Codex skill for editable draw.io graphical abstracts and manuscript concept figures
Supply asset profile
Deep research, source comparison, literature review, RAG, knowledge search, and reports.
Scenario
RAG and knowledge
I need my agent to build a RAG workflow over documents and retrieve reliable context.
Agent fit
Claude Code + OpenAI Agents + CLI
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add keros68/abstract-fig
Maintenance
fresh
2d since push
Risk
Needs review
Low GitHub adoption signal
GitHub quality
16
70/100 quality · 74/100 trust
Coverage tags
Review notes
Low GitHub adoption signal · Quality score needs review
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 reviewInstall readiness, security metadata, maintenance, and adoption risk.
Trust Score v5
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
16 GitHub stars
Repo activity
16 stars, 1 forks
Maintenance
2d since push
License
MIT
Install
npx skills add keros68/abstract-fig
Install safety
standard package or runtime install path
Permission surface
shell or command execution, filesystem or document access
Agent outcomes
No agent outcome data yet
Docs
Strong README/SKILL.md context
Risk summary
Install readiness
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
Do not use when
Alternative
163.5K stars
npx skills add anthropics/skills --skill frontend-design
Alternative
16.5K stars
npx skills@latest add emilkowalski/skills
Alternative
98.4K stars
npx skills add mui/material-ui
Alternative
163.5K stars
npx skills add anthropics/skills --skill canvas-design
Agent safety v2
Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
Test manually in an isolated workspace and compare against safer alternatives.
high
Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.
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.
Install targets
Copy the registry command or an agent-specific install prompt for Codex, Claude Code, and Cursor.
Use the registry command when your workflow supports the OpenAgentSkill installer.
$ npx skills add keros68/abstract-figAgent 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.
Resolve JSON
/api/agent/resolve?task=Use%20Abstract%20Fig%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20Abstract%20Fig%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/keros68-abstract-fig/install
Agent should check
Copy prompt
Task: Use Abstract Fig in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20Abstract%20Fig%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/keros68-abstract-fig/install
Install command: npx skills add keros68/abstract-fig
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/keros68-abstract-fig/install
LLM text format
/api/skills/keros68-abstract-fig/install?format=text
Find alternatives
/api/skills/search?q=Abstract%20Fig&limit=3
Agent prompt
Use Abstract Fig for this task. Review https://www.openagentskill.com/api/skills/keros68-abstract-fig/install, then install with: npx skills add keros68/abstract-figRegistry 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/keros68-abstract-fig
LLM text
/api/registry/manifest/keros68-abstract-fig?format=text
Install alias
/api/registry/install/keros68-abstract-fig
Recommend
/api/registry/recommend?task=Use%20Abstract%20Fig%20in%20an%20agent%20workflow&limit=3
Agent fit
Design and creative
Use-case tags
Platforms
Python, Claude Code, OpenAI Agents
Audit report
Review install readiness, maintenance, trust, quality, and metadata warnings before adding this skill to an agent workflow.
Agent decision cockpit
Prototype with this skill first; keep a fallback candidate ready.
Role in stack
Fallback candidate
Primary fit
Design and creative
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
FIX16 GitHub stars
Stars/forks activity
FIX16 stars, 1 forks; issue activity unavailable in current metadata
Recent maintenance
PASS2d since push
License clarity
PASSMIT
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
Create assets
I need my agent to produce design assets, UI directions, presentations, or creative media workflows.
Build and ship code
I need a coding agent that can understand a repository, edit code, and review pull requests.
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.
Inspect, patch, and verify code
A workflow for software agents that inspect repositories, review pull requests, generate tests, and turn findings into shippable patches.
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 in this category, ranked with the same readiness and quality signals.
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and wants the right word to prompt an AI or designer with. For naming an effect, not designing or building one.
Material UI: Comprehensive React component library that implements Google's Material Design. Free forever.
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
# Abstract-Fig
生成可编辑论文图形摘要和概念模型图的 Codex skill:先用 Codex 里的 image2 制作论文主题元素,拆分为独立透明 PNG,嵌入 draw.io,文字框、箭头、边框、分组和标签全部保持可编辑。
目标不是一张不可编辑的 AI 大图,而是一个能在 draw.io 里继续拖拽、改字、换元素、调版面的 `.drawio` 文件。适合投稿论文的 graphical abstract、机制概念图、方法流程图和综合示意图。
> 中文为主,English version below.
[](LICENSE) [](SKILL.md) [](https://app.diagrams.net/)
## 运行要求
只面向 Codex:完整流程依赖 Codex 里的 image2 生图能力。其他 agent 可以参考 `SKILL.md` 的流程思路,但没有 image2 或等价的生图与文件处理能力,就复现不了"生成元素 → 拆分元素 → 嵌入 draw.io"这条链。
## 使用场景
- 已有论文主线、审稿意见或修改建议,要转成正文概念图或 graphical abstract。 - 需要"图片元素 + 可编辑文字框 + 可编辑箭头"的投稿图,而不是整张贴图。 - 普通流程图太像模板,想加入含水介质、河流、农田、采样井、仪器、地貌等论文主题元素。 - 把已有草图或 draw.io 文件改成适合期刊正文的 boxed manuscript style。
## 功能
从论文内容提炼图件主线(如 `setting -> process/media -> evidence -> status/output`),判断图件类型,生图前先给出绘制方案供选择(agent 自主判断、风格菜单或自定义要求)。生成或复用 image2 元素表,把元素拆成多个透明 PNG,逐个作为独立图片对象嵌入 draw.io;科学逻辑用可编辑的文字框、分区框、箭头和标签表达。默认白底、细边框、少量配色、大字号,并检查压盖、箭头穿字、小字号、A4 缩放后不可读等常见排版问题。
交付物:一个 `.drawio` 文件 + `elements/` 透明 PNG 元素文件夹,外加嵌入检查结果和微调建议。默认不导出 PNG/PDF/SVG——先在 draw.io 里调到满意,再按期刊要求导出。
## 边界
- 不把整张 AI 生成图直接当成最终 draw.io 图。 - PNG 元素内部不能像矢量图一样逐笔编辑;可编辑的是元素位置、大小、替换关系,以及所有文字、边框、箭头和标签。 - 不凭空强化论文机制,不把概念假设画成已证实结论。 - 不替代作者对科学术语、图注、投稿格式和最终分辨率的人工复核。 - 元素质量取决于 image2 生成与拆分效果,复杂背景、阴影和细线可能要手动清理;投稿前建议导出 PDF 按 A4 或期刊栏宽再查一遍。
## 快速开始
在 Codex 里发送:
```text 请从 GitHub 安装这个 skill,并在之后需要制作论文 graphical abstract、概念模型图或可编辑 draw.io 投稿图时优先使用它: https://github.com/keros68/abstract-fig ```
装完重启或新开窗口:
```text 使用 $abstract-fig 根据这篇论文主线做一张可编辑 draw.io 图形摘要,要求先生成主题元素,再拆分嵌入到 draw.io。 ```
手动安装:
```bash git clone https://github.com/keros68/abstract-fig.git ~/.codex/skills/abstract-fig ```
做好的 `.drawio` 文件拖进 [draw.io 官方编辑器](https://app.diagrams.net/) 即可继续编辑;网页询问保存位置时选本地存储。
## 文件结构
- `SKILL.md` - skill 主说明和触发规则。 - `references/figure-types.md` - 图件类型选择规则。 - `referen
Frameworks & Tools
Decision snapshot
recent repository activity
Audit snapshot
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 audit before production use.
Growth loop
Scenario-led draft for Abstract Fig, ready for a manual X post.
The useful research skills are not search wrappers. They help agents keep sources attached. Abstract Fig helps agents turn docs, data, or knowledge bases into grounded work. 16 stars https://www.openagentskill.com/skills/keros68-abstract-fig?ref=x #AIAgents
Listing + install path for Abstract Fig: https://www.openagentskill.com/skills/keros68-abstract-fig?ref=x Install: npx skills add keros68/abstract-fig
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 community indexed listing is attributed to keros68 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/keros68-abstract-fig)
[](https://www.openagentskill.com/skills/keros68-abstract-fig)
[](https://www.openagentskill.com/skills/keros68-abstract-fig/audit)
[](https://www.openagentskill.com/skills/keros68-abstract-fig)keros68
@keros68
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.
163.5K stars · 0 installsAnimation Vocabulary
Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and wants the right word to prompt an AI or designer with. For naming an effect, not designing or building one.
16.5K stars · 0 installsMaterial Ui
Material UI: Comprehensive React component library that implements Google's Material Design. Free forever.
98.4K stars · 0 installsCanvas Design
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
163.5K stars · 0 installs