Skill rankings
Safest AI agent skills for auto install
Skills with strong Trust Score, safe install paths, low risk blocks, clear licenses, and low setup friction.
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
- 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
- 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
- 04
mono-color
Generate original one-ink or controlled two-ink editorial images from any theme, sentence, article idea, object, or reference photo. Always use this skill when the user asks for 单色海报、双色印刷、单色调视觉、蓝色/绿色孔版印刷、risograph、网点照片、复古或当代编辑排版、zine poster, monochrome editorial poster, duotone print, or asks to use the mono-color style. It uses an adaptive white, gray, or pale-beige substrate, no more than two printing inks, active negative space, terse human language, and strong serif/grotesk/mono typography without making retro styling the default or copying a source composition, wording, logo, or artwork. Produce both the final generation prompt and the generated raster image unless the user explicitly asks for prompt only.
@yanliudesignResearch1,919Review 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
- 66/100
- Quality
- 100/100
- Freshness
- 19/100
- Agent evidence
- 80/100
- Evidence confidence
- 94/100
- Install readiness
- 90/100
- 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
- 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
- 07
Archify
Any agent Skill: generate beautiful architecture diagrams with dark/light theme toggle and PNG/JPEG/WebP/SVG export
@tt-a1iAgent Skills47,183Review 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
- 94/100
- Quality
- 100/100
- Freshness
- 26/100
- Agent evidence
- 75/100
- Evidence confidence
- 79/100
- Install readiness
- 90/100
- 08
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
- 09
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
- 10
Superpowers
An agentic skills framework & software development methodology that works.
@obraAgent Skills257,155Review 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
- 69/100
- Evidence confidence
- 73/100
- Install readiness
- 92/100
- 11
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
- 12
Frontend Slides
Create beautiful slides on the web using a coding agent's frontend skills
@zarazhangruiCoding28,772Review 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
- 67/100
- Evidence confidence
- 65/100
- Install readiness
- 92/100
- 13
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
- 14
Ui Ux Pro Max Skill
An AI agent skill that provides design intelligence and UI/UX guidelines for building professional interfaces across multiple platforms.
@nextlevelbuilderDevelopment107,051Review 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
- 63/100
- Evidence confidence
- 60/100
- Install readiness
- 92/100
- 15
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
- 16
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
- 17
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
- 18
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
- 19
Andrej Karpathy Skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
@multica-aiDevelopment175,191Review 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
- 63/100
- Evidence confidence
- 47/100
- Install readiness
- 87/100
- 20
Crawlee
Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation.
@apifyBrowser Automation25,731Review 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
- 38/100
- Agent evidence
- 59/100
- Evidence confidence
- 51/100
- Install readiness
- 92/100
- 21
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
- 22
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
- 23
Aaron Marketing Skills
A comprehensive set of 38 marketing skills and 5 commands for Claude Code covering SEO/GEO and influencer marketing with evaluation frameworks.
@aaron-he-zhuProductivity2,578Review 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
- 68/100
- Quality
- 100/100
- Freshness
- 0/100
- Agent evidence
- 51/100
- Evidence confidence
- 37/100
- Install readiness
- 100/100
- 24
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
- 25
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
- 26
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
- 27
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
- 28
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
- 29
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
- 30
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
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
Combines installation metadata and outcome evidence, accounting for reported risk and setup friction. It does not authorize automatic installation.
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