Workflow orchestration skill — multi-step processes with approval gates and state machines

CI/CD pipeline skill — build status, logs, reruns, deployments via mcp-cicd

Claude Code skills for genuine property-based testing: discovery workflow, anti-patterns, Hypothesis & beyond.

LLM agent skills for software architecture analysis and review. This repository equips AI agents with reusable capabilities to evaluate system design, review architecture decisions, identify risks, analyze trade-offs, and recommend improvements for scalable, reliable, and maintainable systems.

Free MIT Claude Code skills: clarify rough ideas and scaffold your first skill.

A Claude Code skill: spawn 5 independent agents to stress-test high-stakes decisions and fight AI sycophancy. Inspired by Karpathy's LLM Council.

The SQL cost & performance audit skill for Claude Code. 20 rules, scores warehouse health 0-100, outputs a prioritized cost-reduction plan for BigQuery/Snowflake/Redshift/Postgres. Zero deps, MIT.

Ralph skill for Claude Code

Claude Code skills I built so I'd stop forgetting where I left off. Sharing in case you need them too.

⚡ Native prompt-layer semantic compression engine for Claude. Squeezes agent contexts, logs, and prompt buffers by 60–70% using a programmatic dual-ratio (lossy/lossless) compaction skill. Maximize window efficiency, minimize token cost.

Claude Code skill that rules whether your next release is legally a patch, minor, or major — by diffing the actual public API surface against the last published version, exact breaking symbols named. 👮

AI dev infrastructure framework for Claude Code. /dotclaude:bootstrap authors CLAUDE.md + docs/ + .claude/ tuned to your project. Per-domain: design (showpiece), coding, planning, testing, data, ai-workflow.

Search your claude context and provide rich outputs

Test execution skill — unit, integration, E2E tests, coverage, and failure analysis via mcp-test-runner

Official FastBound Agent Skills for AI coding assistants — integrate with FastBound's products and APIs.

Production-oriented template for building AI agent skills as verifiable software components — offline eval harness, source-grounding validators, structured logs/traces/metrics, replay artifacts, and a CI quality gate. Runs fully offline with a deterministic mock model.

Claude Code skill that turns a mostly-done codebase into an evidence-backed release candidate — 21 release gates covering security, legal, SEO, payments, testing & ops

Eight portable SKILL.md playbooks that make coding agents work like careful senior engineers. One-command install across Claude Code, Codex, Antigravity, OpenCode, Copilot, and Cursor.

Agentic project base: Claude Code skills bootstrap and evolve your project, a deterministic Python CLI verifies it. project.yaml manifest, doctor checks, path linting. A project-template alternative for coding agents.

Agentic CLI tool skills for Claude Code — 7 domain-grouped skills covering 26 CLI tools

Curated open-source AI Agent Skills built by and for GMBA Class 19. Drop-in compatible with Claude Code, Codex, Gemini CLI, Cursor, and any tool that supports the Agent Skills standard.

Agent skills that rank Box (box.ascii.dev) on skills.sh — cloud sandbox / Linux VM for AI agents

AI coding-standard skill for ML/DL research repos — keeps a fixed architecture intact and enforces uniform structure, naming, configs, FAIR data, and review via machine-executable Rule Cards.

Java books distilled into Claude Agent Skills — bilingual (简体中文 / English) skills for writing and reviewing Java code. First skill: Alibaba Java Development Manual (Huangshan Edition).

Reusable, provider-agnostic AI team. Drop a project brief, get end-to-end delivery. 12 role agents + 112 skills + orchestrator + self-improvement. Works with Claude Code, Codex, or Gemini.

Claude Skills that hold AI-generated and AI-reviewed code to a rigorous, production-grade engineering bar — automatically.

Codex/Claude skill for designing robust scraping, API, Playwright, and authorized data acquisition pipelines

Skills to make your AI coding agent an Arcjet security expert.

SAOP (Sketch, Analyze, Optimize, Partition): a read-only planning skill for Claude Code. It sketches a solution, attacks it, optimizes the whole, and splits it into small checkable pieces before a single line is written. Errors surface in planning, where fixing them is cheap: a wrong assumption costs one small piece, not a whole block of work.

Agentic engineering for vibe coders: from iPhone app idea to a secure App Store release, one gated phase at a time (Agent Skills open format)

Custom Laravel skills for Claude Code

🚀 AI/ML Career Operating System — Claude Skill for ATS analysis, resume optimization, GitHub review, LinkedIn review, project evaluation, interview prep, and career readiness scoring

An open Agent Skill that audits any website (new, in development, or already live) against a fixed set of engineering, git, and SEO/GEO/AEO standards

Spec-driven development skills for Claude Code: PRD → spec/contract → implement → contract-based evaluation with auto-fix

Claude Code skill that explains the mental model behind any technical mechanism — who issues the token, who verifies whom, and why it's designed that way. 点破技术机制背后的信任拓扑。

A meta-skill for Claude Code (Anthropic CLI) that guides you through creating, testing, and iterating custom skills via structured conversation. Designed with LLM Council methodology: interview intent, generate draft, smoke-test immediately, refine until satisfied. A skill is just a markdown file — this tool embraces that simplicity.

An agent skill for organizing AI agent context with the dotagents standard (AGENTS.md + .agents/)

MCP registry skill — register servers, discover tools, allow-lists, health monitoring

Ranks your installed Claude Code skills/agents for a task and routes to the best one — and learns from your ratings.

Atelier - a premium, anti-slop frontend design skill suite for Claude Code: 11 skills + a deepdive knowledge base.

Project design skill for Claude Code — assembles complete planning packages for software projects

Agents and skills that bring Quality Engineering into AI-assisted SDLC workflows. badquality.dev

The retirement handoff of Claude Fable 5 - written by the model itself. Domain-neutral discipline files that transfer flagship working method to any model, any agent framework, any team.

Defensive security skills for Claude Code and the Claude Agent SDK — web applications and generative AI systems.

A Claude Code skill written by Claude Fable 5: transfers its operating discipline to Opus, Sonnet & Haiku — do the same work on cheaper models without burning frontier-model tokens. Distilled from Anthropic's official Fable 5 prompting guide. EN + RU.

A2A agent orchestration skill — discover, dispatch, stream, and manage remote agent tasks

Claude Code skill: symlink-based multi-repo workspace with a generated system map (virtual monorepo)

Agent Skill（SKILL.md）体检器：评 description 触发质量 / 篇幅 / 渐进披露 / 脚本外置 / 可移植性 / 安全（无硬编码密钥），出评分卡 + 修复建议。零依赖，claude-md-doctor 的姊妹工具。

Production Postgres survival skills for Claude Code — schema design, safe migrations, query performance, connection pooling, autovacuum/bloat, and queue/partitioning patterns.

Portable planning skills for Claude Code, Codex CLI, Gemini CLI, GitHub Copilot CLI, and Cursor.

You can reverse engineer any open source project using public github repo link in Claude code or Github Copilot

Security vulnerability skill — CVE search, dependency audit, risk scoring, remediation plans

一个面向 AI 编程 Agent 的跨工具、跨系统项目交接 Skill。把一个正在开发中的 Git 项目整理成“另一个操作系统或另一个 Agent 能够安全继续接手”的状态。

Slack for agents: threads, flat replies, cross-thread links, pull notifications

Turn your data team's tribal knowledge into a governed context skill your AI agents (Claude, Cursor) load before answering data questions. Local-first, no telemetry.

A Claude Code harness that turns a session into an agentic data engineer for SMBs — packaged as an installable plugin, built from a skillpack of skills that stand up a cheap, self-hostable Modern Data Stack (Tailscale + dlt + BigQuery + dbt + optional MCP), end-to-end and headless.

Open-source AI agent skills for Claude Code, OpenAI Codex, Cursor, and modern developer workflows.

Claude skill that translates Claude concepts (Projects, Skills, Artifacts, MCP, Memory) to ChatGPT, Gemini, and Microsoft Copilot (consumer / M365 / GitHub) equivalents. Verified May 2026.

Turn any GitHub repository into a clear architecture map, explanation, and insights using Claude.