Skip to content
Directory

Agent skills

Skills for AI coding agents, each with what it costs to load, how much of it is scripts and what it touches on your machine.

1,192 skills27 categories Measured from their files, refreshed weekly

How to read a skill

Tokens

What it costs to keep

Idle in context, in use when it runs, and up to with its linked files.

Model dependence

Scripts or instructions

Script-led, mixed or model-led: how much the model has to work out itself.

Touches

What it can reach

Shell, network, file writes, git and credentials, declared or detected.

Scores

Quality, security, repo health

Out of 100, each with what it is made of. Turn a card over to see them.

Showing 210 of 1192 skillsAgent Workflows Code Review And Quality Developer Tools Game Development Clear all
Model-led1,884 tokens in use

finishing-a-development-branch

322,961

Developer Tools · Devops And Releases

Verifies tests, detects your worktree setup, offers merge, pull request or keep, and cleans up after you decide.

Skill
27idle
1,884in use
1,884up to
Tokens, counted offlineView skill
Model-led1,444 tokens in use

receiving-code-review

322,961

Code Review And Quality · Developer Tools

Makes your coding agent verify review feedback against the codebase, ask about unclear items, push back when wrong and fix one at a time.

Skill
38idle
1,444in use
1,444up to
Tokens, counted offlineView skill
Model-led662 tokens in use

requesting-code-review

322,961

Code Review And Quality · Developer Tools

Sends a fresh code reviewer subagent the diff and requirements, then sorts findings into Critical, Important and Minor.

Skill
22idle
662in use
2,114up to
Tokens, counted offlineView skill
Mixed4,484 tokens in use

subagent-driven-development

322,961

Agent Workflows · Developer Tools

Runs an implementation plan with a fresh implementer subagent per task, a spec and quality review after each, and a final branch review.

Skill
17idle
4,484in use
10,486up to
Tokens, counted offlineView skill
Mixed2,220 tokens in use

systematic-debugging

322,961

Code Review And Quality · Developer Tools

A four-phase debugging process that finds the root cause before any fix is proposed.

Skill
21idle
2,220in use
5,201up to
Tokens, counted offlineView skill
Model-led2,330 tokens in use

test-driven-development

322,961

Code Review And Quality · Developer Tools

Enforces red-green-refactor: a failing test first, minimal code to pass it, and deletion of any code written before its test.

Skill
17idle
2,330in use
4,104up to
Tokens, counted offlineView skill
Model-led1,575 tokens in use

using-git-worktrees

322,961

Developer Tools · Devops And Releases

Creates an isolated git workspace for feature work, using your harness's native tool first and git worktree as a fallback.

Skill
35idle
1,575in use
1,575up to
Tokens, counted offlineView skill
Model-led706 tokens in use

using-superpowers

322,961

Agent Workflows

The bootstrap skill that makes your agent check for a relevant skill before any response, including clarifying questions.

Skill
29idle
706in use
3,783up to
Tokens, counted offlineView skill
Model-led815 tokens in use

verification-before-completion

322,961

Agent Workflows · Code Review And Quality · Developer Tools

Requires fresh command output as evidence before your agent claims work is done, fixed or passing.

Skill
43idle
815in use
815up to
Tokens, counted offlineView skill
Model-led3,655 tokens in use

writing-skills

322,961

Agent Workflows

Applies TDD to skill authoring: baseline an agent without the skill, write the skill, then close loopholes until it complies.

Skill
20idle
3,655in use
20,137up to
Tokens, counted offlineView skill
Mixed26,506 tokens in use

claude-api

198,136

Developer Tools

Anthropic's reference skill for building with the Claude API: current model IDs and pricing, SDK patterns in seven languages and cURL, Managed Agents, migrations and evals.

Skill
297idle
26,506in use
317,358up to
Tokens, counted offlineView skill
Model-led1,871 tokens in use

frontend-design

198,136

Design And Visual Art · Developer Tools · Frontend And UI Engineering

Design guidance that pushes Claude toward distinctive, intentional UI instead of templated defaults, from palette and type to layout and copy.

Skill
41idle
1,871in use
1,871up to
Tokens, counted offlineView skill
Mixed2,375 tokens in use

mcp-builder

198,136

Developer Tools

Anthropic's skill for building MCP servers: research the API, implement tools in TypeScript or Python, test with the Inspector, then measure the server with an LLM evaluation harness.

Skill
61idle
2,375in use
29,563up to
Tokens, counted offlineView skill
Mixed7,253 tokens in use

skill-creator

198,136

Agent Workflows · Developer Tools

Anthropic's skill for making skills: Claude drafts a SKILL.md, runs test prompts with and without it, shows the results in a review viewer and tunes the description that triggers it.

Skill
64idle
7,253in use
18,660up to
Tokens, counted offlineView skill
Script-led625 tokens in use

web-artifacts-builder

198,136

Developer Tools · Frontend And UI Engineering

Anthropic's skill for complex claude.ai artifacts: scaffold a React, TypeScript, Tailwind and shadcn/ui project with one script, then bundle it into a single HTML file with another.

Skill
64idle
625in use
625up to
Tokens, counted offlineView skill
Mixed833 tokens in use

webapp-testing

198,136

Code Review And Quality · Developer Tools

Anthropic's skill for testing local web apps: Claude writes native Python Playwright scripts, starts the dev servers with a helper, then inspects screenshots, the DOM and console logs.

Skill
35idle
833in use
833up to
Tokens, counted offlineView skill
Model-led2,987 tokens in use

browser-testing-with-devtools

119,431

Code Review And Quality

Give an agent live browser data through Chrome DevTools MCP: DOM, console, network and performance traces, with safety rules.

Skill
68idle
2,987in use
2,987up to
Tokens, counted offlineView skill
Model-led4,551 tokens in use

code-review-and-quality

119,431

Code Review And Quality

Review every change on five axes with severity labels, change sizing rules and a checklist before it merges.

Skill
83idle
4,551in use
4,551up to
Tokens, counted offlineView skill
Model-led2,963 tokens in use

code-simplification

119,431

Code Review And Quality

Simplify working code for clarity while keeping behavior exactly the same, one tested change at a time.

Skill
89idle
2,963in use
2,963up to
Tokens, counted offlineView skill
Model-led5,125 tokens in use

constraint-driven-development

119,431

Code Review And Quality

Write down a project's quality bar in CONSTRAINTS.md with default thresholds, wire checks to the dev loop and catch agents that weaken it.

Skill
176idle
5,125in use
8,081up to
Tokens, counted offlineView skill
Model-led3,206 tokens in use

context-engineering

119,431

Agent Workflows

Control what an AI coding agent sees with rules files, a context hierarchy, packing strategies and budget management.

Skill
44idle
3,206in use
3,206up to
Tokens, counted offlineView skill
Model-led2,364 tokens in use

debugging-and-error-recovery

119,431

Code Review And Quality

Debug in six steps: stop the line, reproduce, localize, reduce, fix the root cause and guard with a regression test.

Skill
131idle
2,364in use
2,364up to
Tokens, counted offlineView skill
Model-led3,549 tokens in use

doubt-driven-development

119,431

Code Review And Quality

Cross-examine every non-trivial decision with a fresh-context adversarial reviewer before it stands.

Skill
97idle
3,549in use
3,549up to
Tokens, counted offlineView skill
Model-led3,698 tokens in use

test-driven-development

119,431

Code Review And Quality

Write the failing test first, make it pass with minimal code, then refactor, and reproduce every bug with a test.

Skill
120idle
3,698in use
3,698up to
Tokens, counted offlineView skill

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers