Codex Skill Leaderboard

A set of engineering skills for domain modeling, codebase design, systematic debugging, and dual-axis code reviews.

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 collection of token optimization skills that use a compressed communication pattern to reduce LLM context consumption.

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.

Researches recent public sentiment and discussions by pulling engagement data from major social media platforms, technical forums, and the web.

Agent skills for Obsidian CLI, markdown, bases, JSON Canvas, and Defuddle web extraction.

A large-scale collection of agentic skills and templates for building specialized AI automation capabilities.

Provides tools for planning A/B tests, designing growth experiments, and managing an experiment backlog using ICE scoring.

An end-to-end academic research workflow that integrates deep research, manuscript drafting, and a multi-perspective peer-review simulation.

Provides routing for agentic workflow design and tools for scaffolding canvas extensions and plugin manifests.

Provides API and SDK integration for designing, submitting, and retrieving results from protein binding and thermostability assays via Adaptyv Bio Foundry.

A set of skills for implementing React composition patterns, following Vercel best practices, and executing automated deployments.

A collection of 817 structured cybersecurity skills for AI agents, covering red-teaming techniques and credential access mapped to MITRE ATT&CK and NIST CSF.

Provides file-based persistence for AI agents using task_plan.md, findings.md, and progress.md to track multi-step projects across session resets.

Security research workflows for binary diffing, Android APK hooking, and AD CS certificate abuse.

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.

A design skill for extracting visual DNA from URLs or screenshots and applying intentional UI patterns to AI-generated pages.

A library of specialized AI skill definitions for agent workflow design, accessibility auditing, and marketing automation.

A meta-skill engine that distills colleague, relationship, and celebrity personas into reusable AI skill configurations.

Converts PDF, EPUB, and other document formats into structured AI skills by extracting frameworks and mental models.

Formats AI output for ADHD users by leading with next actions, numbering multi-step tasks, and suppressing tangents.

Technical implementation guides for connecting AI assistants to Google Ads APIs and Data Manager services.

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.

A research automation suite for searching arXiv papers, analyzing ML experiment statistics, planning ablation studies, and generating Mermaid diagrams.

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 natural language with integrated visual review and 3D printing handoffs.

Generates validated architecture, sequence, and data-flow diagrams from text or code as explorable HTML files.

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.

An AI-driven system for Obsidian that automates source research, citation drafting, and the organization of a connected Markdown knowledge graph.

Generates self-contained HTML files for architecture diagrams, diff reviews, comparison tables, and technical system overviews.

A marketing operations skill for conducting audits, planning budgets, and managing campaigns across multiple paid advertising platforms.

Converts Stitch designs into React, React Native, and Vite dashboard components with support for design tokens and Web3 patterns.

Generates professional .drawio diagrams from text, code, and infrastructure manifests, supporting UML, C4, ERD, BPMN, and SysML standards.

Connects Claude Code to NotebookLM for source-grounded queries against uploaded documents, with notebook library management and citation-backed answers.

A multi-phase research skill that compiles and synthesizes raw materials into structured, publishable output.

Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations, detecting dangerous input patterns and sandbox misconfigurations.

A browser automation skill for navigating websites, extracting web data, and testing web applications with persistent page state.

A set of product management skills focused on acquisition channel evaluation, unit economics, and the design of multi-agent AI workflows.

Generates Xiaohongshu Rednote carousels, WeChat cover pairs, and Live Photo motion cards using editorial or Swiss design systems.

Structured revision workflow for ML/CV/NLP papers with section-by-section guidance, reverse outlining, and claim-evidence mapping for reviewer-facing clarity.

An autonomous iteration loop that modifies and verifies code against a set metric to optimize performance.

A repository of browser-act skills for automating website interactions and performing bulk data extraction from complex web interfaces.

Provides agent-based guidance and custom persona configurations for .NET SDK setup, ASP.NET Core web development, and system testing.

A set of modular AI skills for office productivity, featuring advanced Excel data analysis and automated presentation creation.