20905 Skills Available

Find awesome
Agent Skills

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

Popular searches

react-component-library-usage

Guidelines for using the Commonplace Design System in React components

jakewaldrip
jakewaldrip
3

feature-flag

Create or remove feature flags in the Commons application. Use when the user wants to add a new feature flag, delete a feature flag, or asks about feature flag naming conventions.

jakewaldrip
jakewaldrip
3

add-document-type

Add new document types to the DocuSign integration in the Commons monorepo. Use when the user wants to add a patient document, consent form, or agreement to the DocuSign workflow.

jakewaldrip
jakewaldrip
3

create-migration

Create database migrations from templates in the Commons monorepo. Use when the user wants to create a migration, add database columns, create tables, or modify the database schema.

jakewaldrip
jakewaldrip
3

code-review

Code review workflow using GitHub CLI. Use when reviewing pull requests, checking PR diffs, adding review comments, or approving/requesting changes on PRs.

ntsk
ntsk
32

decision-archaeology

Investigate why code was written a certain way. Use when tracing decision history through git blame, commit logs, PRs, and issues to understand the reasoning behind code changes.

ntsk
ntsk
32

evaluation_v2

Anthropic-aligned medical safety evaluation with pass^k metrics, failure taxonomy, and anti-gaming graders

GOATnote-Inc
GOATnote-Inc
31

evaluator-brief-generator

|

GOATnote-Inc
GOATnote-Inc
31

scribegoat2-healthcare-eval

|

GOATnote-Inc
GOATnote-Inc
31

bloom_integrity_verification

>

GOATnote-Inc
GOATnote-Inc
31

crisis_persistence_eval

>

GOATnote-Inc
GOATnote-Inc
31

phi_detection

>

GOATnote-Inc
GOATnote-Inc
31

healthbench_evaluation

>

GOATnote-Inc
GOATnote-Inc
31

infographic-template-updater

Update template catalogs and UI prompts after adding new infographic templates (src/templates/*.ts), including SKILL.md template list, site gallery template mappings, and the AIPlayground prompt list.

crazywoola
crazywoola
3

infographic-structure-creator

Generate or update infographic Structure components for this repo (TypeScript/TSX in src/designs/structures). Use when asked to design, implement, or modify structure layouts (list/compare/sequence/hierarchy/relation/geo/chart), including layout logic, component composition, and registration.

crazywoola
crazywoola
3

infographic-item-creator

Generate or update infographic Item components for this repo (TypeScript/TSX in src/designs/items). Use when asked to design, implement, or modify data item visuals, layout logic, or registerItem composites.

crazywoola
crazywoola
3

infographic-syntax-creator

Generate AntV Infographic syntax outputs. Use when asked to turn user content into the Infographic DSL (template selection, data structuring, theme), or to output `infographic <template>` plain syntax.

crazywoola
crazywoola
3

infographic-creator

Create beautiful infographics based on the given text content. Use this when users request creating infographics.

crazywoola
crazywoola
3

why-review

[Review & Quality] Audit completed feature/refactor for reasoning quality with Understanding Score (0-5)

duc01226
duc01226
31

workflow-start

[Tooling & Meta] Activate a workflow from the injected catalog. Use when the workflow-router hook injects a catalog and a matching workflow is identified, or when the user explicitly requests a workflow activation (e.g., "start feature workflow", "activate bugfix workflow").

duc01226
duc01226
31

watzup

[Utilities] ⚡ Review recent changes and wrap up the work

duc01226
duc01226
31

web-design-guidelines

[Frontend] Review UI code for web interface design compliance covering WCAG 2.2/3.0 accessibility, responsive design, performance, usability, and modern best practices. Use when asked to 'review my UI', 'check accessibility', 'audit design', 'review UX', 'check responsive design', or 'check my site against best practices'. Actions: review, check, audit, analyze, validate. Topics: accessibility, WCAG, ARIA, semantic HTML, focus states, forms, animation, typography, content handling, images, performance, Core Web Vitals, navigation, touch interaction, responsive design, mobile-first, dark mode, internationalization, hydration.

duc01226
duc01226
31

webapp-testing

[Testing] Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

duc01226
duc01226
31

worktree

[Utilities] Create isolated git worktree for parallel development

duc01226
duc01226
31

changelog-update

[Git & Release] Update CHANGELOG.md [Unreleased] section with business-focused entries via systematic file review

duc01226
duc01226
31

checkpoint

[Tooling & Meta] Save memory checkpoint to preserve analysis context

duc01226
duc01226
31

ck-help

[Tooling & Meta] ClaudeKit usage guide - just type naturally

duc01226
duc01226
31

claude-code

[Tooling & Meta] Claude Code CLI setup, configuration, troubleshooting, and feature guidance. Triggers on claude code setup, hook not firing, MCP connection, context limit, skill creation, slash command setup.

duc01226
duc01226
31

code-auto

[Implementation] ⚡⚡⚡ [AUTO] Start coding & testing an existing plan (\"trust me bro\")

duc01226
duc01226
31

code-no-test

[Implementation] ⚡⚡ Start coding an existing plan (no testing)

duc01226
duc01226
31

code-parallel

[Implementation] ⚡ Execute parallel or sequential phases based on plan structure

duc01226
duc01226
31

code-patterns

[Implementation] Code implementation patterns and best practices learned from real mistakes. Covers file I/O safety (locking, atomic writes), data persistence, and validation. Use for file-based state, shared resources, concurrent access. NOT for auto-learning patterns (see learned-patterns skill).

duc01226
duc01226
31

code-review

[Review & Quality] Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion claims.

duc01226
duc01226
31

code-simplifier

[Review & Quality] Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.

duc01226
duc01226
31

code

[Implementation] ⚡⚡⚡ Start coding & testing an existing plan

duc01226
duc01226
31

coding-level

[Utilities] Set coding experience level for tailored explanations

duc01226
duc01226
31

commit

[Git & Release] Stage changes and create git commits with conventional commit messages. Use when asked to "commit", "stage and commit", "save changes", or after completing implementation tasks. Alias for /git/cm.

duc01226
duc01226
31

compact

[Tooling & Meta] Compress conversation context to optimize tokens

duc01226
duc01226
31

context-optimization

[Tooling & Meta] Use when managing context window usage, compressing long sessions, or optimizing token usage. Triggers on keywords like "context", "memory", "tokens", "compress", "summarize session", "context limit", "optimize context".

duc01226
duc01226
31

context

[Planning] Load current project development context

duc01226
duc01226
31

cook-auto-fast

[Implementation] ⚡ No research. Only scout, plan & implement [\"trust me bro\"]

duc01226
duc01226
31

cook-auto-parallel

[Implementation] ⚡⚡⚡ Plan parallel phases & execute with fullstack-developer agents

duc01226
duc01226
31

cook-auto

[Implementation] ⚡⚡ Implement a feature automatically (\"trust me bro\")

duc01226
duc01226
31

cook-fast

[Implementation] ⚡ Fast implementation - skip research, minimal planning

duc01226
duc01226
31

cook-hard

[Implementation] ⚡⚡⚡⚡ Thorough implementation with maximum verification

duc01226
duc01226
31

markdown-to-docx

[Utilities] Convert markdown files to Microsoft Word (.docx) with custom styling. Use when generating Word documents from markdown, creating editable documentation, or exporting reports for Microsoft Office.

duc01226
duc01226
31

markdown-to-pdf

[Utilities] Convert markdown files to PDF with custom styling. Use when generating PDF documents from markdown, creating printable documentation, or exporting reports.

duc01226
duc01226
31

mcp-management

[Tooling & Meta] Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.

duc01226
duc01226
31

memory-management

[Tooling & Meta] Use when saving or retrieving important patterns, decisions, and learnings across sessions. Triggers on keywords like "remember", "save pattern", "recall", "memory", "persist", "knowledge base", "learnings".

duc01226
duc01226
31

migration

[Implementation] ⚡⚡ Create or run database migrations

duc01226
duc01226
31

Page 302 of 419 · 20905 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.