The Skill Leaderboard
from open GitHub repositories.
A set of engineering skills for domain modeling, architectural design, bug diagnosis, and standards-based code review.
A library of AI agent skills covering API integration, behavioral nudges, and the creation of algorithmic art using p5.js.
Converts code, docs, and media into a persistent knowledge graph with community detection for architectural querying and GraphRAG integration.
Audits repositories for over-engineering and aggregates shortcut comments into a technical debt ledger.
A token optimization toolkit that uses a compressed, minimalist language style to reduce AI communication costs.
A set of structured engineering skills for AI agents covering API design, context optimization, and production-grade code quality.
A knowledge graph tool for visualizing codebase architecture, analyzing domain flows, and querying repository structures via an interactive dashboard.
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 topic-specific sentiment from the last 30 days.
Agent skills for Obsidian CLI, markdown, bases, JSON Canvas, and Defuddle web extraction.
Tools for planning A/B tests, designing experiment variants, and managing growth experimentation playbooks.
A management system for agentic skills that provides standardized templates and specialized capabilities for AI agents across security, architecture, and web development.
A 10-stage academic research pipeline that integrates deep research, manuscript drafting, and multi-perspective peer review simulation.
A repository of skills for routing agentic workflow requests and scaffolding canvas extensions with integrated governance patterns.
Rewrites AI-generated text to remove chatbot patterns, filler, and inflated claims while preserving the original factual content.
Provides API and SDK integration for protein screening experiments, including BLI/SPR and thermostability assays via the Adaptyv Bio Foundry.
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, following Vercel best practices, and executing automated deployments.
Security research skills for Android APK hooking, SSL bypass, and Active Directory Certificate Services abuse.
A design skill for extracting visual DNA from URLs or screenshots and applying intentional UI patterns to AI-generated pages.
Implements persistent file-based tracking of task plans and progress to maintain state across AI agent sessions.
Creates branded architecture, data flow, and UML diagrams in multiple formats with support for brand token integration and custom styling.
A library of 68 agent skills for product management across discovery, strategy, execution, analytics, go-to-market, growth, and AI code auditing, with structured templates for PRDs, user stories, A/B tests, and more.
A skill library for content production and publishing: visual asset generation, cross-platform posting, Markdown formatting, diagram creation, and automated release workflows.
Converts various document formats into structured agent skills by extracting frameworks, principles, and techniques for use with AI agents.
A library of over 800 specialized AI skills covering agent workflow design, accessibility auditing, and marketing automation.
A 73-skill game development pipeline covering brainstorming, design, architecture, prototyping, implementation, testing, QA, localization, security, release, and live ops for indie teams and solo developers.
A tool for distilling human traits and source material into reusable person profiles and skills for AI agents.
Formats AI output for ADHD users by leading with next actions, numbering multi-step tasks, and suppressing tangents.
Enterprise integration skills for the Gemini API and Agent Platform, covering SDK usage, multimodal capabilities, and stateful interaction management.
A collection of agent skills focused on context engineering, harness design, and multi-agent architecture for production systems.
A library of automation skills for the Codex CLI and API, including utilities for IDE deep linking and brand guideline application.
Generates validated architecture, sequence, and data-flow diagrams from text or code as interactive HTML and SVG files.
A research automation toolkit for searching arXiv papers, analyzing ML experiment statistics, and planning ablation studies.
An SEO analysis suite for auditing site health, analyzing backlink profiles, and generating data-driven content briefs using Ahrefs and DataForSEO integrations.
Eight skills covering GSAP core, timelines, ScrollTrigger, performance, framework integration, plugins, and utility methods for web animation development.
Generates parametric CAD parts and robot-description files from text, with integrated visual review and 3D print job initiation.
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.
Generates and optimizes tool-specific prompts for LLMs, coding agents, and generative AI tools.
An AI-driven system for Obsidian that automates source research, citation drafting, and the organization of a connected Markdown knowledge graph.
A set of AI skills for full-stack development, including Angular 17+ architecture, .NET Core expertise, and system design documentation.
Generates self-contained HTML diagrams, architecture overviews, and visual diff reviews for technical systems and plans.
A 16-skill GEO audit suite that scores AI citability, crawler access, content E-E-A-T, technical SEO, and brand authority, then produces client-ready reports and proposals.
A marketing operations skill for conducting audits, planning budgets, and managing campaigns across multiple paid advertising platforms.
Converts Stitch designs into React and React Native components, including Vite-based dashboards with Web3 integration and TanStack Query.
Generates .drawio XML files and exports them to image formats for UML, SysML, BPMN, and cloud architecture diagrams.
Connects Claude Code to NotebookLM for source-grounded queries against uploaded documents, with notebook library management and citation-backed answers.
A structured Android reverse engineering pipeline covering fingerprinting, decompilation with jadx and Fernflower, Kotlin name recovery, call flow tracing, and two-tier API endpoint documentation.
Creates self-contained dark-themed HTML/SVG architecture diagrams for systems, cloud infrastructure, security diagrams, and network topologies with export to PNG and PDF.
A six-phase research workflow that synthesizes unfamiliar domains and source bundles into publish-ready reference material.
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.