional detail only when it carries recognition or action. Do not delete so aggressively that the result collapses into a stick symbol. - Distort scale when a hand, tool, opening, joint, shell, edge, or movement carries the idea. - Prefer an implied boundary over a complete outline.
### Pass 3: Pen Life
Restore the physical behavior that image models and vector tools remove.
- Vary pressure and direction unevenly along long sweeps. - Let selected terminals taper, dry out, or stop bluntly. - Add one local retrace or ink-darkened overlap at the recognition knot. - Preserve one broad drift or visible lurch plus smaller speed kinks. - Let one intended junction miss, overlap, or restart slightly displaced. - Keep useful false starts and competing fragments when they show the hand losing and recovering the form. - Concentrate repeated correction and scribbled density at one recognition knot. Outside it, prefer one imperfect attempt over several sketchy alternatives. - Stop before the result becomes clean, balanced, or fully explained.
## Adapt Without Humanizing
- `Living form`: use posture, mass distribution, locomotion, and distinctive anatomy. - `Object`: exaggerate the operational edge, opening, handle, joint, contact, or material path. - `Place`: use one boundary, route, threshold, and scale cue. - `Abstract relationship`: first choose an observable physical metaphor, then express tension, exchange, interruption, growth, or separation through its gesture. Do not draw free-floating lines when the meaning depends on explanation. - `Logo`: begin with a relaxed pen master; derive a separate production vector only after the gesture works.
Do not transfer human facial shorthand to non-human subjects. For human figures, preserve posture and character while withholding clean anatomy. Build the figure from unequal, partially incompatible fragments, with enough local specificity to remain observed rather than diagrammatic.
## Compose Story Scenes
Treat complexity as relationships, not line count.
1. Reduce the event to two or three readable beats. 2. Give each actor a different narrative weight. Scale, crop, and detail may violate realistic perspective when that makes the event clearer. 3. Place one compact `narrative hinge` where intention becomes consequence: contact, exchange, reveal, interruption, impact, or release. 4. Connect the beats with one causal sweep, shared baseline, reach, gaze, object path, or directional gap. Do not add arrows or motion icons. 5. Use unequal information density: describe the principal action, abbreviate supporting actors, and leave the setting largely unstated. 6. Break balance deliberately with one dominant mass, off-center crop, oversized operational feature, displaced small actor, or edge-reaching contour. 7. Let blank paper separate time and distance. Do not fill it with scenery. 8. Stop when the viewer can infer what just happened or is about to happen.
When a scene is humorous, put the humor in disproportion, posture, timing, and physical consequence. Do not explain it with sweat drops, surprise ticks, exclamation marks, speed marks, or other cartoon punctuation unless requested.
Choose a composition family from [style-system.md](references/style-system.md) according to the event. Do not repeat one family across a series by default.
## Select Rendering Capability
Inspect the tools available in the current environment before rendering:
1. In Codex, prefer the system `imagegen` workflow and built-in `image_gen` tool. 2. On another platform, use its native raster generation or editing capability while preserving the reference roles, prompt rules, and validation gates here. 3. If the available tool cannot receive local reference files, use the textual stroke specification and state that the calibration image was not applied. 4. If no image-generation capability exists, do not claim to have rendered an image. Deliver a renderer-ready prompt, the intended reference roles, and the complete validation checklist instead. 5. Never require an API key, install a dependency, or switch to an external service without the user's explicit approval.
## Use Image Generation
Use the selected raster capability for exploration and illustration.
When recent reference crops are available:
1. Supply two or three as line-material references. 2. State that their subjects and compositions must be ignored. 3. Generate one direction per call. 4. Compare the result at actual size, not only as a thumbnail. 5. Edit one stroke problem at a time.
When no user references are available, supply the bundled [stroke-calibration.png](assets/stroke-calibration.png). It controls physical pen instability: pressure, drift, missed junctions, overshoots, displaced restarts, broad lurches, retracing, ink deposition, dry breaks, and abrupt terminals. Ignore every shape and layout in the asset. Never copy a swatch as an object, symbol, border, motif, or composition. Keep structural assembly in the text prompt; do not add a second visual reference whose cleaner lines could dilute the material.
Use a bounded decontrol pass when the first readable render remains too competent:
1. Preserve the subject, action, text, composition, hierarchy, and blank space. 2. Change only line construction: break a clean contour, displace one restart, remove conventional detail, and let one structural drift alter the silhouette. 3. Compare before and after at actual size. 4. Keep the edit only when readability survives and the line no longer resembles trained editorial, fashion, or period sketching. Otherwise keep the readable draft and edit one region at a time.
Ask for a photographed or scanned black-pen drawing only when physical stroke texture matters. Keep paper texture subtle and never use it to fake quality.
## Build Logos
1. Explore the mark as a relaxed pen gesture first. 2. Remove narrative detail without sterilizing the line. 3. Create two masters when appropriate: - `expressive master`: preserves pen irregularity for display use; - `production master`: optically tuned SVG for small sizes. 4. Treat generated raster marks as sketches, not finished logos. 5. Reconstruct deliberate vector paths; never auto-trace paper noise. 6. Test one color, reversed color, 24 px, 48 px, and print-size black.
Do not force an illustration line to survive at favicon size by making every stroke thick and geometric.
## Comparative Validation
Validate against at least three recent, same-cluster references. The candidate must pass every primary gate:
- `Physicality`: reads as real pen movement, not a Bézier outline or generic sketch filter. - `Tempo`: contains visible contrast between fast sweeps and slower recognition marks. - `Instability`: at least one structural line visibly loses and recovers control; intended meetings are not all perfectly registered. - `Shorthand`: forms are inferred from decisive fragments rather than fully described. - `Relaxation`: proportions, spacing, anatomy, and terminals feel unforced without turning into uniform noise. - `Transfer`: the line behavior survives the new subject without importing human accessories or source motifs. - `Originality`: no source composition, character, or signature device is reproduced.
For story scenes, add two primary gates:
- `Causality`: the spatial arrangement makes the action and consequence inferable. - `Hierarchy`: scale, crop, density, and empty space clearly prioritize the story without defaulting to balanced staging or realistic perspective.
Secondary gates:
- the intended subject or relationship is inferable; - the composition has a clear movement and quiet release; - texture does not dominate; - the output fits its intended reproduction size.
Fail the result immediately if it is vector-clean, diagrammatic, evenly polished, uniformly wobbly, decoratively distressed, or only recognizable because of labels. Also fail it when most contours arrive exactly where expected, figures read as competent fashion or period illustration, faces and hands are cleanly resolved, or the image could pass as a professional quick sketch with texture added afterward. Visible shoelaces, fingers, pockets, complete facial features,
Source provenance
Decision snapshot
recent repository activity
Audit
Install and adoption review
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Free and open source. Review the report before installing into production agents.
Growth loop
Scenario-led draft for antibes-holiday, ready for a manual X post.
antibes-holiday: Create original relaxed black-pen graphics from concepts or visual references, including spar... 282 stars https://www.openagentskill.com/skills/haorantang97-antibes-holiday?ref=x
Listing + install path for antibes-holiday: https://www.openagentskill.com/skills/haorantang97-antibes-holiday?ref=x Install: npx skills add haorantang97/LabArt --skill antibes-holiday
Listing source
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
This Registry indexed listing is attributed to haorantang97 but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/haorantang97-antibes-holiday?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/haorantang97-antibes-holiday?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/haorantang97-antibes-holiday/audit)
[](https://www.openagentskill.com/skills/haorantang97-antibes-holiday?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)haorantang97
@haorantang97
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Sandbox only
Frontend Design
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
174.2K StarsTaste Skill: Anti-Slop Frontend
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
84.4K StarsCanvas Design
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
174.2K StarsAnthropic Brand Guidelines
Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related artifacts.
174.2K StarsSandbox only
Install targets
Codex install prompt
Install the "antibes-holiday" agent skill from https://github.com/haorantang97/LabArt/tree/main/plugins/antibes-holiday/skills/antibes-holiday. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Create original relaxed black-pen graphics from concepts or visual references, including sparse illustrations, narrative scenes, animals, objects, abstract relationships, icons, and logo marks. Use when the user wants quick hand-drawn line energy, causal story staging, non-equilibrium proportion, shorthand forms, open contours, structural line drift, misregistered junctions, selective retracing, physical pen texture, or a transferable illustration system that must not collapse into clean vector minimalism or polished period-sketch drawing. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"haorantang97-antibes-holiday","task":"Install antibes-holiday","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.Supply asset profile
Design assets, images, video, audio, multimodal media, presentation, and creative production skills.
Scenario
Design and creative
I need my agent to produce design assets, UI directions, presentations, or creative media workflows.
Agent fit
Claude Code + OpenAI Agents + CLI
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add haorantang97/LabArt --skill antibes-holiday
Maintenance
fresh
9d since push
Risk
Needs review
Dependency or permission surface needs review
GitHub quality
282
71/100 Quality · 72/100 Trust
Coverage tags
Review notes
Dependency or permission surface needs review · Permission surface may require sandboxing
Agent adoption scorecard
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
StrongSolid option that is likely worth shortlisting for production workflows.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Needs reviewA machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
OpenAgentSkill Trust Score v5
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
282 GitHub stars
Repo activity
282 stars, 16 forks
Maintenance
9d since push
License
PolyForm-Noncommercial-1.0.0
Install
npx skills add haorantang97/LabArt --skill antibes-holiday
Install safety
Agent-readable metadata
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
Suited agents
Install decision
Trust and risk
Outcome loop
Install command
npx skills add haorantang97/LabArt --skill antibes-holidayDo not use when
Alternative
174.2K Stars
npx skills add anthropics/skills --skill frontend-design
Alternative
84.4K Stars
npx skills add Leonxlnx/taste-skill --skill design-taste-frontend
Alternative
174.2K Stars
npx skills add anthropics/skills --skill canvas-design
Alternative
174.2K Stars
npx skills add anthropics/skills --skill brand-guidelines
Agent safety v2
This skill should not be selected by an agent without explicit human security review.
Do not auto-install. Inspect the source, dependencies, and permission surface first.
high
Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.
medium
Skill may drive a browser or interact with web pages.
medium
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Skill may read or write project files, documents, generated artifacts, or local workspace state.
Agent resolve plan
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Open JSON
/api/agent/resolve?task=Use%20antibes-holiday%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20antibes-holiday%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/haorantang97-antibes-holiday/install
Agent should check
Copy prompt
Task: Use antibes-holiday in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20antibes-holiday%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/haorantang97-antibes-holiday/install
Install command: npx skills add haorantang97/LabArt --skill antibes-holiday
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/haorantang97-antibes-holiday/install
LLM text format
/api/skills/haorantang97-antibes-holiday/install?format=text
Find alternatives
/api/skills/search?q=antibes-holiday&limit=3
Agent prompt
Use antibes-holiday for this task. Review https://www.openagentskill.com/api/skills/haorantang97-antibes-holiday/install, then install with: npx skills add haorantang97/LabArt --skill antibes-holidayRegistry metadata
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/haorantang97-antibes-holiday
LLM text
/api/registry/manifest/haorantang97-antibes-holiday?format=text
Install alias
/api/registry/install/haorantang97-antibes-holiday
Recommend
/api/registry/recommend?task=Use%20antibes-holiday%20in%20an%20agent%20workflow&limit=3
Agent fit
Local desktop
Use-case tags
Platforms
Claude Code, OpenAI Agents
Audit report
A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
Agent decision cockpit
Prototype with this skill first; keep a fallback candidate ready.
Role in stack
Fallback candidate
Primary fit
Local desktop
Trust label
Prototype first
Install path
Command ready
Use when
Evidence
review first
Implementation path
Trust profile
Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
GitHub adoption
INFO282 GitHub stars
Stars/forks activity
CHECK282 stars, 16 forks; issue activity unavailable in current metadata
Recent maintenance
PASS9d since push
License clarity
CHECKPolyForm-Noncommercial-1.0.0 - confirm commercial-use terms
Good signals
Review before install
Recommended action
Run only in a sandbox and compare close alternatives before using it for real work.
Quality profile
Solid option that is likely worth shortlisting for production workflows.
Workflow fit
Operate local tools
I need my agent to operate local files and desktop apps in a repeatable workflow.
Create assets
I need my agent to produce design assets, UI directions, presentations, or creative media workflows.
Search private knowledge
I need my agent to build a RAG workflow over documents and retrieve reliable context.
Workflow fit
Design, build, test, and ship interfaces
A practical workflow for agents that turn product briefs or Figma designs into polished frontend code, review the result, test it in a browser, and prepare a safe deployment.
Operate and verify web apps
A workflow for agents that navigate products, fill forms, take screenshots, and verify real user flows across web applications.
Ingest, retrieve, and cite
A workflow for document-heavy agents that ingest files, create searchable knowledge, retrieve relevant context, and answer with grounded sources.
Alternative shortlist
Similar skills that may fit this task.
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related artifacts.
--- name: antibes-holiday description: Create original relaxed black-pen graphics from concepts or visual references, including sparse illustrations, narrative scenes, animals, objects, abstract relationships, icons, and logo marks. Use when the user wants quick hand-drawn line energy, causal story staging, non-equilibrium proportion, shorthand forms, open contours, structural line drift, misregistered junctions, selective retracing, physical pen texture, or a transferable illustration system that must not collapse into clean vector minimalism or polished period-sketch drawing. license: PolyForm-Noncommercial-1.0.0 ---
# Antibes Holiday
Create original graphics that feel drawn in one alert but lightly unsteady sitting with a real black pen. Prioritize stroke life, tempo, shorthand, structural instability, and the courage to stop. Semantic compression remains useful, but a clean concept never compensates for lines that look professionally controlled.
## Start With Evidence
When references are supplied:
1. Define the target style cluster from stroke material, tempo, omission, density, and composition. 2. Exclude unrelated style clusters from the same reference body. 3. Record dates inside the cluster and weight recent mature work most heavily. 4. Inspect at least three high-weight images at actual size. 5. Separate stroke behavior from recurring subjects and accessories. 6. Use references for line material and gesture only. Never reuse their subject, pose, composition, or signature motif.
Default evidence weighting:
- newest mature same-cluster works: `60%`; - recent supporting same-cluster works: `30%`; - early same-cluster works: `10%`; - different styles or experiments: `0%`.
Read [style-system.md](references/style-system.md) before drawing. Read [prompt-recipes.md](references/prompt-recipes.md) before using an image-generation model.
## Define The Drawing
1. Classify the deliverable: `illustration`, `series`, `icon/badge`, or `logo`. 2. State what must be felt or recognized in one sentence. 3. Choose the subject's most telling action, mass, edge, joint, or relationship. 4. Decide where the drawing should move quickly and where the pen should briefly slow down. 5. Select one dominant sweep and one compact recognition knot. 6. For a scene, identify the `principal actor`, `counterforce`, `narrative hinge`, and the causal path between them. 7. Choose one deliberate scale distortion and one quiet region that carries distance, pause, anticipation, or release. 8. Choose one controlled structural failure: a drifting contour, missed junction, overshoot, displaced restart, incompatible pair of fragments, or abandoned path.
Do not default to a person, face, unrequested character traits, accessories, or anthropomorphism.
## Draw In Three Passes
### Pass 1: Gesture
Draw three fast structural variants.
- Use one to three long sweeps. - Do not close shapes for neatness. - Do not correct proportions yet. - Let at least one sweep drift, lurch, overshoot, or stop before reaching its expected destination. - Permit one to four residual or corrective fragments across an expressive illustration. They must record discovery, not decorate the page. - Reject the prettiest or most anatomically competent variant if it feels designed, trained, or gracefully sketched rather than found while drawing.
### Pass 2: Recognition
Add only the shorthand needed to make the subject legible.
- Use short angular, hooked, wavy, or looping fragments. - Concentrate fragments at the action, contact, or identity knot. - Let large regions remain unnamed. - Omit any boundary the viewer can infer. Do not let one connected contour competently explain the whole form. - Spend conventional detail only when it carries recognition or action. Do not delete so aggressively that the result collapses into a stick symbol. - Distort scale when a hand, tool, opening, joint, shell, edge, or movement carries the idea. - Prefer an implied boundary over a complete outline.
### Pass 3: Pen Life
Restore the physical behavior that image models and vector tools remove.
- Vary pressure and direction unevenly along long sweeps. - Let selected terminals taper, dry out, or stop bluntly. - Add one local retrace or ink-darkened overlap at the recognition knot. - Preserve one broad drift or visible lurch plus smaller speed kinks. - Let one intended junction miss, overlap, or restart slightly displaced. - Keep useful false starts and competing fragments when they show the hand losing and recovering the form. - Concentrate repeated correction and scribbled density at one recognition knot. Outside it, prefer one imperfect attempt over several sketchy alternatives. - Stop before the result becomes clean, balanced, or fully explained.
## Adapt Without Humanizing
- `Living form`: use posture, mass distribution, locomotion, and distinctive anatomy. - `Object`: exaggerate the operational edge, opening, handle, joint, contact, or material path. - `Place`: use one boundary, route, threshold, and scale cue. - `Abstract relationship`: first choose an observable physical metaphor, then express tension, exchange, interruption, growth, or separation through its gesture. Do not draw free-floating lines when the meaning depends on explanation. - `Logo`: begin with a relaxed pen master; derive a separate production vector only after the gesture works.
Do not transfer human facial shorthand to non-human subjects. For human figures, preserve posture and character while withholding clean anatomy. Build the figure from unequal, partially incompatible fragments, with enough local specificity to remain observed rather than diagrammatic.
## Compose Story Scenes
Treat complexity as relationships, not line count.
1. Reduce the event to two or three readable beats. 2. Give each actor a different narrative weight. Scale, crop, and detail may violate realistic perspective when that makes the event clearer. 3. Place one compact `narrative hinge` where intention becomes consequence: contact, exchange, reveal, interruption, impact, or release. 4. Connect the beats with one causal sweep, shared baseline, reach, gaze, object path, or directional gap. Do not add arrows or motion icons. 5. Use unequal information density: describe the principal action, abbreviate supporting actors, and leave the setting largely unstated. 6. Break balance deliberately with one dominant mass, off-center crop, oversized operational feature, displaced small actor, or edge-reaching contour. 7. Let blank paper separate time and distance. Do not fill it with scenery. 8. Stop when the viewer can infer what just happened or is about to happen.
When a scene is humorous, put the humor in disproportion, posture, timing, and physical consequence. Do not explain it with sweat drops, surprise ticks, exclamation marks, speed marks, or other cartoon punctuation unless requested.
Choose a composition family from [style-system.md](references/style-system.md) according to the event. Do not repeat one family across a series by default.
## Select Rendering Capability
Inspect the tools available in the current environment before rendering:
1. In Codex, prefer the system `imagegen` workflow and built-in `image_gen` tool. 2. On another platform, use its native raster generation or editing capability while preserving the reference roles, prompt rules, and validation gates here. 3. If the available tool cannot receive local reference files, use the textual stroke specification and state that the calibration image was not applied. 4. If no image-generation capability exists, do not claim to have rendered an image. Deliver a renderer-ready prompt, the intended reference roles, and the complete validation checklist instead. 5. Never require an API key, install a dependency, or switch to an external service without the user's explicit approval.
## Use Image Generation
Use the selected raster capability for exploration and illustration.
When recent reference crops are available:
1. Supply two or three as line-material references. 2. State that their subjects and compositions must be ignored. 3. Generate one direction per call. 4. Compare the result at actual size, not only as a thumbnail. 5. Edit one stroke problem at a time.
When no user references are available, supply the bundled [stroke-calibration.png](assets/stroke-calibration.png). It controls physical pen instability: pressure, drift, missed junctions, overshoots, displaced restarts, broad lurches, retracing, ink deposition, dry breaks, and abrupt terminals. Ignore every shape and layout in the asset. Never copy a swatch as an object, symbol, border, motif, or composition. Keep structural assembly in the text prompt; do not add a second visual reference whose cleaner lines could dilute the material.
Use a bounded decontrol pass when the first readable render remains too competent:
1. Preserve the subject, action, text, composition, hierarchy, and blank space. 2. Change only line construction: break a clean contour, displace one restart, remove conventional detail, and let one structural drift alter the silhouette. 3. Compare before and after at actual size. 4. Keep the edit only when readability survives and the line no longer resembles trained editorial, fashion, or period sketching. Otherwise keep the readable draft and edit one region at a time.
Ask for a photographed or scanned black-pen drawing only when physical stroke texture matters. Keep paper texture subtle and never use it to fake quality.
## Build Logos
1. Explore the mark as a relaxed pen gesture first. 2. Remove narrative detail without sterilizing the line. 3. Create two masters when appropriate: - `expressive master`: preserves pen irregularity for display use; - `production master`: optically tuned SVG for small sizes. 4. Treat generated raster marks as sketches, not finished logos. 5. Reconstruct deliberate vector paths; never auto-trace paper noise. 6. Test one color, reversed color, 24 px, 48 px, and print-size black.
Do not force an illustration line to survive at favicon size by making every stroke thick and geometric.
## Comparative Validation
Validate against at least three recent, same-cluster references. The candidate must pass every primary gate:
- `Physicality`: reads as real pen movement, not a Bézier outline or generic sketch filter. - `Tempo`: contains visible contrast between fast sweeps and slower recognition marks. - `Instability`: at least one structural line visibly loses and recovers control; intended meetings are not all perfectly registered. - `Shorthand`: forms are inferred from decisive fragments rather than fully described. - `Relaxation`: proportions, spacing, anatomy, and terminals feel unforced without turning into uniform noise. - `Transfer`: the line behavior survives the new subject without importing human accessories or source motifs. - `Originality`: no source composition, character, or signature device is reproduced.
For story scenes, add two primary gates:
- `Causality`: the spatial arrangement makes the action and consequence inferable. - `Hierarchy`: scale, crop, density, and empty space clearly prioritize the story without defaulting to balanced staging or realistic perspective.
Secondary gates:
- the intended subject or relationship is inferable; - the composition has a clear movement and quiet release; - texture does not dominate; - the output fits its intended reproduction size.
Fail the result immediately if it is vector-clean, diagrammatic, evenly polished, uniformly wobbly, decoratively distressed, or only recognizable because of labels. Also fail it when most contours arrive exactly where expected, figures read as competent fashion or period illustration, faces and hands are cleanly resolved, or the image could pass as a professional quick sketch with texture added afterward. Visible shoelaces, fingers, pockets, complete facial features,
Source provenance
Decision snapshot
recent repository activity
Audit
Install and adoption review
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Free and open source. Review the report before installing into production agents.
Growth loop
Scenario-led draft for antibes-holiday, ready for a manual X post.
antibes-holiday: Create original relaxed black-pen graphics from concepts or visual references, including spar... 282 stars https://www.openagentskill.com/skills/haorantang97-antibes-holiday?ref=x
Listing + install path for antibes-holiday: https://www.openagentskill.com/skills/haorantang97-antibes-holiday?ref=x Install: npx skills add haorantang97/LabArt --skill antibes-holiday
Listing source
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
This Registry indexed listing is attributed to haorantang97 but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/haorantang97-antibes-holiday?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/haorantang97-antibes-holiday?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/haorantang97-antibes-holiday/audit)
[](https://www.openagentskill.com/skills/haorantang97-antibes-holiday?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)haorantang97
@haorantang97
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Sandbox only
Frontend Design
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
174.2K StarsTaste Skill: Anti-Slop Frontend
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
84.4K StarsCanvas Design
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
174.2K StarsAnthropic Brand Guidelines
Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related artifacts.
174.2K StarsSandbox only
Install targets
Codex install prompt
Install the "antibes-holiday" agent skill from https://github.com/haorantang97/LabArt/tree/main/plugins/antibes-holiday/skills/antibes-holiday. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Create original relaxed black-pen graphics from concepts or visual references, including sparse illustrations, narrative scenes, animals, objects, abstract relationships, icons, and logo marks. Use when the user wants quick hand-drawn line energy, causal story staging, non-equilibrium proportion, shorthand forms, open contours, structural line drift, misregistered junctions, selective retracing, physical pen texture, or a transferable illustration system that must not collapse into clean vector minimalism or polished period-sketch drawing. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"haorantang97-antibes-holiday","task":"Install antibes-holiday","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.Supply asset profile
Design assets, images, video, audio, multimodal media, presentation, and creative production skills.
Scenario
Design and creative
I need my agent to produce design assets, UI directions, presentations, or creative media workflows.
Agent fit
Claude Code + OpenAI Agents + CLI
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add haorantang97/LabArt --skill antibes-holiday
Maintenance
fresh
9d since push
Risk
Needs review
Dependency or permission surface needs review
GitHub quality
282
71/100 Quality · 72/100 Trust
Coverage tags
Review notes
Dependency or permission surface needs review · Permission surface may require sandboxing
Agent adoption scorecard
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
StrongSolid option that is likely worth shortlisting for production workflows.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Needs reviewA machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
OpenAgentSkill Trust Score v5
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
282 GitHub stars
Repo activity
282 stars, 16 forks
Maintenance
9d since push
License
PolyForm-Noncommercial-1.0.0
Install
npx skills add haorantang97/LabArt --skill antibes-holiday
Install safety
Agent-readable metadata
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
Suited agents
Install decision
Trust and risk
Outcome loop
Install command
npx skills add haorantang97/LabArt --skill antibes-holidayDo not use when
Alternative
174.2K Stars
npx skills add anthropics/skills --skill frontend-design
Alternative
84.4K Stars
npx skills add Leonxlnx/taste-skill --skill design-taste-frontend
Alternative
174.2K Stars
npx skills add anthropics/skills --skill canvas-design
Alternative
174.2K Stars
npx skills add anthropics/skills --skill brand-guidelines
Agent safety v2
This skill should not be selected by an agent without explicit human security review.
Do not auto-install. Inspect the source, dependencies, and permission surface first.
high
Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.
medium
Skill may drive a browser or interact with web pages.
medium
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Skill may read or write project files, documents, generated artifacts, or local workspace state.
Agent resolve plan
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Open JSON
/api/agent/resolve?task=Use%20antibes-holiday%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20antibes-holiday%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/haorantang97-antibes-holiday/install
Agent should check
Copy prompt
Task: Use antibes-holiday in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20antibes-holiday%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/haorantang97-antibes-holiday/install
Install command: npx skills add haorantang97/LabArt --skill antibes-holiday
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/haorantang97-antibes-holiday/install
LLM text format
/api/skills/haorantang97-antibes-holiday/install?format=text
Find alternatives
/api/skills/search?q=antibes-holiday&limit=3
Agent prompt
Use antibes-holiday for this task. Review https://www.openagentskill.com/api/skills/haorantang97-antibes-holiday/install, then install with: npx skills add haorantang97/LabArt --skill antibes-holidayRegistry metadata
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/haorantang97-antibes-holiday
LLM text
/api/registry/manifest/haorantang97-antibes-holiday?format=text
Install alias
/api/registry/install/haorantang97-antibes-holiday
Recommend
/api/registry/recommend?task=Use%20antibes-holiday%20in%20an%20agent%20workflow&limit=3
Agent fit
Local desktop
Use-case tags
Platforms
Claude Code, OpenAI Agents
Audit report
A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
Agent decision cockpit
Prototype with this skill first; keep a fallback candidate ready.
Role in stack
Fallback candidate
Primary fit
Local desktop
Trust label
Prototype first
Install path
Command ready
Use when
Evidence
review first
Implementation path
Trust profile
Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
GitHub adoption
INFO282 GitHub stars
Stars/forks activity
CHECK282 stars, 16 forks; issue activity unavailable in current metadata
Recent maintenance
PASS9d since push
License clarity
CHECKPolyForm-Noncommercial-1.0.0 - confirm commercial-use terms
Good signals
Review before install
Recommended action
Run only in a sandbox and compare close alternatives before using it for real work.
Quality profile
Solid option that is likely worth shortlisting for production workflows.
Workflow fit
Operate local tools
I need my agent to operate local files and desktop apps in a repeatable workflow.
Create assets
I need my agent to produce design assets, UI directions, presentations, or creative media workflows.
Search private knowledge
I need my agent to build a RAG workflow over documents and retrieve reliable context.
Workflow fit
Design, build, test, and ship interfaces
A practical workflow for agents that turn product briefs or Figma designs into polished frontend code, review the result, test it in a browser, and prepare a safe deployment.
Operate and verify web apps
A workflow for agents that navigate products, fill forms, take screenshots, and verify real user flows across web applications.
Ingest, retrieve, and cite
A workflow for document-heavy agents that ingest files, create searchable knowledge, retrieve relevant context, and answer with grounded sources.
Alternative shortlist
Similar skills that may fit this task.
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related artifacts.
--- name: antibes-holiday description: Create original relaxed black-pen graphics from concepts or visual references, including sparse illustrations, narrative scenes, animals, objects, abstract relationships, icons, and logo marks. Use when the user wants quick hand-drawn line energy, causal story staging, non-equilibrium proportion, shorthand forms, open contours, structural line drift, misregistered junctions, selective retracing, physical pen texture, or a transferable illustration system that must not collapse into clean vector minimalism or polished period-sketch drawing. license: PolyForm-Noncommercial-1.0.0 ---
# Antibes Holiday
Create original graphics that feel drawn in one alert but lightly unsteady sitting with a real black pen. Prioritize stroke life, tempo, shorthand, structural instability, and the courage to stop. Semantic compression remains useful, but a clean concept never compensates for lines that look professionally controlled.
## Start With Evidence
When references are supplied:
1. Define the target style cluster from stroke material, tempo, omission, density, and composition. 2. Exclude unrelated style clusters from the same reference body. 3. Record dates inside the cluster and weight recent mature work most heavily. 4. Inspect at least three high-weight images at actual size. 5. Separate stroke behavior from recurring subjects and accessories. 6. Use references for line material and gesture only. Never reuse their subject, pose, composition, or signature motif.
Default evidence weighting:
- newest mature same-cluster works: `60%`; - recent supporting same-cluster works: `30%`; - early same-cluster works: `10%`; - different styles or experiments: `0%`.
Read [style-system.md](references/style-system.md) before drawing. Read [prompt-recipes.md](references/prompt-recipes.md) before using an image-generation model.
## Define The Drawing
1. Classify the deliverable: `illustration`, `series`, `icon/badge`, or `logo`. 2. State what must be felt or recognized in one sentence. 3. Choose the subject's most telling action, mass, edge, joint, or relationship. 4. Decide where the drawing should move quickly and where the pen should briefly slow down. 5. Select one dominant sweep and one compact recognition knot. 6. For a scene, identify the `principal actor`, `counterforce`, `narrative hinge`, and the causal path between them. 7. Choose one deliberate scale distortion and one quiet region that carries distance, pause, anticipation, or release. 8. Choose one controlled structural failure: a drifting contour, missed junction, overshoot, displaced restart, incompatible pair of fragments, or abandoned path.
Do not default to a person, face, unrequested character traits, accessories, or anthropomorphism.
## Draw In Three Passes
### Pass 1: Gesture
Draw three fast structural variants.
- Use one to three long sweeps. - Do not close shapes for neatness. - Do not correct proportions yet. - Let at least one sweep drift, lurch, overshoot, or stop before reaching its expected destination. - Permit one to four residual or corrective fragments across an expressive illustration. They must record discovery, not decorate the page. - Reject the prettiest or most anatomically competent variant if it feels designed, trained, or gracefully sketched rather than found while drawing.
### Pass 2: Recognition
Add only the shorthand needed to make the subject legible.
- Use short angular, hooked, wavy, or looping fragments. - Concentrate fragments at the action, contact, or identity knot. - Let large regions remain unnamed. - Omit any boundary the viewer can infer. Do not let one connected contour competently explain the whole form. - Spend conventional detail only when it carries recognition or action. Do not delete so aggressively that the result collapses into a stick symbol. - Distort scale when a hand, tool, opening, joint, shell, edge, or movement carries the idea. - Prefer an implied boundary over a complete outline.
### Pass 3: Pen Life
Restore the physical behavior that image models and vector tools remove.
- Vary pressure and direction unevenly along long sweeps. - Let selected terminals taper, dry out, or stop bluntly. - Add one local retrace or ink-darkened overlap at the recognition knot. - Preserve one broad drift or visible lurch plus smaller speed kinks. - Let one intended junction miss, overlap, or restart slightly displaced. - Keep useful false starts and competing fragments when they show the hand losing and recovering the form. - Concentrate repeated correction and scribbled density at one recognition knot. Outside it, prefer one imperfect attempt over several sketchy alternatives. - Stop before the result becomes clean, balanced, or fully explained.
## Adapt Without Humanizing
- `Living form`: use posture, mass distribution, locomotion, and distinctive anatomy. - `Object`: exaggerate the operational edge, opening, handle, joint, contact, or material path. - `Place`: use one boundary, route, threshold, and scale cue. - `Abstract relationship`: first choose an observable physical metaphor, then express tension, exchange, interruption, growth, or separation through its gesture. Do not draw free-floating lines when the meaning depends on explanation. - `Logo`: begin with a relaxed pen master; derive a separate production vector only after the gesture works.
Do not transfer human facial shorthand to non-human subjects. For human figures, preserve posture and character while withholding clean anatomy. Build the figure from unequal, partially incompatible fragments, with enough local specificity to remain observed rather than diagrammatic.
## Compose Story Scenes
Treat complexity as relationships, not line count.
1. Reduce the event to two or three readable beats. 2. Give each actor a different narrative weight. Scale, crop, and detail may violate realistic perspective when that makes the event clearer. 3. Place one compact `narrative hinge` where intention becomes consequence: contact, exchange, reveal, interruption, impact, or release. 4. Connect the beats with one causal sweep, shared baseline, reach, gaze, object path, or directional gap. Do not add arrows or motion icons. 5. Use unequal information density: describe the principal action, abbreviate supporting actors, and leave the setting largely unstated. 6. Break balance deliberately with one dominant mass, off-center crop, oversized operational feature, displaced small actor, or edge-reaching contour. 7. Let blank paper separate time and distance. Do not fill it with scenery. 8. Stop when the viewer can infer what just happened or is about to happen.
When a scene is humorous, put the humor in disproportion, posture, timing, and physical consequence. Do not explain it with sweat drops, surprise ticks, exclamation marks, speed marks, or other cartoon punctuation unless requested.
Choose a composition family from [style-system.md](references/style-system.md) according to the event. Do not repeat one family across a series by default.
## Select Rendering Capability
Inspect the tools available in the current environment before rendering:
1. In Codex, prefer the system `imagegen` workflow and built-in `image_gen` tool. 2. On another platform, use its native raster generation or editing capability while preserving the reference roles, prompt rules, and validation gates here. 3. If the available tool cannot receive local reference files, use the textual stroke specification and state that the calibration image was not applied. 4. If no image-generation capability exists, do not claim to have rendered an image. Deliver a renderer-ready prompt, the intended reference roles, and the complete validation checklist instead. 5. Never require an API key, install a dependency, or switch to an external service without the user's explicit approval.
## Use Image Generation
Use the selected raster capability for exploration and illustration.
When recent reference crops are available:
1. Supply two or three as line-material references. 2. State that their subjects and compositions must be ignored. 3. Generate one direction per call. 4. Compare the result at actual size, not only as a thumbnail. 5. Edit one stroke problem at a time.
When no user references are available, supply the bundled [stroke-calibration.png](assets/stroke-calibration.png). It controls physical pen instability: pressure, drift, missed junctions, overshoots, displaced restarts, broad lurches, retracing, ink deposition, dry breaks, and abrupt terminals. Ignore every shape and layout in the asset. Never copy a swatch as an object, symbol, border, motif, or composition. Keep structural assembly in the text prompt; do not add a second visual reference whose cleaner lines could dilute the material.
Use a bounded decontrol pass when the first readable render remains too competent:
1. Preserve the subject, action, text, composition, hierarchy, and blank space. 2. Change only line construction: break a clean contour, displace one restart, remove conventional detail, and let one structural drift alter the silhouette. 3. Compare before and after at actual size. 4. Keep the edit only when readability survives and the line no longer resembles trained editorial, fashion, or period sketching. Otherwise keep the readable draft and edit one region at a time.
Ask for a photographed or scanned black-pen drawing only when physical stroke texture matters. Keep paper texture subtle and never use it to fake quality.
## Build Logos
1. Explore the mark as a relaxed pen gesture first. 2. Remove narrative detail without sterilizing the line. 3. Create two masters when appropriate: - `expressive master`: preserves pen irregularity for display use; - `production master`: optically tuned SVG for small sizes. 4. Treat generated raster marks as sketches, not finished logos. 5. Reconstruct deliberate vector paths; never auto-trace paper noise. 6. Test one color, reversed color, 24 px, 48 px, and print-size black.
Do not force an illustration line to survive at favicon size by making every stroke thick and geometric.
## Comparative Validation
Validate against at least three recent, same-cluster references. The candidate must pass every primary gate:
- `Physicality`: reads as real pen movement, not a Bézier outline or generic sketch filter. - `Tempo`: contains visible contrast between fast sweeps and slower recognition marks. - `Instability`: at least one structural line visibly loses and recovers control; intended meetings are not all perfectly registered. - `Shorthand`: forms are inferred from decisive fragments rather than fully described. - `Relaxation`: proportions, spacing, anatomy, and terminals feel unforced without turning into uniform noise. - `Transfer`: the line behavior survives the new subject without importing human accessories or source motifs. - `Originality`: no source composition, character, or signature device is reproduced.
For story scenes, add two primary gates:
- `Causality`: the spatial arrangement makes the action and consequence inferable. - `Hierarchy`: scale, crop, density, and empty space clearly prioritize the story without defaulting to balanced staging or realistic perspective.
Secondary gates:
- the intended subject or relationship is inferable; - the composition has a clear movement and quiet release; - texture does not dominate; - the output fits its intended reproduction size.
Fail the result immediately if it is vector-clean, diagrammatic, evenly polished, uniformly wobbly, decoratively distressed, or only recognizable because of labels. Also fail it when most contours arrive exactly where expected, figures read as competent fashion or period illustration, faces and hands are cleanly resolved, or the image could pass as a professional quick sketch with texture added afterward. Visible shoelaces, fingers, pockets, complete facial features,
Source provenance
Decision snapshot
recent repository activity
Audit
Install and adoption review
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Free and open source. Review the report before installing into production agents.
Growth loop
Scenario-led draft for antibes-holiday, ready for a manual X post.
antibes-holiday: Create original relaxed black-pen graphics from concepts or visual references, including spar... 282 stars https://www.openagentskill.com/skills/haorantang97-antibes-holiday?ref=x
Listing + install path for antibes-holiday: https://www.openagentskill.com/skills/haorantang97-antibes-holiday?ref=x Install: npx skills add haorantang97/LabArt --skill antibes-holiday
Listing source
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
This Registry indexed listing is attributed to haorantang97 but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/haorantang97-antibes-holiday?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/haorantang97-antibes-holiday?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/haorantang97-antibes-holiday/audit)
[](https://www.openagentskill.com/skills/haorantang97-antibes-holiday?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)haorantang97
@haorantang97
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Sandbox only
Frontend Design
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
174.2K StarsTaste Skill: Anti-Slop Frontend
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
84.4K StarsCanvas Design
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
174.2K StarsAnthropic Brand Guidelines
Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related artifacts.
174.2K StarsPermission surface
secrets or environment access, shell or command execution
Agent outcomes
No agent outcome data yet
Docs
Strong README/SKILL.md context
Risk summary
Install readiness
Permission surface
secrets or environment access, shell or command execution
Agent outcomes
No agent outcome data yet
Docs
Strong README/SKILL.md context
Risk summary
Install readiness
Permission surface
secrets or environment access, shell or command execution
Agent outcomes
No agent outcome data yet
Docs
Strong README/SKILL.md context
Risk summary
Install readiness
Permission surface
secrets or environment access, shell or command execution
Agent outcomes
No agent outcome data yet
Docs
Strong README/SKILL.md context
Risk summary
Install readiness