83431 Skills Available

Find awesome
Agent Skills

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

Popular searches

docs-seeker

Searching internet for technical documentation using llms.txt standard, GitHub repositories via Repomix, and parallel exploration. Use when user needs: (1) Latest documentation for libraries/frameworks, (2) Documentation in llms.txt format, (3) GitHub repository analysis, (4) Documentation without direct llms.txt support, (5) Multiple documentation sources in parallel

vneseyoungster
vneseyoungster
2618

gemini-vision

Guide for implementing Google Gemini API image understanding - analyze images with captioning, classification, visual QA, object detection, segmentation, and multi-image comparison. Use when analyzing images, answering visual questions, detecting objects, or processing documents with vision.

vneseyoungster
vneseyoungster
2618

project-documentation

Comprehensive codebase documentation generator following a layered methodology. This skill should be used when scanning and documenting a codebase for the first time, when creating onboarding documentation for new developers, when generating architecture overviews, walkthroughs, and API references. Supports README generation, architecture diagrams, entry point documentation, pattern guides, and edge case documentation.

vneseyoungster
vneseyoungster
2618

figma-analyzer

Extract design assets and metadata from Figma using the Figma REST API.

vneseyoungster
vneseyoungster
2618

clean-code

Enforce SOLID, DRY, KISS principles during implementation.

vneseyoungster
vneseyoungster
2618

component-design

Design React/Vue components following atomic design and composition

vneseyoungster
vneseyoungster
2618

error-handling

Implement consistent error handling across the application.

vneseyoungster
vneseyoungster
2618

migration

Create reversible database migrations with rollback scripts.

vneseyoungster
vneseyoungster
2618

architecture-planning

Create detailed architecture plans with decision records and risk

vneseyoungster
vneseyoungster
2618

task-breakdown

Use when converting architecture plans into implementation phases. Creates independent, bite-sized phase files that can be executed separately.

vneseyoungster
vneseyoungster
2618

requirement-clarification

Generate clarifying questions from research findings. MUST be used

vneseyoungster
vneseyoungster
2618

user-intent-parser

Parse user requirements into structured format with explicit

vneseyoungster
vneseyoungster
2618

repomix

Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate multiple output formats (XML, Markdown, plain text), preserve file structure and context, optimize for AI consumption with token counting, filter by file types and directories, add custom headers and summaries. Use when packaging codebases for AI analysis, creating repository snapshots for LLM context, analyzing third-party libraries, preparing for security audits, generating documentation context, or evaluating unfamiliar codebases.

vneseyoungster
vneseyoungster
2618

dependency-analysis

Analyze project dependencies for security vulnerabilities, outdated

vneseyoungster
vneseyoungster
2618

pattern-detection

Detect and document existing code patterns in a codebase. Use to

vneseyoungster
vneseyoungster
2618

sequential-thinking

Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope.

vneseyoungster
vneseyoungster
2618

context-preservation

Generate structured handoff summaries between workflow phases.

vneseyoungster
vneseyoungster
2618

git-workflow

Follow git conventions for commits, branches, and PRs.

vneseyoungster
vneseyoungster
2618

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.

vneseyoungster
vneseyoungster
2618

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

vneseyoungster
vneseyoungster
2618

test-driven-development

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

vneseyoungster
vneseyoungster
2618

code-review

Review code for quality, security, performance, and maintainability.

vneseyoungster
vneseyoungster
2618

documentation

Generate and update documentation from code.

vneseyoungster
vneseyoungster
2618

security-scan

Scan code for OWASP vulnerabilities and security issues.

vneseyoungster
vneseyoungster
2618

test-generation

Generate comprehensive tests following project testing patterns.

vneseyoungster
vneseyoungster
2618

writing-skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

vneseyoungster
vneseyoungster
2618

secrets

|

fred-drake
fred-drake
263

provision-nixos-server

|

fred-drake
fred-drake
263

pi-module

|

fred-drake
fred-drake
263

infrastructure

|

fred-drake
fred-drake
263

container-update-report

Update container digests and deploy affected hosts end-to-end. Use when the user wants to check for container updates, update container digests, or deploy container changes. Triggers on requests like "update containers", "check for container updates", "deploy container updates", or "run container-update-report".

fred-drake
fred-drake
263

cmux-pi-subagent

Spawn a pi subagent in a visible cmux pane, run a task in it, collect the answer, and close the pane. Use when you want to delegate a self-contained task to a separate pi process running in its own cmux split (deploy → execute → collect → remove), instead of doing the work inline. Requires running inside a cmux surface.

built for fdrake
built for fdrake
263

woodpecker-pipelines

Patterns and hard-won gotchas for designing, debugging, and writing Woodpecker CI pipeline files. Use when authoring or editing `.woodpecker.yml` / `.woodpecker/*.yml`, when a pipeline shows `error` status with no step logs, when shell variables in `commands:` blocks are not interpolating as expected, when splitting between single-file and multi-pipeline directory layouts, or when running iOS signing / archive flows on a non-interactive Mac agent. Companion to the `woodpecker-cli` skill (which is the CLI reference) — this one is the workflow-design + debugging reference.

fred-drake
fred-drake
263

woodpecker-cli

Reference for the Woodpecker CI command-line tool. Use when working with Woodpecker CI pipelines, managing repositories, secrets, registries, organizations, or users via the CLI. Covers pipeline operations (start, stop, approve, logs), repository management, secret/registry configuration, and local pipeline execution.

fred-drake
fred-drake
263

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.

fred-drake
fred-drake
263

hytale-modding

Develop mods for Hytale, a voxel-based sandbox RPG by Hypixel Studios. Use when creating server plugins (commands, events, entities), working with the Entity Component System (ECS), creating custom UI, managing inventory, world generation, prefabs, or publishing mods. Covers Java 25 development with Maven, IntelliJ IDEA setup, and the complete plugin development lifecycle.

fred-drake
fred-drake
263

humanizer

|

fred-drake
fred-drake
263

woodpecker-upgrade

Upgrade Woodpecker CI across the server, Linux agent, and macOS agent while keeping the gRPC protocol version in lockstep. Use when the user wants to upgrade Woodpecker, bump the agent or server, or investigate a "GRPC version mismatch" error.

fred-drake
fred-drake
263

claude-plugin

|

fred-drake
fred-drake
263

s-audit

>

falkicon
falkicon
257

k-fenui

>

falkicon
falkicon
257

using-mechanic

>

falkicon
falkicon
257

k-apidefs

>

falkicon
falkicon
257

k-create-skill

>

falkicon
falkicon
257

k-desktop

>

falkicon
falkicon
257

s-debug

>

falkicon
falkicon
257

s-clean

>

falkicon
falkicon
257

k-mechanic

>

falkicon
falkicon
257

k-ecosystem

>

falkicon
falkicon
257

s-research

>

falkicon
falkicon
257

Page 841 of 1669 · 83431 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.