Codex agent orchestration skill with adaptive thread thinking, callbacks, QA/review gates, fenced automations, project autopilot, and optional agy/Gemini review.

Any capability as a filesystem-native Skill for every agent.

Aeon skill: beautiful two-color Excalidraw diagrams from drawfiles, machine-validated

判断一个skill适不适合你用的skill——啥好用。它可以根据你的需求，把候选 Skill 的用途、安装代价、风险和需求匹配度做成清晰易懂的 HTML 说明书，提升你挑选skill的效率，省点时间和token。

Reusable skills for AI coding agents (OpenCode, Claude Code, Cursor, Copilot and more)

让 prompt 从"感觉好了"变成"真好了" · Where "feels better" becomes "measurably better" for your AI prompts.

Claude skill: aligns a Figma design or scrappy code to your real Storybook components. Never reconstructs, never invents.

Mouse Trail Masking Reveal: portable Agent Skills for cursor-trail reveal effects across Codex, Claude Code, Gemini, Kimi, Qwen, and GLM agents

Codex App-only skill for coordinating managed worktree background threads

Agent skill and reference runtime for maintaining a git-backed business ontology: source intake, review gates, evals, and MCP/GBrain boundaries.

MGR — Método Governado por Rastreabilidade (Traceability-Governed Method): spec-driven development framework for coding agents, portable between Claude Code and GitHub Copilot

AI-powered Xiaohongshu note imitation writing skill

Minecraft開発用スキル

A community Claude Skill for Flutter mobile app development, Clean Architecture, Firebase, REST APIs, Laravel APIs, UI building, debugging, and publishing.

Give Codex a story. Get an editable AI-video package powered by Dreamina: shots, prompts, generation, editing, SRT, stems, and QA.

Give your Zo Computer a deliberate case of ADHD: parallel isolated ideation across distorted cognitive frames, then a critic pass that scores, flags traps, and deepens the survivors. MIT.

An installable Claude Code + Obsidian companion system: persistent wiki-memory, curated skills/agents, isolated zones, and a self-improvement loop.

AI agent methodology skill for Codex, Claude Code, and OpenCode: dialectical analysis, software architecture reasoning, product strategy, and project retrospection.唯物辩证批判思维 Skill — 基于毛选方法论的 AI 底层思维框架的 coding 框架

Make AI agents check what they actually verified before claiming something is done.

A tool-agnostic method (Claude Skill) for turning scattered docs, design files, and videos into a citation-grounded, queryable knowledge base — every answer shows its receipts.

Agent skill for creating premium Remotion marketing videos product demos, SaaS promos, motion graphics, UI walkthroughs, social ads, and explainers using React and code-first animation.

Detector-guided humanizer skill for Claude Code: lower the AI-detection score of English text while preserving every key term, number, citation, and the original logic. Keyless, agent-as-rewriter.

Full-lifecycle engineering plugin for Claude Code — brainstorm → plan → build → review → ship, with production-grade standards at every step.

Claude Code skills for Apple platform development — visionOS SharePlay, SpriteKit, and GameKit multiplayer

AI 에이전트가 한글(HWP/HWPX) 편집기 rhwp-studio를 GUI 수준에서 조작·검증하도록 만든 에이전트 스킬 모음(rhwp-gui-agent). Agent skills to drive the Rust/WASM HWP editor for AI-authored Korean documents.

Evolutionary Self-Recursive Architecture for Hermes Agent — meta-skills, OODA, smart orchestration

Catch what's off before you ship. A Claude Code skill that audits UI and routes each issue to layout, interaction, copy, or engineering.

Harness agnostic skill pack for AI coding agents that audits codebases for technical debt across ten categories

🎨 My Claude Code config. Build something interesting and fun.

Solo/indie playbook for shipping small iOS/macOS & Android apps — an AI agent skill pack for Claude Code, Antigravity, Cursor & Gemini

Pi skill for generating native draw.io diagrams and exports

Ticket → production-PR pipeline for Claude Code & Codex CLI, enforced by hooks. 21-skill pipeline, one configurator, adapts to any codebase.

Agent Skill for Claude Code and Codex: public Instagram creator discovery, influencer vetting, engagement-rate calculation, and lead CSV validation.

Turn your ai agent into senior engineer..The result is fast code that fails slowly. AI Agent Skills solves this by giving agents the same disciplined workflows senior engineers use

Codex skill for local investment research

Turn recurring Claude Code and OpenAI Codex mistakes into durable, reviewable workspace memory with safe local context patches.

Benchmarked Claude Code plugin that makes cheaper Claude models (Haiku, Sonnet, Opus) match Fable 5's output at a fraction of the token cost — auto-routed reasoning levels, verification discipline, closed-loop habit correction, statusline HUD with usage meters, and a portable AGENTS.md export for any AI coding agent.

Skill for AutoSkill

An AI agent skill that guides you through writing academic papers and theses, section by section.

Cursor skills and harness-oriented workflows for project intake, problem framing, and AI-ready task decomposition.

Reusable Agent Skill for client delivery guardrails in Codex and Claude Code

A multi-purpose macOS command-line tools, friendly with agents. Written in Odin.

An automated tool based on Kimi WebBridge to extract wrong answers from icve exam review pages and format them into a structured text notebook.

AI skill for automating KiCad project workflows via the kicad-tools CLI — schematic and PCB analysis, validation, repair, and manufacturing export. Compatible with GitHub Copilot, Google Antigravity, and other AI tools supporting the open Agent Skills standard.

Production-ready skills for AI coding agents. 13 skills, 9 agents, harness hooks & quality gates (signed optional for long sessions). Plan, build, test, debug, ship. Any repo, any language. Claude Code native, universal LLM compatible.

Roxy SEO: an open-source agent skill and PI extension for SEO, AEO, GEO, AI search visibility, technical audits, structured data, and content strategy.

A tiny cross-client Agent Skill for searching all official Unitree documentation.

Canonical AI engineering workflow skills, aggregated by wakqasahmed/skills

Reverse-engineer, audit, and improve AI agent skills

LIA Labs / Learnkit - "Make your AI agents Learn Improve and Adapt".

Объективная оценка бизнес-идей через 18 субагентов и Business Reality Score. Agent Skill для Claude Code, Cursor и Codex.

Local capability router for Codex, Claude Code, Cursor, MCP servers, skills, agents, and rules.

A complete, opinionated, fork-friendly operating system for an AI-instructed company. Three layers — markdown skills (patterns of thought for agents), a justfile template, a constitutional pattern. 13 universal skills, dogfooded by the company that authored them.

Bratan is a self-improving Retrieval-Augmented Generation framework built on an adversarial three-agent loop

Evidence-led Chinese investment research skill for stocks and China OTC public funds

TypeScript CLI and Preact render kit for turning agent plans and review gates into local HTML with optional approvals.

An agent skill that brings paranoid text spacing (盤古之白) for AI coding agents.

AI-native VMware compliance and baseline enforcement (CIS, vSphere SCG, 等保 2.0, PCI-DSS) — sibling to vmware-* skill family

Load agent skills from the internet temporarily without permanent installation. Works with Kilo, Claude Code, Cursor, Copilot, and any agent.

Workbench for Agent Skills — lint, test, benchmark, and gate-install SKILL.md skills for Claude Code, Codex, Cursor, Gemini, and more