A collection of agent skills for AI coding agents.

Runtime-agnostic Agent Skill for structured product teardowns — competitive intelligence, market analysis, and UI/UX research — from a competitor's homepage and demo/review videos.

A collection of agent skills for repository setup, multi-CLI agent workflows, and intelligent context loading.

Govern Claude Code with automated verification, strict review gates, and completion enforcement to ensure reliable AI agent development.

An agent skill that creates, improves, validates, and retires your agent skills. Human-curated, not auto-generated.

Curated AI agent skills for automating common development workflows

Agent-neutral Trivy security scanning skill for local vulnerability, misconfiguration, secret, and license scans.

Swiggy MCP skills for group food ordering agents.

Mzu personal OpenClaw / Agent Skills collection

😌 AI-powered rhyming assistant skill for Chinese, English, and Korean poetry, lyrics, and sentences. 支持中英韩三语的智能押韵生成与检测 AI skill.

BU 330.760 HW5 — meeting-notes-to-actions agent skill

Portable Markdown skill for AI vibe coding with data and analytics: pipelines, BI dashboards, SQL optimisation, metrics, data quality, and analytics workflows.

Hermes Agent skill + CLI: turn one raw goal prompt into an isolated optimized Markdown contract + paired ANALYSIS/BOOTSTRAP/RED/GREEN/REFACTOR TDD task-list YAML, with a paste-target /goal handoff — never executes the goal. 12-executor catalog (Claude Code, Codex, OpenCode, Gemini, Cursor, Aider, Pi, Qwen, Goose, Amp, Crush, Hermes).

🚧 BETA · Skills for the handoff → compact → resume workflow. Preserve key session context across compactions, with a confirmation gate on resume.

Official ModelBound plugin for Cursor — slash commands for skill pipeline, trust & safety, versions, and MCP-backed context sync.

Canonical Agent Skills library for Claude Code, Cursor, Codex, and other agents.

Harness-agnostic SKILL modules for AI coding agents — mutation-oriented code analysis and contract-as-seam GitHub issue planning. Drop into Claude Code, Codex, Cursor, Aider, or any LLM that reads SKILL.md.

AI Agent skills and workflows for a research-driven solo AI company.

Agentic tools for developers who lead their AI, not follow it.

Agent Skill that helps AI agents build mobile friendly, responsive, overflow-free web UI that stays consistent with your project

Policy-as-code admission controller for AI agent skills and MCP tools. SkillBOM, lockfiles, and supply-chain baselines.

Cross-tool model routing skill for Codex, Cursor, and Antigravity

DeepSeek-first API CLI and Agent Skills toolkit with multi-provider fallback

Self-onboarding Claude Code skill that tailors your resume to any job posting and renders it to Word, Markdown, and PDF — accuracy-first keyword threading from a single tagged master-resume file.

Production-grade agent skills for Claude Code, OpenAI Codex, Gemini CLI, and every platform implementing the Agent Skills open standard

Read-only diagnosis and a safe, rollback-aware cleanup plan for bloated Git repositories. Zero-dependency Python; ships as a Claude Code skill.

Belgian accounting (FR/NL) Agent Skill for Claude — PCMN/MAR, écritures/boekingen, comptes annuels, BE GAAP

Agent Skills for Conventional Commits, maintainability code reviews, and pull request descriptions.

AI Knowledge Work Platform — Chat when you need answers, Work when you need results. Two modes, one seamless experience. Runs in terminal, browser, or desktop.

自分のClaude Code履歴を解析し、繰り返す依頼を高精度プロンプト＋自動ルーターに蒸留。捏造を拒否する共通プロトコル付き

Skills to help developers using AI agents with React PDF Kit library

Provider-neutral Agent Skill for designing, auditing, and operating multi-agent teams

GenPark skill: Run pay-per-acquisition social drops, Plaid card-linked verification, and Venmo rewards payouts using Claim Merchants.

12 Claude Agent Skills for the full B2B event lifecycle (10 specialist + 2 meta) — agentskills.io standard

Reusable Codex skills for creating visual, portfolio-grade GitHub READMEs with a consistent AI Engineering identity.

Meta-skill that tracks skill usage, recommends the right skill for a task, and chains skills into named workflows. PostToolUse hook into a local SQLite DB, plus a recommendation engine and declarative workflow files.

Compile one Agent Skill into harness-native skills for every coding agent

M.I.C. — a three-layer JSON profile format for AI agents: Memory (triggers), Intention (goals), Context (persona).

Give Claude your law firm's memory. A CLAUDE.md template plus voice, intake rules, templates and matter notes in one folder your AI reads before it writes. Shared with your team via GitHub, no terminal required. By Irfad Imtiaz at My Legal Academy.

Agent stuff

PostgreSQL intelligence skill for Claude Code, Codex, Cursor, Windsurf, and local LLM agents

A scoped mentoring skill for codebase understanding and technical distillation.

GenPark skill: Automate AI marketing strategy and execution using the MktFlywheel framework.

Open-source agent skills for shipping & operating real infrastructure. First: ec2-docker-host — many apps on one EC2 box with Docker, shared Caddy + DBs, without disturbing neighbors.

一个借鉴 Tim Cook 公开管理理念的商业决策辅助 AI Skill — 库存审查、现金流诊断、产品聚焦、运营评估、价值观约束和危机应对

AI-first workspace bootstrapper — installs skills, packs, agents, and disciplines into .agents/. Cross-compatible with Claude Code and OpenCode.

Unofficial Pi package for vercel-labs/opensrc

OpenRouter free-LLM CLI & skill for coding agents

Claude/Codex/Hermes skill for README-to-GitHub Pages landing pages via Stitch MCP - GitHub Pages: https://cskwork.github.io/stitch-landing-skill/

Agent Memory Blueprint: public-safe templates, validators, and skill packaging for machine-first long-running agent memory.