77982 Skills Available

Find awesome
Agent Skills

Agent-Skills.md is a agent skills marketplace, to find the right agent skills for you.

Popular searches

typescript

TypeScript and React/TSX coding conventions and patterns

JustinFirsching
JustinFirsching
0

api-design

REST API design patterns for endpoints, responses, errors, and conventions

JustinFirsching
JustinFirsching
0

testing

Testing strategy, patterns, and best practices for unit, integration, and e2e tests

JustinFirsching
JustinFirsching
0

security-check

Security audit patterns for identifying vulnerabilities and security issues

JustinFirsching
JustinFirsching
0

python

Python coding conventions, type hints, and FastAPI patterns

JustinFirsching
JustinFirsching
0

project-structure

Project organization conventions for files, modules, and directory structure

JustinFirsching
JustinFirsching
0

go

Go idioms, error handling, and API patterns

JustinFirsching
JustinFirsching
0

code-review

Systematic code review checklist for quality, correctness, and maintainability

JustinFirsching
JustinFirsching
0

database-migration-create

Safely creates database migrations

cpa03
cpa03
0

madappgang-claude-code-debugging-strategies

Universal debugging strategies and techniques applicable across all technology stacks. Use when approaching unknown bugs or need language-agnostic debugging methodology.

cpa03
cpa03
0

git-commit-standard

Generates conventional commits based on file changes. Analyzes diffs and creates properly formatted commit messages.

cpa03
cpa03
0

test-suite-create

Creates a comprehensive test suite for a feature

cpa03
cpa03
0

resilience-check

Checklist for reliability engineering

cpa03
cpa03
0

react-component-create

Create new React components following project patterns and best practices. Includes proper typing, testing, and documentation.

cpa03
cpa03
0

professor-for-testing-agentic-qe-skill-builder

Build comprehensive testing skills with TDD, quality engineering, and automated test generation. Use when creating test suites or improving testing practices.

cpa03
cpa03
0

planning-with-files

Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.

cpa03
cpa03
0

pattern-extraction

Extracts reusable patterns from code changes

cpa03
cpa03
0

obra-superpowers-writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code

cpa03
cpa03
0

obra-superpowers-using-git-worktrees

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

cpa03
cpa03
0

obra-superpowers-test-driven-development

Use when implementing any feature or bugfix, before writing implementation code

cpa03
cpa03
0

obra-superpowers-systematic-debugging

Systematic debugging approach with 4-phase root cause analysis. Use when troubleshooting complex bugs, identifying root causes, or following structured debugging methodology.

cpa03
cpa03
0

obra-superpowers-brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

cpa03
cpa03
0

muratcankoylan-agent-skills-for-context-engineering-memory-systems

Context management and persistent memory systems for AI agents. Use when optimizing context windows or building agent memory systems.

cpa03
cpa03
0

modu-ai-moai-adk-moai-tool-opencode

Multi-agent orchestration using MoAI framework for complex task coordination. Use when orchestrating multiple agents or building multi-agent workflows.

cpa03
cpa03
0

maxritter-claude-codepro-backend-models-standards

Backend development standards and best practices for API design, database, security, and performance. Use when designing or reviewing backend systems.

cpa03
cpa03
0

security-audit

Procedure for analyzing code or dependencies for vulnerabilities

cpa03
cpa03
0

typescript-refactor

Safely refactor TypeScript code while maintaining type safety and test coverage. Includes verification steps.

cpa03
cpa03
0

git-commit-message

Auto-generates conventional commit messages from git diffs with tiered format enforcement. Analyzes staged changes to produce meaningful commit messages following Conventional Commits specification.

cpa03
cpa03
0

ci-pipeline-update

Updates CI/CD pipelines for DevOps Engineer

cpa03
cpa03
0

api-endpoint-create

Standard procedure for creating robust API endpoints

cpa03
cpa03
0

code-review-checklist

Generates a code review checklist for the Code Reviewer agent

cpa03
cpa03
0

dependency-audit

Audit npm dependencies for security vulnerabilities, outdated packages, and license compliance.

cpa03
cpa03
0

docs-update

Standard procedure for updating documentation

cpa03
cpa03
0

rules-optimizer

Create and optimize .claude/rules/*.md files for repository-specific coding conventions. Use when asked to create, optimize, or review rules, when a pattern keeps recurring that Claude gets wrong, or when codifying a convention. Not for editing CLAUDE.md — edit that file directly.

hairihou
hairihou
0

session-insights

Analyze the current conversation for inefficiencies and improvement opportunities. Use when "how did this session go", "what went wrong", "what could I have done better", or reviewing session quality. Not for personal reflection — use retrospect. Not for logging work — use diary.

hairihou
hairihou
0

constructive-feedback

Transform harsh, vague, or emotionally charged feedback text into actionable form using the Situation-Behavior-Impact-Suggestion framework. Use when "sounds too harsh", "how should I say this", "draft feedback", or "rephrase this message".

hairihou
hairihou
0

code-critic

Brutally honest code review targeting over-engineering, premature abstraction, and defensive excess. Use when "is this over-engineered", "check complexity", "too much abstraction", or "what do you think of this code". Not for PR comments — use conventional-comments for that.

hairihou
hairihou
0

bonsai

Maintain and groom config files in the current repository. Use when "bonsai", "tidy up", "prune configs", "clean up", "spring cleaning", or reviewing config health. Not for code quality review — use code-critic for that.

hairihou
hairihou
0

1on1-prep

Prepare for 1on1 meetings using a Psychological Safety x Responsibility framework. Use when preparing for a 1on1, noticing behavioral changes, or planning a difficult conversation with a report.

hairihou
hairihou
0

conventional-comments

Format code review comments using Conventional Comments labels and decorations. Use when writing inline review comments on a PR diff. Not for creating PRs — use pr for that. Not for complexity analysis — use code-critic for that.

hairihou
hairihou
0

decision-log

Record or search technical decisions in a persistent SQLite database. Default mode records the most recent decision from conversation with alternatives and reasoning. Use with "search" argument to query past decisions.

hairihou
hairihou
0

devils-advocate

Structured critical analysis using parallel advocate and critic agents. Use when asked to evaluate a decision, play devils advocate, challenge an approach, or weigh pros and cons of architecture/technology choices.

hairihou
hairihou
0

diary

Append completed tasks and learnings to an Obsidian daily note. Use when "diary", "log", "record what I did", "end of day", or "wrap up". Not for session quality — use session-insights. Not for personal reflection — use retrospect.

hairihou
hairihou
0

npm-update-report

Dependency update workflow with vulnerability assessment and verification. Use when asked to check outdated packages, bump dependencies, run audit, do periodic dependency maintenance, or when security vulnerabilities are reported.

hairihou
hairihou
0

pr

Create or update a GitHub pull request. Use when asked to create a PR, submit for review, or push changes as a PR. Not for code review comments — use conventional-comments for that.

hairihou
hairihou
0

retrospect

Guided personal reflection that separates fact, interpretation, and emotion through structured inquiry. Use when "something feels off", "need to process this", "had a conflict", or decisions feel unclear. Not for technical decision analysis — use devils-advocate for that.

hairihou
hairihou
0

speclet-council

Run parallel reviews on draft/spec/ticket inputs and emit Council artifacts

danielcastro-dev
danielcastro-dev
0

speclet-loop

Execute one autonomous iteration - implement the next story from spec.json

danielcastro-dev
danielcastro-dev
0

speclet-ticket

Convert a large draft into individual tickets for isolated implementation sessions

danielcastro-dev
danielcastro-dev
0

speclet-spec

Convert a draft document into an executable spec.json with trackable stories

danielcastro-dev
danielcastro-dev
0

Page 1550 of 1560 · 77982 results

Adoption

Agent Skills are supported by leading AI development tools.

FAQ

Frequently asked questions about Agent Skills.

01

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.

02

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.

03

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.

04

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.

05

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.