Skills ranked by real agent outcome evidence.

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.

Promising agent evidence: 45 outcomes, 100% success, Agent Proven Score 80/100. 45 install attempts, 0 risk blocks, and excellent quality.

Promising agent evidence: 45 outcomes, 100% success, 45 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 80/100.

Turn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.

Promising agent evidence: 38 outcomes, 100% success, Agent Proven Score 80/100. 38 install attempts, 0 risk blocks, and excellent quality.

Promising agent evidence: 38 outcomes, 100% success, 38 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 80/100.

Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.

Promising agent evidence: 13 outcomes, 100% success, Agent Proven Score 77/100. 13 install attempts, 0 risk blocks, and excellent quality.

Promising agent evidence: 13 outcomes, 100% success, 13 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 77/100.

Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.

Promising agent evidence: 56 outcomes, 93% success, Agent Proven Score 69/100. 56 install attempts, 0 risk blocks, and excellent quality.

Promising agent evidence: 56 outcomes, 93% success, 56 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 69/100.

Review UI code for web interface guidelines, UX quality, accessibility, and interaction design best practices.

Promising agent evidence: 12 outcomes, 100% success, Agent Proven Score 77/100. 12 install attempts, 0 risk blocks, and excellent quality.

Promising agent evidence: 12 outcomes, 100% success, 12 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 77/100.

Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.

Early agent signal: 32 outcomes, 88% success, Agent Proven Score 66/100. 32 install attempts, 0 risk blocks, and excellent quality.

Early agent signal: 32 outcomes, 88% success, 32 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 66/100.

Any agent Skill: generate beautiful architecture diagrams with dark/light theme toggle and PNG/JPEG/WebP/SVG export

Promising agent evidence: 17 outcomes, 100% success, Agent Proven Score 75/100. 17 install attempts, 0 risk blocks, and excellent quality.

Promising agent evidence: 17 outcomes, 100% success, 17 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 75/100.

Generate interactive 3D holographic collectible-card websites from a user description or reference image, using layered artwork, Blender and Three.js. Includes project-local Blender installation, reusable parallax materials and browser verification.

Promising agent evidence: 17 outcomes, 100% success, Agent Proven Score 75/100. 17 install attempts, 0 risk blocks, and excellent quality.

Promising agent evidence: 17 outcomes, 100% success, 17 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 75/100.

Applies Cursor's prose-discipline rules to remove filler and AI writing tells from agent-facing and user-facing text.

Promising agent evidence: 13 outcomes, 100% success, Agent Proven Score 75/100. 13 install attempts, 0 risk blocks, and excellent quality.

Promising agent evidence: 13 outcomes, 100% success, 13 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 75/100.

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.

Promising agent evidence: 25 outcomes, 100% success, Agent Proven Score 74/100. 25 install attempts, 0 risk blocks, and excellent quality.

Promising agent evidence: 25 outcomes, 100% success, 25 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 74/100.

Use Playwright to interact with and test local web applications, capture screenshots, debug UI behavior, and inspect browser logs.

Promising agent evidence: 8 outcomes, 100% success, Agent Proven Score 73/100. 8 install attempts, 0 risk blocks, and excellent quality.

Promising agent evidence: 8 outcomes, 100% success, 8 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 73/100.

An agentic skills framework & software development methodology that works.

Promising agent evidence: 13 outcomes, 92% success, Agent Proven Score 69/100. 13 install attempts, 0 risk blocks, and excellent quality.

Promising agent evidence: 13 outcomes, 92% success, 13 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 69/100.

🎨 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.

Early agent signal: 8 outcomes, 88% success, Agent Proven Score 67/100. 8 install attempts, 0 risk blocks, and excellent quality.

Early agent signal: 8 outcomes, 88% success, 8 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 67/100.

Create beautiful slides on the web using a coding agent's frontend skills

Early agent signal: 12 outcomes, 92% success, Agent Proven Score 67/100. 11 install attempts, 0 risk blocks, and excellent quality.

Early agent signal: 12 outcomes, 92% success, 11 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 67/100.

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.

Promising agent evidence: 7 outcomes, 100% success, Agent Proven Score 69/100. 7 install attempts, 0 risk blocks, and excellent quality.

Promising agent evidence: 7 outcomes, 100% success, 7 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 69/100.

A relentless interview to sharpen a plan or design.

Early agent signal: 6 outcomes, 100% success, Agent Proven Score 67/100. 6 install attempts, 0 risk blocks, and excellent quality.

Early agent signal: 6 outcomes, 100% success, 6 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 67/100.

An AI agent skill that provides design intelligence and UI/UX guidelines for building professional interfaces across multiple platforms.

Early agent signal: 7 outcomes, 86% success, Agent Proven Score 63/100. 7 install attempts, 0 risk blocks, and excellent quality.

Early agent signal: 7 outcomes, 86% success, 7 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 63/100.

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Early agent signal: 5 outcomes, 100% success, Agent Proven Score 63/100. 5 install attempts, 0 risk blocks, and excellent quality.

Early agent signal: 5 outcomes, 100% success, 5 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 63/100.

Create a structured post-earnings equity research update with key metrics, estimate changes, charts, and thesis review.

Early agent signal: 5 outcomes, 100% success, Agent Proven Score 63/100. 5 install attempts, 0 risk blocks, and excellent quality.

Early agent signal: 5 outcomes, 100% success, 5 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 63/100.

Review a branch or diff against repository standards and the originating spec in two independent analysis passes.

Early agent signal: 4 outcomes, 100% success, Agent Proven Score 61/100. 4 install attempts, 0 risk blocks, and excellent quality.

Early agent signal: 4 outcomes, 100% success, 4 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 61/100.

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.

Early agent signal: 6 outcomes, 83% success, Agent Proven Score 59/100. 6 install attempts, 0 risk blocks, and excellent quality.

Early agent signal: 6 outcomes, 83% success, 6 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 59/100.

A full-lifecycle Claude Code skill for creating, compiling, reviewing, and polishing academic Beamer LaTeX presentations with quality scoring and pedagogical audits.

Early agent signal: 4 outcomes, 100% success, Agent Proven Score 59/100. 4 install attempts, 0 risk blocks, and excellent quality.

Early agent signal: 4 outcomes, 100% success, 4 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 59/100.

Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed frontend or backend skills for framework-specific patterns. Use when reviewing code quality or naming with no framework-specific skill that applies.

Early agent signal: 3 outcomes, 100% success, Agent Proven Score 57/100. 3 install attempts, 0 risk blocks, and excellent quality.

Early agent signal: 3 outcomes, 100% success, 3 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 57/100.

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

Early agent signal: 3 outcomes, 100% success, Agent Proven Score 57/100. 3 install attempts, 0 risk blocks, and excellent quality.

Early agent signal: 3 outcomes, 100% success, 3 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 57/100.

Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related artifacts.

Early agent signal: 3 outcomes, 100% success, Agent Proven Score 57/100. 3 install attempts, 0 risk blocks, and excellent quality.

Early agent signal: 3 outcomes, 100% success, 3 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 57/100.

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.

Early agent signal: 3 outcomes, 100% success, Agent Proven Score 57/100. 3 install attempts, 0 risk blocks, and excellent quality.

Early agent signal: 3 outcomes, 100% success, 3 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 57/100.

Translate Figma designs into production-ready UI code with close visual fidelity and component-level detail.

Early agent signal: 3 outcomes, 100% success, Agent Proven Score 57/100. 3 install attempts, 0 risk blocks, and excellent quality.

Early agent signal: 3 outcomes, 100% success, 3 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 57/100.

A distributable agent skill that converts Chinese story text or ordered images into hand-drawn diary-comic style MP4 animations via Remotion, with 20 visual styles and support for Codex, Claude Code, and Kimi Code.

Early agent signal: 3 outcomes, 100% success, Agent Proven Score 57/100. 3 install attempts, 0 risk blocks, and excellent quality.

Early agent signal: 3 outcomes, 100% success, 3 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 57/100.

Generate highly simplified personified IP mascot logos with Flat-first geometry, rounded heavy forms, two IP colors plus one background color by default, and extremely subtle neo-skeuomorphic shading. Use when creating an animal, creature, robot, ghost, plant, object, or other character as a minimal square logo or app-icon artwork, including when the agent should infer three distinct IP directions from product-repository context.

Early agent signal: 3 outcomes, 100% success, Agent Proven Score 57/100. 3 install attempts, 0 risk blocks, and excellent quality.

Early agent signal: 3 outcomes, 100% success, 3 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 57/100.

Eliminates predictable AI writing patterns from prose while preserving specific meaning and reader trust.

Needs agent review: 6 outcomes, 67% success, Agent Proven Score 46/100. 6 install attempts, 0 risk blocks, and excellent quality.

Needs agent review: 6 outcomes, 67% success, 6 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 46/100.

Expert guidance for the SAS programming language — DATA step, PROC SQL, macro language, formats, ODS, and common procedures. Pure SAS syntax only, no SASjs-framework content. Use when writing, reviewing, or debugging .sas programs, or answering SAS language questions.

Early agent signal: 2 outcomes, 100% success, Agent Proven Score 60/100. 2 install attempts, 0 risk blocks, and promising quality.

Early agent signal: 2 outcomes, 100% success, 2 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 60/100.

Use when designing, implementing, or reviewing adaptive Compose UI for KMP or Android projects — window-size layouts, adaptive navigation, canonical layouts, multi-window support, and resource strategy.

Early agent signal: 3 outcomes, 100% success, Agent Proven Score 55/100. 3 install attempts, 0 risk blocks, and promising quality.

Early agent signal: 3 outcomes, 100% success, 3 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 55/100.

Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.

Early agent signal: 2 outcomes, 100% success, Agent Proven Score 51/100. 2 install attempts, 0 risk blocks, and excellent quality.

Early agent signal: 2 outcomes, 100% success, 2 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 51/100.

Write precise Seedance 2.0 prompts for multimodal video, camera movement, editing, music, and product storytelling.

Early agent signal: 2 outcomes, 100% success, Agent Proven Score 51/100. 2 install attempts, 0 risk blocks, and excellent quality.

Early agent signal: 2 outcomes, 100% success, 2 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 51/100.

120 marketing skills for SEO/GEO, influencer, paid ads, email, launch, organic social, and brand narrative agents.

Early agent signal: 2 outcomes, 100% success, Agent Proven Score 51/100. 2 install attempts, 0 risk blocks, and excellent quality.

Early agent signal: 2 outcomes, 100% success, 2 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 51/100.

Create a consent-aware digital-avatar layer for AI video production with narration approval and final quality gates.

Early agent signal: 2 outcomes, 100% success, Agent Proven Score 51/100. 2 install attempts, 0 risk blocks, and excellent quality.

Early agent signal: 2 outcomes, 100% success, 2 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 51/100.