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.
Grill Me
328,791A relentless interview that sharpens a plan or design, started with one command and run by the grilling skill.
Grilling
328,791Interview the user in numbered rounds, each question with a recommended answer, until every branch of the design tree is settled.
Software Factory
328,791A 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 Beats
328,791Writing And Communication
Assemble a pile of raw notes into an article one beat at a time, choosing each next beat from options while every concept is grounded first.
Writing Fragments
328,791Writing And Communication
Mine raw writing fragments through a relentless interview, saved to one Markdown file with no outline or structure imposed yet.
Writing Shape
328,791Writing And Communication
Read a pile of raw notes and shape it into an article paragraph by paragraph, choosing the opening, grounding each concept and arguing over format.
chief-of-staff
328,764Pursue a long-running goal in one session by coordinating subagents and keeping a dated wiki of what was learned.
loop-me
328,764Get grilled about the recurring loops in your work and end up with workflow specs ready to delegate.
retro
328,764Run a retrospective on a coding agent session and get ranked suggestions for improving its environment.
tdd
328,764Test-first development for coding agents: agree the seams, then one failing test and one minimal fix per slice.
to-spec
328,764Synthesize the current conversation into a structured spec and publish it to your issue tracker.
to-tickets
328,764Break a plan or spec into tracer-bullet tickets with declared blocking edges and publish them to your tracker.
triage
328,764Move issues and external PRs through a state machine of triage roles and write agent-ready briefs.
wayfinder
328,764Plan work too big for one session as a map of decision tickets on your tracker and resolve them one at a time.
Ask Matt
328,754A router over Matt Pocock's engineering skills that tells you which skill or flow fits your situation, from idea to shipped code.
Codebase Design
328,754Developer Tools
Shared vocabulary for deep modules: a lot of behaviour behind a small interface, placed at a clean seam and testable through that interface.
Domain Modeling
328,754Builds and sharpens a project's domain model by challenging terms, stress-testing scenarios and updating GLOSSARY.md and ADRs inline.
Grill With Docs
328,754A user-invoked skill that runs the grilling interview and the domain-modeling discipline together, leaving a glossary and ADRs behind.
Implement
328,754Developer 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
328,754Developer Tools
Implements a whole spec on one integration branch by running implementer subagents in parallel across the ready tickets.
PR
328,754Developer Tools
A pull request body template with a summary as the smallest useful visual, before and after evidence, and a merge-danger call.
Research
328,754Delegates reading to a background agent that investigates primary sources and saves cited findings as a Markdown file in your repo.
academy-guide
197,764AI Fluency
When someone asks how to use Claude or a Claude product, Claude answers first, then points to one or two strongly matching Claude Academy courses, tutorials or use cases.
mcp-builder
197,764Developer 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.