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.

386 skills5 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 226 of 386 skillsCredentials Git Network Writes Files Shell 90 and up Clear all
Model-led10 tokens in use

Grill Me

328,791

A relentless interview that sharpens a plan or design, started with one command and run by the grilling skill.

Skill
14idle
10in use
10up to
Tokens, counted offlineView skill
Model-led403 tokens in use

Grilling

328,791

Interview the user in numbered rounds, each question with a recommended answer, until every branch of the design tree is settled.

Skill
38idle
403in use
403up to
Tokens, counted offlineView skill
Model-led152 tokens in use

Handoff

328,791

Compact the current conversation into a handoff document so a fresh agent can continue the work, with suggested skills and secrets redacted.

Skill
19idle
152in use
152up to
Tokens, counted offlineView skill
Model-led1,288 tokens in use

Software Factory

328,791

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.

Skill
23idle
1,288in use
9,720up to
Tokens, counted offlineView skill
Model-led1,964 tokens in use

Teach

328,791

Turn a directory into a multi-session learning workspace with a mission, cited resources, learning records, HTML lessons and reference sheets.

Skill
17idle
1,964in use
3,345up to
Tokens, counted offlineView skill
Model-led604 tokens in use

to-questionnaire

328,791

Turns a decision you cannot answer alone into a Markdown questionnaire for the one person who can, after a short interview about who it goes to and what you need back.

Skill
22idle
604in use
604up to
Tokens, counted offlineView skill
Model-led70 tokens in use

wait-what

328,791

A slash command for the moment a message does not land: the agent re-pitches it with the missing context, in Simplified Technical English, using your glossary terms.

Skill
18idle
70in use
70up to
Tokens, counted offlineView skill
Model-led1,050 tokens in use

Writing Beats

328,791

Writing 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.

Skill
27idle
1,050in use
1,050up to
Tokens, counted offlineView skill
Model-led2,313 tokens in use

writing-for-agents

328,791

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.

Skill
28idle
2,313in use
2,866up to
Tokens, counted offlineView skill
Model-led761 tokens in use

Writing Fragments

328,791

Writing And Communication

Mine raw writing fragments through a relentless interview, saved to one Markdown file with no outline or structure imposed yet.

Skill
17idle
761in use
761up to
Tokens, counted offlineView skill
Model-led1,340 tokens in use

Writing Shape

328,791

Writing 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.

Skill
19idle
1,340in use
1,340up to
Tokens, counted offlineView skill
Model-led1,013 tokens in use

chief-of-staff

328,764

Pursue a long-running goal in one session by coordinating subagents and keeping a dated wiki of what was learned.

Skill
24idle
1,013in use
1,013up to
Tokens, counted offlineView skill
Model-led518 tokens in use

loop-me

328,764

Get grilled about the recurring loops in your work and end up with workflow specs ready to delegate.

Skill
20idle
518in use
518up to
Tokens, counted offlineView skill
Model-led926 tokens in use

retro

328,764

Run a retrospective on a coding agent session and get ranked suggestions for improving its environment.

Skill
12idle
926in use
926up to
Tokens, counted offlineView skill
Model-led737 tokens in use

tdd

328,764

Test-first development for coding agents: agree the seams, then one failing test and one minimal fix per slice.

Skill
33idle
737in use
1,571up to
Tokens, counted offlineView skill
Model-led599 tokens in use

to-spec

328,764

Synthesize the current conversation into a structured spec and publish it to your issue tracker.

Skill
31idle
599in use
599up to
Tokens, counted offlineView skill
Model-led1,201 tokens in use

to-tickets

328,764

Break a plan or spec into tracer-bullet tickets with declared blocking edges and publish them to your tracker.

Skill
54idle
1,201in use
1,201up to
Tokens, counted offlineView skill
Model-led1,521 tokens in use

triage

328,764

Move issues and external PRs through a state machine of triage roles and write agent-ready briefs.

Skill
34idle
1,521in use
4,390up to
Tokens, counted offlineView skill
Model-led2,806 tokens in use

wayfinder

328,764

Plan work too big for one session as a map of decision tickets on your tracker and resolve them one at a time.

Skill
46idle
2,806in use
2,806up to
Tokens, counted offlineView skill
Model-led2,975 tokens in use

Ask Matt

328,754

A router over Matt Pocock's engineering skills that tells you which skill or flow fits your situation, from idea to shipped code.

Skill
22idle
2,975in use
3,931up to
Tokens, counted offlineView skill
Model-led1,295 tokens in use

Codebase Design

328,754

Developer Tools

Shared vocabulary for deep modules: a lot of behaviour behind a small interface, placed at a clean seam and testable through that interface.

Skill
57idle
1,295in use
2,451up to
Tokens, counted offlineView skill
Model-led735 tokens in use

Domain Modeling

328,754

Builds and sharpens a project's domain model by challenging terms, stress-testing scenarios and updating GLOSSARY.md and ADRs inline.

Skill
37idle
735in use
1,907up to
Tokens, counted offlineView skill
Model-led18 tokens in use

Grill With Docs

328,754

A user-invoked skill that runs the grilling interview and the domain-modeling discipline together, leaving a glossary and ADRs behind.

Skill
31idle
18in use
18up to
Tokens, counted offlineView skill
Model-led106 tokens in use

Implement

328,754

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.

Skill
16idle
106in use
106up 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