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.
Ask Matt
329,112Agent Workflows
A router over Matt Pocock's engineering skills that tells you which skill or flow fits your situation, from idea to shipped code.
chief-of-staff
329,112Agent Workflows
Pursue a long-running goal in one session by coordinating subagents and keeping a dated wiki of what was learned.
claude-handoff
329,112Agent Workflows
Hand the current conversation to a fresh named background Claude agent that picks up the work immediately.
Handoff
329,112Agent Workflows
Compact the current conversation into a handoff document so a fresh agent can continue the work, with suggested skills and secrets redacted.
Implement
329,112Agent Workflows · Developer Tools
Builds the work in a spec or ticket by driving TDD at pre-agreed seams, then runs code-review and commits to the current branch.
Implement Spec
329,112Agent Workflows · Developer Tools
Implements a whole spec on one integration branch by running implementer subagents in parallel across the ready tickets.
loop-me
329,112Agent Workflows
Get grilled about the recurring loops in your work and end up with workflow specs ready to delegate.
Research
329,112Agent Workflows · Research And Academic Writing
Delegates reading to a background agent that investigates primary sources and saves cited findings as a Markdown file in your repo.
retro
329,112Agent Workflows
Run a retrospective on a coding agent session and get ranked suggestions for improving its environment.
Software Factory
329,112Agent Workflows
A shared vocabulary for designing a software factory: the agent tasks it runs and the services it plugs into, with surveys for picking each product.
writing-for-agents
329,112Agent Workflows · Writing And Communication
A reference for writing any document an agent reads, from skills to AGENTS.md and CLAUDE.md, built on context pointers, the information hierarchy and pruning.
dispatching-parallel-agents
322,961Agent Workflows · Developer Tools
Splits two or more independent problems across focused subagents, each with its own scope, constraints and expected output.
subagent-driven-development
322,961Agent 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.
using-superpowers
322,961Agent Workflows
The bootstrap skill that makes your agent check for a relevant skill before any response, including clarifying questions.
verification-before-completion
322,961Agent Workflows · Code Review And Quality · Developer Tools
Requires fresh command output as evidence before your agent claims work is done, fixed or passing.
skill-creator
198,136Agent 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.
using-agent-skills
119,431Agent Workflows
Map incoming work to the right agent skill and follow six operating behaviors that apply across all of them.
Neat Freak
22,434Agent Workflows
End-of-session cleanup that aligns project docs, CLAUDE.md or AGENTS.md rule files and agent memory with what the code and running services do today.
SkillOpt Sleep for Claude Code
19,174Agent Workflows
Gives Claude Code a sleep cycle: it reads past sessions, replays recurring tasks and stages CLAUDE.md and SKILL.md edits that beat a held-out score.
SkillOpt Sleep for Codex
19,174Agent Workflows
Gives Codex a sleep cycle: it reviews past sessions, replays recurring tasks and stages skill and CLAUDE.md edits that pass a held-out score gate.
SkillOpt Sleep for Cursor
19,174Agent Workflows
Reviews recent Cursor sessions, replays recurring tasks and stages edits to a project Cursor skill that pass a held-out score gate.
prompt-engineer
12,473Agent Workflows
Designs, tests and refines LLM prompts with few-shot and chain-of-thought patterns, structured output schemas, system prompts and eval suites.
dbs-install-skill
11,518Agent Workflows
Links one skill, or a folder of skills, into every agent installed on the machine with a single script, and cleans up duplicate entries.
goal-prompt
8,320Agent Workflows
Drafts one-line /goal commands for Claude Code and Codex that have a checkable end state, a stated check, invariants and a stop bound.