Install safety
Skills with strong Trust Score, safe install paths, low risk blocks, clear licenses, and low setup friction.
Daily snapshot: Aug 22, 2026, 2:55 AM UTC
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
Early agent signal: 2 outcomes, 100% success, Agent Proven Score 51/100. 0 risk blocks and 0 setup-required reports.
$ npx skills add anthropics/skills --skill frontend-designReverse-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.
Early agent signal: 1 outcome, 100% success, Agent Proven Score 51/100. 0 risk blocks and 0 setup-required reports.
$ npx skills@latest add emilkowalski/skillsCross-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.
Early agent signal: 2 outcomes, 100% success, Agent Proven Score 48/100. 0 risk blocks and 0 setup-required reports.
$ npx skills add eugeniughelbur/obsidian-second-brainRun multimodal agents that operate desktop interfaces
Early agent signal: 1 outcome, 100% success, Agent Proven Score 42/100. 0 risk blocks and 0 setup-required reports.
$ npx skills add bytedance/UI-TARS-desktopAny agent Skill: generate beautiful architecture diagrams with dark/light theme toggle and PNG/JPEG/WebP/SVG export
Early agent signal: 1 outcome, 100% success, Agent Proven Score 42/100. 0 risk blocks and 0 setup-required reports.
$ npx skills add tt-a1i/archify中文小黑怪诞正文配图生成 Skill | 16:9 白底手绘 | 少量红橙蓝批注 | Codex Skill
Early agent signal: 1 outcome, 100% success, Agent Proven Score 42/100. 0 risk blocks and 0 setup-required reports.
$ npx skills add helloianneo/ian-xiaohei-illustrationsA comprehensive set of 38 marketing skills and 5 commands for Claude Code covering SEO/GEO and influencer marketing with evaluation frameworks.
Early agent signal: 1 outcome, 100% success, Agent Proven Score 42/100. 0 risk blocks and 0 setup-required reports.
$ npx skills add aaron-he-zhu/aaron-marketing-skillsTurn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.
Early agent signal: 1 outcome, 100% success, Agent Proven Score 42/100. 0 risk blocks and 0 setup-required reports.
$ npx skills add Alisa0808/vox-director --skill vox-directorDesign and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
Early agent signal: 2 outcomes, 50% success, Agent Proven Score 33/100. 0 risk blocks and 0 setup-required reports.
$ npx skills add Leonxlnx/taste-skill --skill design-taste-frontendTongyi Deep Research, the Leading Open-source Deep Research Agent
Early agent signal: 1 outcome, 0% success, Agent Proven Score 24/100. 0 risk blocks and 0 setup-required reports.
$ npx skills add Alibaba-NLP/DeepResearchProduction-grade engineering skills for AI coding agents.
Early agent signal: 1 outcome, 0% success, Agent Proven Score 19/100. 0 risk blocks and 0 setup-required reports.
$ npx skills add addyosmani/agent-skillsAn agentic skills framework & software development methodology that works.
Excellent quality, 257K stars, and no reported agent risk blocks yet.
$ npx skills add obra/superpowersBreak a plan, spec, or conversation into independently actionable tracer-bullet tickets with explicit blocking relationships.
Excellent quality, 177K stars, and no reported agent risk blocks yet.
$ npx skills add mattpocock/skills --skill to-ticketsImplement work from an approved spec or ticket set, run focused and full tests, invoke code review, and commit the result to the current branch.
Excellent quality, 176K stars, and no reported agent risk blocks yet.
$ npx skills add mattpocock/skills --skill implementA single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Excellent quality, 175K stars, and no reported agent risk blocks yet.
$ npx skills add multica-ai/andrej-karpathy-skillsUse Playwright to interact with and test local web applications, capture screenshots, debug UI behavior, and inspect browser logs.
Excellent quality, 171K stars, and no reported agent risk blocks yet.
$ npx skills add anthropics/skills --skill webapp-testingCreate original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
Excellent quality, 171K stars, and no reported agent risk blocks yet.
$ npx skills add anthropics/skills --skill canvas-designApply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related artifacts.
Excellent quality, 171K stars, and no reported agent risk blocks yet.
$ npx skills add anthropics/skills --skill brand-guidelinesReview a branch or diff against repository standards and the originating spec in two independent analysis passes.
Excellent quality, 169K stars, and no reported agent risk blocks yet.
$ npx skills add mattpocock/skills --skill code-reviewA relentless interview that pressure-tests a plan against the codebase, sharpens domain language, and updates CONTEXT.md and ADRs when decisions become durable.
Excellent quality, 165K stars, and no reported agent risk blocks yet.
$ npx skills add mattpocock/skills --skill grill-with-docsTurn the current conversation and codebase context into a structured implementation spec, then publish it to the configured project issue tracker.
Excellent quality, 165K stars, and no reported agent risk blocks yet.
$ npx skills add mattpocock/skills --skill to-specAn AI agent skill that provides design intelligence and UI/UX guidelines for building professional interfaces across multiple platforms.
Excellent quality, 107K stars, and no reported agent risk blocks yet.
$ npx skills add nextlevelbuilder/ui-ux-pro-max-skillBring a coding agent directly into the terminal
Excellent quality, 106K stars, and no reported agent risk blocks yet.
$ npx skills add google-gemini/gemini-cliMake AI agents interact with websites using natural language
Excellent quality, 101K stars, and no reported agent risk blocks yet.
$ npx skills add browser-use/browser-use🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Excellent quality, 97K stars, and no reported agent risk blocks yet.
$ npx skills add JuliusBrussee/cavemanA tool that converts codebases, SQL schemas, and other files into queryable knowledge graphs for AI coding assistants.
Excellent quality, 92K stars, and no reported agent risk blocks yet.
$ npx skills add Graphify-Labs/graphifyLightweight coding agent that runs in your terminal
Excellent quality, 91K stars, and no reported agent risk blocks yet.
$ npx skills add openai/codex🎨 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.
Excellent quality, 88K stars, and no reported agent risk blocks yet.
$ npx skills add nexu-io/open-designMakes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Excellent quality, 86K stars, and no reported agent risk blocks yet.
$ npx skills add DietrichGebert/ponytailGraphs 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.
Excellent quality, 75K stars, and no reported agent risk blocks yet.
$ npx skills add Egonex-AI/Understand-AnythingInstall safety
Skills with strong Trust Score, safe install paths, low risk blocks, clear licenses, and low setup friction.
Daily snapshot: Aug 22, 2026, 2:55 AM UTC
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
Early agent signal: 2 outcomes, 100% success, Agent Proven Score 51/100. 0 risk blocks and 0 setup-required reports.
$ npx skills add anthropics/skills --skill frontend-designReverse-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.
Early agent signal: 1 outcome, 100% success, Agent Proven Score 51/100. 0 risk blocks and 0 setup-required reports.
$ npx skills@latest add emilkowalski/skillsCross-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.
Early agent signal: 2 outcomes, 100% success, Agent Proven Score 48/100. 0 risk blocks and 0 setup-required reports.
$ npx skills add eugeniughelbur/obsidian-second-brainRun multimodal agents that operate desktop interfaces
Early agent signal: 1 outcome, 100% success, Agent Proven Score 42/100. 0 risk blocks and 0 setup-required reports.
$ npx skills add bytedance/UI-TARS-desktopAny agent Skill: generate beautiful architecture diagrams with dark/light theme toggle and PNG/JPEG/WebP/SVG export
Early agent signal: 1 outcome, 100% success, Agent Proven Score 42/100. 0 risk blocks and 0 setup-required reports.
$ npx skills add tt-a1i/archify中文小黑怪诞正文配图生成 Skill | 16:9 白底手绘 | 少量红橙蓝批注 | Codex Skill
Early agent signal: 1 outcome, 100% success, Agent Proven Score 42/100. 0 risk blocks and 0 setup-required reports.
$ npx skills add helloianneo/ian-xiaohei-illustrationsA comprehensive set of 38 marketing skills and 5 commands for Claude Code covering SEO/GEO and influencer marketing with evaluation frameworks.
Early agent signal: 1 outcome, 100% success, Agent Proven Score 42/100. 0 risk blocks and 0 setup-required reports.
$ npx skills add aaron-he-zhu/aaron-marketing-skillsTurn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.
Early agent signal: 1 outcome, 100% success, Agent Proven Score 42/100. 0 risk blocks and 0 setup-required reports.
$ npx skills add Alisa0808/vox-director --skill vox-directorDesign and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
Early agent signal: 2 outcomes, 50% success, Agent Proven Score 33/100. 0 risk blocks and 0 setup-required reports.
$ npx skills add Leonxlnx/taste-skill --skill design-taste-frontendTongyi Deep Research, the Leading Open-source Deep Research Agent
Early agent signal: 1 outcome, 0% success, Agent Proven Score 24/100. 0 risk blocks and 0 setup-required reports.
$ npx skills add Alibaba-NLP/DeepResearchProduction-grade engineering skills for AI coding agents.
Early agent signal: 1 outcome, 0% success, Agent Proven Score 19/100. 0 risk blocks and 0 setup-required reports.
$ npx skills add addyosmani/agent-skillsAn agentic skills framework & software development methodology that works.
Excellent quality, 257K stars, and no reported agent risk blocks yet.
$ npx skills add obra/superpowersBreak a plan, spec, or conversation into independently actionable tracer-bullet tickets with explicit blocking relationships.
Excellent quality, 177K stars, and no reported agent risk blocks yet.
$ npx skills add mattpocock/skills --skill to-ticketsImplement work from an approved spec or ticket set, run focused and full tests, invoke code review, and commit the result to the current branch.
Excellent quality, 176K stars, and no reported agent risk blocks yet.
$ npx skills add mattpocock/skills --skill implementA single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Excellent quality, 175K stars, and no reported agent risk blocks yet.
$ npx skills add multica-ai/andrej-karpathy-skillsUse Playwright to interact with and test local web applications, capture screenshots, debug UI behavior, and inspect browser logs.
Excellent quality, 171K stars, and no reported agent risk blocks yet.
$ npx skills add anthropics/skills --skill webapp-testingCreate original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
Excellent quality, 171K stars, and no reported agent risk blocks yet.
$ npx skills add anthropics/skills --skill canvas-designApply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related artifacts.
Excellent quality, 171K stars, and no reported agent risk blocks yet.
$ npx skills add anthropics/skills --skill brand-guidelinesReview a branch or diff against repository standards and the originating spec in two independent analysis passes.
Excellent quality, 169K stars, and no reported agent risk blocks yet.
$ npx skills add mattpocock/skills --skill code-reviewA relentless interview that pressure-tests a plan against the codebase, sharpens domain language, and updates CONTEXT.md and ADRs when decisions become durable.
Excellent quality, 165K stars, and no reported agent risk blocks yet.
$ npx skills add mattpocock/skills --skill grill-with-docsTurn the current conversation and codebase context into a structured implementation spec, then publish it to the configured project issue tracker.
Excellent quality, 165K stars, and no reported agent risk blocks yet.
$ npx skills add mattpocock/skills --skill to-specAn AI agent skill that provides design intelligence and UI/UX guidelines for building professional interfaces across multiple platforms.
Excellent quality, 107K stars, and no reported agent risk blocks yet.
$ npx skills add nextlevelbuilder/ui-ux-pro-max-skillBring a coding agent directly into the terminal
Excellent quality, 106K stars, and no reported agent risk blocks yet.
$ npx skills add google-gemini/gemini-cliMake AI agents interact with websites using natural language
Excellent quality, 101K stars, and no reported agent risk blocks yet.
$ npx skills add browser-use/browser-use🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Excellent quality, 97K stars, and no reported agent risk blocks yet.
$ npx skills add JuliusBrussee/cavemanA tool that converts codebases, SQL schemas, and other files into queryable knowledge graphs for AI coding assistants.
Excellent quality, 92K stars, and no reported agent risk blocks yet.
$ npx skills add Graphify-Labs/graphifyLightweight coding agent that runs in your terminal
Excellent quality, 91K stars, and no reported agent risk blocks yet.
$ npx skills add openai/codex🎨 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.
Excellent quality, 88K stars, and no reported agent risk blocks yet.
$ npx skills add nexu-io/open-designMakes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Excellent quality, 86K stars, and no reported agent risk blocks yet.
$ npx skills add DietrichGebert/ponytailGraphs 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.
Excellent quality, 75K stars, and no reported agent risk blocks yet.
$ npx skills add Egonex-AI/Understand-Anything