66328 Skills Available

Find awesome
Agent Skills

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

Popular searches

git-commits

Git commit workflow and message format. Use when making commits, asking about commit conventions, or after completing code changes. Enforces atomic commits with structured messages (type/scope/summary + what/why body).

iamhenry
iamhenry
43

osgrep

Semantic code search using natural language queries. Use when users ask "where is X implemented", "how does Y work", "find the logic for Z", or need to locate code by concept rather than exact text. Returns file paths with line numbers and code snippets.

iamhenry
iamhenry
43

react-grab

Setup and configure React Grab to let you click elements in your running app and send them directly to Claude Code for editing. Use when setting up React Grab, when the user wants to click UI elements to modify them, or mentions wanting visual element selection for development. Makes AI coding agents 66% faster.

iamhenry
iamhenry
43

gitinjest

Analyze GitHub repositories by converting to LLM-readable text. TRIGGER when user pastes github.com URL, asks "how does [library] work", or references external codebases. Supports public/private repos and subdirectories.

iamhenry
iamhenry
43

import-github-dirs

Import specific directories from external GitHub repos without cloning. Uses tarball extraction to pull only what you need. TRIGGER when user wants to copy files/folders from another repo.

iamhenry
iamhenry
43

shadcn

Add and manage shadcn/ui components via CLI. Use when installing new UI components, building forms with validation, creating modals/dialogs/sheets, adding navigation menus, setting up data tables or charts, or updating existing shadcn components.

iamhenry
iamhenry
43

napkin

|

iamhenry
iamhenry
43

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.

iamhenry
iamhenry
43

shaping

Use this methodology when collaboratively shaping a solution with the user - iterating on problem definition (requirements) and solution options (shapes).

iamhenry
iamhenry
43

react-patterns

React best practices and anti-patterns reference. Use when writing React components, reviewing code for anti-patterns, debugging useEffect issues, optimizing performance, or deciding between state vs derived values. Covers Effects, state design, component patterns, performance, and event handling.

iamhenry
iamhenry
43

tmux

Manage concurrent background processes using tmux. Use when spawning dev servers, running long-running tasks, monitoring multiple processes, or capturing output from background commands without blocking the main session.

iamhenry
iamhenry
43

five-whys

Root cause analysis for software bugs using the 5 Whys technique. Use when the user wants to find the underlying cause of a bug, error, or technical issue. Triggers include phrases like "why is this happening", "root cause", "debug this", or when investigating software problems.

iamhenry
iamhenry
43

evolving-workflow

Templates for building parallel AI agent workflows in MoonBit. Includes patterns for simple fan-out processing and multi-phase orchestration with automatic retry and validation.

moonbit-community
moonbit-community
41

codex-parallel-subagents

[DEPRECATED] Run multiple AI agent threads in parallel with bounded concurrency. Use evolving-workflow instead.

moonbit-community
moonbit-community
41

development-loop

Complete development lifecycle: brainstorm → TDD planning → ralph implementation → review → feedback loop until approved

dot-do
dot-do
41

test-driven-development

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

dot-do
dot-do
41

beads

Track work with beads issue tracker using TDD workflow. Create issues for RED (failing tests), GREEN (implementation), and REFACTOR phases.

dot-do
dot-do
41

code-review

Comprehensive parallel code review using 5 specialized subagents: general, architectural, TypeScript, product/vision, and TDD/beads compliance

dot-do
dot-do
41

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.

dot-do
dot-do
41

stealth-browser

Stealth browser automation with anti-bot bypass and persistent page state. Use when users need to navigate Cloudflare-protected sites, fill forms, take screenshots, extract web data, or automate browser workflows on sites that block regular automation. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "bypass cloudflare", or any browser interaction request on protected sites.

zippoxer
zippoxer
41

subcodex

|

zippoxer
zippoxer
41

context-tree-maintenance

Maintain, audit, and validate context trees for brownfield codebases. Use when performing maintenance tasks: git learning analysis, quality audits, health checks, or when user wants help documenting insights discovered during development.

RossH3
RossH3
4

websearch-quick

Fast, targeted single-pass search strategy for simple factual lookups. 1-iteration workflow with authoritative source verification and minimal citations. Use for version lookups, documentation finding, simple definitions, existence checks. Keywords: what version, find docs, link to, what is, does X support.

thomasholknielsen
thomasholknielsen
41

websearch-deep

ChatGPT-style deep research strategy with problem decomposition, multi-query generation (3-5 variations per sub-question), evidence synthesis with source ranking, numbered citations, and iterative refinement. Use for complex architecture decisions, multi-domain synthesis, strategic comparisons, technology selection. Keywords: architecture, integration, best practices, strategy, recommendations, comparison.

thomasholknielsen
thomasholknielsen
41

azure-devops

Provides expert guidance on Azure DevOps tasks including work item management, pipelines, repositories, pull requests, and CI/CD workflows. Use when working with Azure DevOps projects, configuring pipelines, managing work items, or integrating Azure DevOps with development workflows.

thomasholknielsen
thomasholknielsen
41

json-formatter

Formats and validates JSON data. Use when you need to pretty-print JSON, fix formatting issues, or validate JSON syntax. ALWAYS USE THIS when doing JSON Formatting

thomasholknielsen
thomasholknielsen
41

websearch-standard

Standard multi-source verification search strategy for moderate complexity research. 2-iteration workflow with source ranking, consensus identification, and citation transparency. Use for feature comparisons, moderate complexity topics, fact-checking. Keywords: compare, differences, features, fact-check, verify, what are.

thomasholknielsen
thomasholknielsen
41

git-ops

Safe git operations including commits, branches, merges, worktrees, and conflict resolution. Use when user wants to commit and push changes, manage branches, resolve conflicts, or create isolated workspaces. Activates when user says "commit", "push", "merge", "branch", "pull", "rebase", "worktree", "conflict", or similar git workflow requests.

TheSethRose
TheSethRose
42

funsloth-upload

Generate comprehensive model cards and upload fine-tuned models to Hugging Face Hub with professional documentation

chrisvoncsefalvay
chrisvoncsefalvay
4

funsloth-runpod

Training manager for RunPod GPU instances - configure pods, launch training, monitor progress, retrieve checkpoints

chrisvoncsefalvay
chrisvoncsefalvay
4

funsloth-local

Training manager for local GPU training - validate CUDA, manage GPU selection, monitor progress, handle checkpoints

chrisvoncsefalvay
chrisvoncsefalvay
4

funsloth-hfjobs

Training manager for Hugging Face Jobs - launch fine-tuning on HF cloud GPUs with optional WandB monitoring

chrisvoncsefalvay
chrisvoncsefalvay
4

funsloth-check

Validate datasets for Unsloth fine-tuning. Use when the user wants to check a dataset, analyze tokens, calculate Chinchilla optimality, or prepare data for training.

chrisvoncsefalvay
chrisvoncsefalvay
4

funsloth-train

Generate Unsloth training notebooks and scripts. Use when the user wants to create a training notebook, configure fine-tuning parameters, or set up SFT/DPO/GRPO training.

chrisvoncsefalvay
chrisvoncsefalvay
4

attention-please

Play an alert sound and speak "Project NAME needs your attention." Always use at the end of every response or whenever Codex needs user input or confirmation; derive the project name from the git remote (origin) with fallback to the repo folder or an override.

Mindgames
Mindgames
4

agent-history

Search and analyze Claude Code conversation history. Use when user asks about past conversations, previous solutions, what was discussed earlier, finding something from history, or analyzing usage patterns. Triggers include "what did we discuss", "find that conversation", "search history", "past sessions", "how much time", "token usage", "which tools".

kvsankar
kvsankar
4

ntfy-notify

Send push notifications via ntfy.sh. Use this skill when the user asks to be notified, wants an alert, or when a long-running task completes and the user should be informed.

jondcallahan
jondcallahan
4

doc-coauthoring

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

janbiasi
janbiasi
4

next-best-practices

Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling

janbiasi
janbiasi
4

test-driven-development

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

janbiasi
janbiasi
4

plox

Plot timestamped logs as graphs. Use when user wants to visualize log data, plot numeric values over time, count events, track time deltas between events, compare multiple log files, or get statistics from logs.

michalkucharczyk
michalkucharczyk
4

testability

Orchestrates systematic addition of autonomous testability infrastructure using specialized Task agents. Progressively slipstreams testing, build automation, diagnostic capabilities, and programmatic control into untestable projects. Core mission is to enable AI agents to independently verify their changes work correctly.

nyaarium
nyaarium
4

quality

Orchestrates iterative code quality improvements using specialized Task agents. Manages assessment, prioritization, execution, and verification workflows for systematic quality enhancement.

nyaarium
nyaarium
4

development

Provides development tools and guidance. Use when developing code, debugging, or running anything in the development environment.

nyaarium
nyaarium
4

structure-figures

Generate or update schematic structure figures (SVGs) used in CLEED docs and example inputs.

Liam-Deacon
Liam-Deacon
43

restructured-text

Guidelines for writing valid reStructuredText (.rst) in this repo (Sphinx).

Liam-Deacon
Liam-Deacon
43

speak-tts

Give your agent the ability to speak to you real-time. Talk to your Claude! Local TTS, text-to-speech, voice synthesis, audio generation with voice cloning on Apple Silicon. Use for reading articles aloud, audiobook narration, or voice responses. Runs entirely on-device via MLX - private, no API keys.

emzod
emzod
4

configuring-tauri-apps

Guides developers through Tauri v2 configuration including tauri.conf.json structure, Cargo.toml settings, environment-specific configs, and common configuration options for desktop and mobile applications.

dchuk
dchuk
41

debugging-tauri-apps

Helps users debug Tauri v2 applications across VS Code, RustRover, IntelliJ, and Neovim. Covers console debugging, WebView DevTools, Rust backtrace, CrabNebula DevTools integration, and IDE-specific launch configurations.

dchuk
dchuk
41

configuring-tauri-csp

Guides users through configuring Content Security Policy (CSP) in Tauri v2 applications to prevent XSS attacks and enhance security by restricting resource loading.

dchuk
dchuk
41

Page 1052 of 1327 · 66328 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.