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 skillsDeveloper Tools Agent Workflows Code Review And Quality Game Development Clear all
Model-led117 tokens in use

Working Effectively with Legacy Code

3,324

Code Review And Quality

Change hard-to-test code safely with rules inspired by Michael Feathers: characterization tests, seams, sprout and wrap methods, dependency breaking.

Skill
37idle
117in use
3,891up to
Tokens, counted offlineView skill
Mixed1,683 tokens in use

Playwright Skill

3,307

Code Review And Quality

Lets a coding agent write and run its own Playwright scripts to test sites, check layouts, fill forms and capture screenshots.

Skill
69idle
1,683in use
5,639up to
Tokens, counted offlineView skill
Mixed4,346 tokens in use

Agent Instructions

687

Agent Workflows

Write and maintain the AGENTS.md or CLAUDE.md every session reads, so each rule is met at the moment it applies.

Skill
42idle
4,346in use
17,221up to
Tokens, counted offlineView skill
Mixed2,660 tokens in use

Claude Agents

687

Agent Workflows

Drive headless Claude Code (claude -p) from another agent as a peer, a builder or a fresh reviewer, through a wrapper that keeps sessions and modes.

Skill
40idle
2,660in use
5,351up to
Tokens, counted offlineView skill
Model-led2,703 tokens in use

Code Review

687

Code Review And Quality

Review code for correctness first, with performance and security as options, and report only defects that survived a check of the strongest counterargument.

Skill
36idle
2,703in use
6,240up to
Tokens, counted offlineView skill
Mixed4,167 tokens in use

Codex Agents

687

Agent Workflows

Use the Codex CLI as a peer, a builder or a fresh reviewer, through a wrapper that remembers the session, model and sandbox across turns.

Skill
43idle
4,167in use
6,939up to
Tokens, counted offlineView skill
Model-led3,983 tokens in use

Delegation

687

Agent Workflows

Brief the goal, keep decisions with you, run parallel delegates safely and verify the handoff before you trust a subagent's report.

Skill
37idle
3,983in use
7,387up to
Tokens, counted offlineView skill
Model-led2,736 tokens in use

derive-tests

687

Code Review And Quality

Turns documented intent into a test coverage map: which rules have tests today, which are proposed, and which gaps are left, ranked by what crossing them exposes.

Skill
32idle
2,736in use
2,914up to
Tokens, counted offlineView skill
Model-led2,382 tokens in use

Flight Deck

687

Agent Workflows

A status board for long agent work: STATUS.md, LOG.md and an owner page that survive compaction and show only what needs you.

Skill
42idle
2,382in use
15,590up to
Tokens, counted offlineView skill
Script-led5,255 tokens in use

Gemini Agents

687

Agent Workflows

Drive Google's Antigravity CLI as a requested peer, builder or second reviewer, only after the user has agreed and heard the support status.

Skill
44idle
5,255in use
7,856up to
Tokens, counted offlineView skill
Model-led2,751 tokens in use

Grok Agents

687

Agent Workflows

Drive the headless Grok CLI from another agent as a peer, a builder or a fresh reviewer from a different model family.

Skill
38idle
2,751in use
2,964up to
Tokens, counted offlineView skill
Mixed3,455 tokens in use

Guardrail Hooks

687

Agent Workflows

Turn a rule an agent keeps breaking into a permission rule, hook or script, with templates for a one-way-door guard and a commit-identity guard.

Skill
43idle
3,455in use
7,278up to
Tokens, counted offlineView skill
Model-led761 tokens in use

Handover

687

Agent Workflows

Write the one note a fresh agent session starts from, after checking the disk, the running jobs and git against what the session remembers.

Skill
73idle
761in use
824up to
Tokens, counted offlineView skill
Mixed6,459 tokens in use

independent-review

687

Code Review And Quality

A release gate built on a fresh, read-only reviewer that never saw the build: git-computed subjects, a five-part brief, mandatory triage and a clear stopping rule.

Skill
39idle
6,459in use
12,239up to
Tokens, counted offlineView skill
Model-led798 tokens in use

intended-vs-implemented

687

Code Review And Quality

A review method that compares AI-built code with its recorded intent to find unenforced permissions, public cron endpoints and private data leaking onto public surfaces.

Skill
37idle
798in use
798up to
Tokens, counted offlineView skill
Model-led1,268 tokens in use

Retro

687

Agent Workflows

At the end of a session, list the friction, find its cause and build a checked fix into your agent setup, or conclude that no change is warranted.

Skill
69idle
1,268in use
1,417up to
Tokens, counted offlineView skill
Model-led3,606 tokens in use

start-here

687

Agent Workflows

Say what you have (an idea, a change, a bug or a release) and get the product's next step and the skill that does it.

Skill
69idle
3,606in use
3,973up to
Tokens, counted offlineView skill
Model-led4,094 tokens in use

test-harness

687

Code Review And Quality

Rules for tests where a green gate means something: what each harness fakes, how to run and report the gate, regression tests for fixes, and lessons from real bugs.

Skill
43idle
4,094in use
21,069up 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