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.
How to read a skill
What it costs to keep
Idle in context, in use when it runs, and up to with its linked files.
Scripts or instructions
Script-led, mixed or model-led: how much the model has to work out itself.
What it can reach
Shell, network, file writes, git and credentials, declared or detected.
Quality, security, repo health
Out of 100, each with what it is made of. Turn a card over to see them.
Working Effectively with Legacy Code
3,324Code Review And Quality
Change hard-to-test code safely with rules inspired by Michael Feathers: characterization tests, seams, sprout and wrap methods, dependency breaking.
Playwright Skill
3,307Code Review And Quality
Lets a coding agent write and run its own Playwright scripts to test sites, check layouts, fill forms and capture screenshots.
Agent Instructions
687Agent Workflows
Write and maintain the AGENTS.md or CLAUDE.md every session reads, so each rule is met at the moment it applies.
Claude Agents
687Agent 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.
Code Review
687Code 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.
Codex Agents
687Agent 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.
Delegation
687Agent Workflows
Brief the goal, keep decisions with you, run parallel delegates safely and verify the handoff before you trust a subagent's report.
derive-tests
687Code 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.
Flight Deck
687Agent 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.
Gemini Agents
687Agent 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.
Grok Agents
687Agent Workflows
Drive the headless Grok CLI from another agent as a peer, a builder or a fresh reviewer from a different model family.
Guardrail Hooks
687Agent 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.
Handover
687Agent 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.
independent-review
687Code 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.
intended-vs-implemented
687Code 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.
Retro
687Agent 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.
start-here
687Agent 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.
test-harness
687Code 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.