What are Agent Skills?

Agent Skills are reusable, production-ready capability packs for AI agents. Each skill lives in its own folder and is described by a SKILL.md file with metadata and instructions.

What does this agent-skills.md site do?

Agent Skills is a curated directory that indexes skill repositories and lets you browse, preview, and download skills in a consistent format.

Where are skills stored in a repo?

By default, the site scans the skills/ folder. You can also submit a URL that points directly to a specific skills folder.

What is required inside SKILL.md?

SKILL.md must include YAML frontmatter with at least name and description. The body contains the actual guidance and steps for the agent.

How can I submit a repo?

Click Submit in the header and paste a GitHub URL that points to a skills folder. We’ll parse it and add any valid skills to the directory.

Find awesome Agent Skills

git-create-pr

Create a GitHub Pull Request with conventional commit format and pre-filled

mgiovani

git-commit

Generate conventional commits following conventionalcommits.org specification.

mgiovani

gh-daily

Generate smart standup reports from GitHub Issues activity and git history.

mgiovani

fix-bug

Fix bugs using test-driven debugging, root cause analysis, and comprehensive verification. Automatically activates when users want to fix a bug, debug an issue, resolve an error, investigate failing tests, or address problems in the codebase.

mgiovani

find-skills

Discover and install third-party agent skills from the open skills ecosystem (skills.sh). This skill should be used when users want to find, install, update, or manage external skills for Claude Code or other AI agents, or when they mention skills.sh, npx skills, or want to extend their agent with community skills.

mgiovani

ci-generate

Generate CI/CD pipeline configurations for GitHub Actions, GitLab CI,

mgiovani

test-suite

Generate comprehensive test suites with coverage analysis and parallel test writing. Automatically activates when users want to write tests, add test coverage, generate test cases, improve testing, or analyze coverage gaps. Supports pytest, vitest, jest, and all major test frameworks.

mgiovani

team-review

Multi-agent PR review team orchestration with 7 specialized reviewers for security-sensitive or architectural PRs. Spawns architecture, security, performance, testing, style, docs/UX, and adversary reviewers as a coordinated team. Premium review for critical code changes.

mgiovani

team-implement

Spec-driven team orchestration: adaptive development team that scales from 3 to 11 agents based on project complexity. Accepts plain text, Jira tickets, GitHub issues, PRs, files, directories, or URLs as input. Plans thoroughly first, gets user approval, then implements with parallel agents.

mgiovani

skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

mgiovani

review-security

Perform comprehensive security review targeting OWASP Top 10 2025 vulnerabilities

mgiovani

review-perf

Perform comprehensive performance review analyzing database queries,

mgiovani

review-deps

Audit project dependencies for vulnerabilities, license compliance risks,

mgiovani

docs-update

Update documentation by synchronizing with the current codebase state.

mgiovani

docs-rfc

Create numbered RFC (Request For Comments) documents for proposing and

mgiovani

docs-init

Initialize comprehensive documentation structure for a project based

mgiovani

docs-diagram

Generate Mermaid diagrams from codebase analysis including architecture,

mgiovani

docs-check

Validate documentation freshness, completeness, and quality against the

mgiovani

docs-adr

Create numbered Architecture Decision Records (ADR) documenting architectural

mgiovani

create-rule

Create a new memory rule following Claude Code best practices for project

mgiovani

create-command

Create a new slash command (skill) following best practices and prompt

mgiovani

using-firebase

Comprehensive Firebase development guidance for GCP-hosted applications. Covers Firestore database operations (CRUD, queries, transactions, data modeling), Cloud Functions (1st and 2nd generation, TypeScript and Python, all trigger types), Firebase CLI operations, emulator setup and data persistence, security rules (Firestore and Storage), authentication integration, hosting configuration, and GCP service integration. Use when working with Firebase projects, deploying Cloud Functions, querying Firestore, setting up triggers (Firestore, Auth, Storage, HTTP, Callable, Scheduled, Pub/Sub), managing security rules, configuring hosting rewrites/headers, managing secrets, or integrating with GCP services like BigQuery and Cloud Tasks. Triggers include firebase, firestore, cloud functions, firebase functions, firebase hosting, firebase auth, firebase storage, firebase emulator, firebase deploy, firebase init, firebase rules, callable function, scheduled function, onDocumentCreated, onRequest, onCall, onSchedule.

Claude Skills Community

bd-workflow

How to use bd (beads) for issue tracking, ready work, status updates, and comments in this repo.

lambdamechanic

python

Default Python stack for Lambda: uv + Astral tools, typed code, schemas, and Hypothesis.

lambdamechanic

galahad

how to approach tests, types and coverage

lambdamechanic

dumbwaiter-mcp

Provider-agnostic wait-for-change skill that uses the Dumbwaiter MCP server to wait on PR events (GitHub first) via wait.start/status/cancel/await, with progress notifications and durable state.

lambdamechanic

lambda-workflow

One lifecycle for Lambda repos: choose a bd task, start work, land the PR, and watch GitHub via Dumbwaiter MCP until it merges.

lambdamechanic

landing-the-plane

Checklist for finishing work, pushing a branch, and opening a ready-for-review PR with tests and tracker updates.

lambdamechanic

testing-patterns

Testing patterns and standards for this codebase, including async effects, fakes vs mocks, and property-based testing.

lambdamechanic

typescript

Default TypeScript stack for Lambda: pnpm workspaces + Turbo, strict TS, and sensible DX helpers.

lambdamechanic

zfc

Zero Framework Cognition Principles

lambdamechanic

template-skill

Replace with description of the skill and when Claude should use it.

lambdamechanic

starting-the-task

A short checklist for kicking off work effectively: plan, branch, track with bd, and set up validation.

lambdamechanic

sk

How to use the repo-scoped sk CLI to manage Claude Skills in this codebase.

lambdamechanic

rust-guidelines

Pragmatic Rust conventions to keep code readable, testable, and performant for this project.

lambdamechanic

developing-openai-agents-sdk-agents

Build, create, debug, review, implement, and optimize agentic AI applications using the OpenAI Agents SDK for TypeScript. Use when creating new agents, defining tools, implementing handoffs between agents, adding guardrails, debugging agent behavior, reviewing agent code, or orchestrating multi-agent systems with the @openai/agents package.