Skill rankings
Best Codex skills for AI agents
Reusable skills and workflows that fit Codex-style coding, repository inspection, testing, automation, and install handoffs.
Shown: 30 · Candidates: 471
Compare top 4- 01
Vox Director
Turn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.
@Alisa0808Design2,207Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 67/100
- Quality
- 100/100
- Freshness
- 89/100
- Agent evidence
- 80/100
- Evidence confidence
- 94/100
- Install readiness
- 100/100
- Task fit
- 100/100
- 02
Canvas Design
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
@anthropicsDesign180,366Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 100/100
- Quality
- 100/100
- Freshness
- 97/100
- Agent evidence
- 77/100
- Evidence confidence
- 85/100
- Install readiness
- 100/100
- Task fit
- 100/100
- 03
Web Design Guidelines
Review UI code for web interface guidelines, UX quality, accessibility, and interaction design best practices.
@vercel-labsDesign32,187Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 90/100
- Quality
- 100/100
- Freshness
- 12/100
- Agent evidence
- 77/100
- Evidence confidence
- 83/100
- Install readiness
- 100/100
- Task fit
- 100/100
- 04
unslop
Applies Cursor's prose-discipline rules to remove filler and AI writing tells from agent-facing and user-facing text.
@cursorProductivity4,829Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 74/100
- Quality
- 100/100
- Freshness
- 93/100
- Agent evidence
- 75/100
- Evidence confidence
- 79/100
- Install readiness
- 87/100
- Task fit
- 100/100
- 05
Guizang Ppt Skill
AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime.
@op7418Agent Skills24,929Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 88/100
- Quality
- 100/100
- Freshness
- 8/100
- Agent evidence
- 74/100
- Evidence confidence
- 76/100
- Install readiness
- 100/100
- Task fit
- 100/100
- 06
Webapp Testing
Use Playwright to interact with and test local web applications, capture screenshots, debug UI behavior, and inspect browser logs.
@anthropicsBrowser Automation180,366Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 100/100
- Quality
- 100/100
- Freshness
- 97/100
- Agent evidence
- 73/100
- Evidence confidence
- 69/100
- Install readiness
- 100/100
- Task fit
- 100/100
- 07
Frontend Design
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
@anthropicsDesign180,366Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 100/100
- Quality
- 100/100
- Freshness
- 97/100
- Agent evidence
- 69/100
- Evidence confidence
- 94/100
- Install readiness
- 68/100
- Task fit
- 100/100
- 08
Apple Design
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces.
@emilkowalskiDesign34,452Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 91/100
- Quality
- 100/100
- Freshness
- 0/100
- Agent evidence
- 69/100
- Evidence confidence
- 60/100
- Install readiness
- 100/100
- Task fit
- 100/100
- 09
Open Design
🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design Systems 🖼️ Web · desktop · mobile prototypes · slides · images · videos · HyperFrames 📦 Sandboxed preview · HTML/PDF/PPTX/MP4 export 🤖 Claude Code / OpenClaw / Codex / Cursor / OpenCode / Qwen / Copilot / Hermes / Kimi & 17+ CLIs.
@nexu-ioAgent Skills88,117Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 99/100
- Quality
- 100/100
- Freshness
- 0/100
- Agent evidence
- 67/100
- Evidence confidence
- 69/100
- Install readiness
- 92/100
- Task fit
- 100/100
- 10
Taste Skill: Anti-Slop Frontend
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
@LeonxlnxDesign94,461Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 100/100
- Quality
- 100/100
- Freshness
- 97/100
- Agent evidence
- 66/100
- Evidence confidence
- 100/100
- Install readiness
- 68/100
- Task fit
- 100/100
- 11
Equity Research Earnings Analysis
Create a structured post-earnings equity research update with key metrics, estimate changes, charts, and thesis review.
@anthropicsFinance39,310Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 92/100
- Quality
- 100/100
- Freshness
- 61/100
- Agent evidence
- 63/100
- Evidence confidence
- 47/100
- Install readiness
- 90/100
- Task fit
- 100/100
- 12
Code Review
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
@mattpocockCoding168,580Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 100/100
- Quality
- 100/100
- Freshness
- 0/100
- Agent evidence
- 61/100
- Evidence confidence
- 49/100
- Install readiness
- 100/100
- Task fit
- 100/100
- 13
Anthropic Brand Guidelines
Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related artifacts.
@anthropicsDesign180,366Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 100/100
- Quality
- 100/100
- Freshness
- 97/100
- Agent evidence
- 57/100
- Evidence confidence
- 44/100
- Install readiness
- 100/100
- Task fit
- 100/100
- 14
Figma Implement Design
Translate Figma designs into production-ready UI code with close visual fidelity and component-level detail.
@openaiDesign27,985Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 89/100
- Quality
- 100/100
- Freshness
- 35/100
- Agent evidence
- 57/100
- Evidence confidence
- 44/100
- Install readiness
- 100/100
- Task fit
- 100/100
- 15
Understand Anything
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
@Egonex-AIRag Knowledge75,065Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 98/100
- Quality
- 100/100
- Freshness
- 0/100
- Agent evidence
- 57/100
- Evidence confidence
- 44/100
- Install readiness
- 100/100
- Task fit
- 100/100
- 16
Seedance 2.0 Prompt Writing
Write precise Seedance 2.0 prompts for multimodal video, camera movement, editing, music, and product storytelling.
@dexhunterDesign4,244Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 73/100
- Quality
- 100/100
- Freshness
- 57/100
- Agent evidence
- 51/100
- Evidence confidence
- 37/100
- Install readiness
- 100/100
- Task fit
- 100/100
- 17
Marketingskills
Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.
@coreyhaines31Development40,608Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 92/100
- Quality
- 100/100
- Freshness
- 0/100
- Agent evidence
- 51/100
- Evidence confidence
- 37/100
- Install readiness
- 100/100
- Task fit
- 100/100
- 18
Animation 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.
@emilkowalskiDesign16,544Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 84/100
- Quality
- 100/100
- Freshness
- 0/100
- Agent evidence
- 51/100
- Evidence confidence
- 22/100
- Install readiness
- 100/100
- Task fit
- 100/100
- 19
Humanizer
Rewrites AI-sounding text so it reads naturally while preserving every factual claim and matching the writer's voice.
@bladerProductivity37,414Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 92/100
- Quality
- 100/100
- Freshness
- 0/100
- Agent evidence
- 50/100
- Evidence confidence
- 31/100
- Install readiness
- 100/100
- Task fit
- 100/100
- 20
Hallmark
Anti-AI-slop design skill for Claude Code, Cursor, and Codex.
@NutlopeDevelopment27,701Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 89/100
- Quality
- 100/100
- Freshness
- 0/100
- Agent evidence
- 50/100
- Evidence confidence
- 31/100
- Install readiness
- 100/100
- Task fit
- 100/100
- 21
Shuohao Skills
A collection of agent skills for AI short-drama production, covering character bibles, outlines, art bibles, scripts, and storyboards, designed for Claude Code and Codex.
@eternityspringDesign1,566Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 64/100
- Quality
- 100/100
- Freshness
- 0/100
- Agent evidence
- 50/100
- Evidence confidence
- 31/100
- Install readiness
- 100/100
- Task fit
- 100/100
- 22
Obsidian Second Brain
Cross-CLI skill for Obsidian: turn your vault into a living AI-first second brain across Claude Code, Codex, Gemini, and OpenCode. 43 commands - now with /obsidian-architect to document your codebase, key-less web research, Google Calendar, and self-rewriting notes.
@eugeniughelburAgent Frameworks4,294Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 73/100
- Quality
- 100/100
- Freshness
- 21/100
- Agent evidence
- 48/100
- Evidence confidence
- 31/100
- Install readiness
- 100/100
- Task fit
- 100/100
- 23
stop-slop
Eliminates predictable AI writing patterns from prose while preserving specific meaning and reader trust.
@hardikpandyaProductivity16,263Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 84/100
- Quality
- 100/100
- Freshness
- 80/100
- Agent evidence
- 46/100
- Evidence confidence
- 57/100
- Install readiness
- 84/100
- Task fit
- 100/100
- 24
Portfolio Monitoring
Review portfolio-company financial packages, flag variance to plan, and prepare monitored KPI summaries.
@anthropicsFinance39,310Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 92/100
- Quality
- 100/100
- Freshness
- 61/100
- Agent evidence
- 42/100
- Evidence confidence
- 22/100
- Install readiness
- 90/100
- Task fit
- 100/100
- 25
3-Statement Financial Model
Complete and link income statement, balance sheet, and cash flow statement model templates with formulas and checks.
@anthropicsFinance39,310Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 92/100
- Quality
- 100/100
- Freshness
- 61/100
- Agent evidence
- 42/100
- Evidence confidence
- 22/100
- Install readiness
- 90/100
- Task fit
- 100/100
- 26
Vercel React Best Practices
React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.
@vercel-labsCoding32,187Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 90/100
- Quality
- 100/100
- Freshness
- 12/100
- Agent evidence
- 42/100
- Evidence confidence
- 22/100
- Install readiness
- 100/100
- Task fit
- 100/100
- 27
Implement
Implement work from an approved spec or ticket set, run focused and full tests, invoke code review, and commit the result to the current branch.
@mattpocockCoding175,741Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 100/100
- Quality
- 100/100
- Freshness
- 0/100
- Agent evidence
- 42/100
- Evidence confidence
- 22/100
- Install readiness
- 100/100
- Task fit
- 100/100
- 28
no-ai-slop
Audits or minimally edits drafts to remove named AI-writing patterns without flattening the author's voice.
@petergyangProductivity5,828Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 75/100
- Quality
- 100/100
- Freshness
- 20/100
- Agent evidence
- 42/100
- Evidence confidence
- 22/100
- Install readiness
- 100/100
- Task fit
- 100/100
- 29
Scientific Agent Skills
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 160,000+ scientists worldwide. 140 ready-to-use skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
@K-Dense-AIData Analysis33,491Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 91/100
- Quality
- 100/100
- Freshness
- 0/100
- Agent evidence
- 42/100
- Evidence confidence
- 22/100
- Install readiness
- 100/100
- Task fit
- 100/100
- 30
Baoyu Skills
JimLiu/baoyu-skills is a high-star GitHub project relevant to AI agent workflows.
@JimLiuAgent Skills23,352Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 87/100
- Quality
- 100/100
- Freshness
- 0/100
- Agent evidence
- 42/100
- Evidence confidence
- 22/100
- Install readiness
- 87/100
- Task fit
- 100/100
A shortlist from up to 480 directory candidates, not the entire registry. Stars belong to repositories. Signals are not safety guarantees or runtime verification.
How this list works
Uses explicit platform mentions or inferred task fit, plus quality and outcome evidence. Inferred compatibility is not a runtime test.
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
30-day snapshot data