The Skill Leaderboard
from open GitHub repositories.
An agentic skills framework for brainstorming designs, dispatching parallel agents, and standardizing AI-assisted development processes.
A set of engineering skills for domain modeling, architectural design, bug diagnosis, and standards-based code review.
Behavioral guidance for writing, reviewing, and refactoring code with explicit assumptions, minimal scope, and verifiable success criteria.
A set of agent skills for implementing API integrations, behavioral nudges, and p5.js algorithmic art generation.
Audits repositories for over-engineering, tracks shortcut comments in a debt ledger, and measures the impact of code simplification.
Generates multi-platform banners and creative assets using specific art direction styles and platform dimensions.
Converts codebases, docs, and media into a persistent knowledge graph with tools for architecture analysis and GraphRAG JSON export.
A token optimization toolkit that compresses LLM prompts and agent communications to reduce consumption.
A set of engineering skills for AI agents covering API design, interface contracts, and context engineering.
A design-focused skill collection for premium frontend direction, visual generation, redesigns, brand systems, and motion-led implementation.
A knowledge graph tool for visualizing codebase structure, extracting domain flows, and analyzing pull request risks.
A frontend design skill for auditing UX, optimizing visual hierarchy, and implementing advanced UI effects and reusable design tokens.
A library of 864 Claude skills covering automation, artifact creation, brand styling, changelog generation, ad extraction, and composio MCP integrations for over 100 services.
Aggregates posts and engagement from major social platforms and the web to research public sentiment from the last 30 days.
Adjusts AI output for ADHD users by leading with next actions, numbering steps, and suppressing verbose tangents.
A writing tool that removes AI-specific structural patterns, stock phrasing, and filler to make generated text read more naturally.
Guidance for designing A/B tests, managing experiment backlogs with ICE scoring, and implementing growth experimentation programs.
A suite of agents for academic writing, citation checking, and multi-perspective peer review simulation.
A suite of skills for AI agents to manage Obsidian vaults, edit JSON Canvas files, and debug plugin development.
Interfaces with the Adaptyv Bio Foundry API to design, submit, and monitor protein characterization experiments including affinity assays and thermostability tests.
A large-scale repository of agentic skills and templates for AI automation, including tools for solution architecture, security auditing, and 3D web development.
Generates branded architecture, data flow, and process diagrams including UML, ER models, and user journey maps with support for Mermaid and Excalidraw imports.
Implements high-performance animations and gestures in Expo using Reanimated, Gesture Handler, and expo-haptics.
Security workflows for AI agent prompt injection, APK hooking, and Active Directory certificate abuse within sandbox environments.
A prompt library for repository documentation, agentic workflow routing, and technical code review.
A converter that extracts frameworks and principles from documents to create structured skills for AI coding assistants.
A library of 818 structured cybersecurity skills for AI agents, covering red-teaming tasks such as DPAPI decryption and Active Directory privilege escalation.
A set of skills for implementing React composition patterns, optimizing React Native applications, and executing Vercel deployments.
Open-source, self-hosted alternative to OpenAI Dots, Grok Bot. Built to be undetectable by anti-bot systems.
A design skill for extracting visual DNA from URLs or screenshots and applying intentional UI patterns to AI-generated pages.
A set of curated skills for developing ASP.NET Core applications and ChatGPT Apps SDK integrations using official guidance.
A library of over 800 AI skill definitions covering agent orchestration, accessibility auditing, marketing optimization, and engineering workflows.
Provides persistent planning via task_plan.md, findings.md, and progress.md files to support session recovery and state tracking for multi-step agent tasks.
A code review methodology that identifies actionable defects by verifying implementation against boundary agreements and forcing violating executions.
Automates versioning, changelog generation, and GitHub Releases for multiple languages alongside translation utilities.
Conducts security audits and vulnerability research across codebases, APIs, services, and CLI tools.
A comprehensive suite of 74 skills for game development, featuring studio-hierarchy coordination, technical decision tracking, and project auditing.
Creates reusable Person Profiles from source material about colleagues, relationships, or celebrities.
A collection of skills for AI agents to perform gcloud CLI operations and manage Google Cloud authentication and authorization.
Combines Ahrefs API analysis for backlinks and keywords with AI generation of OG images, hero banners, and SEO visuals.
A set of tools for generating parametric CAD models and exporting them to 3D printers.
A collection of agent skills for context engineering, harness engineering, and the development of production-ready multi-agent systems.
A research automation suite for searching academic papers, analyzing ML experiment results, planning ablation studies, and generating technical diagrams.
A library of automation skills for the Codex CLI and API, including utilities for IDE deep linking and brand guideline application.
Eight skills covering GSAP core, timelines, ScrollTrigger, performance, framework integration, plugins, and utility methods for web animation development.
Automates source-grounded research and the filing of cited dossiers into an Obsidian Markdown knowledge graph.
Generates shareable launch videos with music and motion from a project directory or website URL.
Generates and optimizes tool-specific prompts for LLMs, coding agents, and generative AI tools.
A library of AI skills covering PR reviews and PowerPoint orchestration, including color palette selection and slide design recipes.
A library of agent skill files covering the AI research lifecycle: autonomous experimentation, model architecture, fine-tuning, mechanistic interpretability, distributed training, safety, optimization, evaluation, inference serving, and MLOps.
What are skills?
How do I open a .skill file?
Why use skills instead of relying on the base AI?
Is it safe to install skills?
What does a skill include?
When does an agent use a skill?
Do skills only work for coding?
Which platforms support skills?
What's the deal with frontmatter?
--- markers. It holds the metadata the agent reads before anything else: name, description, sometimes version, license, allowed tools. Get it wrong and the agent won't trigger the skill when it should. The spec lists every field.What are the rules for the skill name?
name field is lowercase, uses hyphens (no spaces, no underscores), sticks to letters, digits, and hyphens, and caps out at 64 characters per the Agent Skills spec. Treat it like a URL slug: "pdf-form-filler" works, "My Cool Skill!" does not. The name has to match the folder name exactly.What should the description include?
Can a skill bundle contain multiple SKILL.md files?
office/ (one sub-skill each for docx, pptx, xlsx, and pdf) or accounting workflows where every procedure has its own quirks.