setup-playbook
Skill0 starsChanged 5 days agoMITView on GitHub
Configure this repo for the playbook: run setup-matt-pocock-skills, then wire in the playbook's extensions to those skills. Run once, and again after installing a new extension.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- mojopoly/three-loopstheir own version, first seen Oct 20, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- mojopoly/three-loops★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository35 other files it gives its agents.
- ask-mattSkill
- codebase-designSkill
- code-reviewSkill
- create-verification-skillSkill
- cutSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- grillingSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- implementSkill
- implement-specSkill
- improve-codebase-architectureSkill
- lean-product-canvasSkill
- maintain-verification-skillSkill
- napkin-mathSkill
- property-testingSkill
- prototypeSkill
- pr-review-canvasSkill
- prSkill
- researchSkill
- retroSkill
- setup-matt-pocock-skillsSkill
- tddSkill
- teachSkill
- to-prdSkill
- to-questionnaireSkill
- to-specSkill
- to-ticketsSkill
- triageSkill
- wait-whatSkill
- wayfinderSkill
- wizardSkill
- writing-for-agentsSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
If the Skill tool refuses the call, stop and tell the user to run /setup-matt-pocock-skills, then /setup-playbook again.
- Distinctive: line 23
Check which extensions are installed: a skill folder alongside this one, or the name in your available skills.
- Very specific: line 50
When Verification is wired in and no verify-* skill exists: if the app runs, tell the user to run /create-verification-skill in a new …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Setup Playbook
The playbook extends the vendored engineering skills without editing them: each extension is a skill of its own, and a pointer in AGENTS.md tells the agent when to load it. This skill writes those pointers.
1. Base setup
Call the Skill tool with "setup-matt-pocock-skills" and follow it through its "Done" step; when it asks which instructions file to create, recommend AGENTS.md. Done when its ## Agent skills block and docs/agents/*.md are written. When ## Agent skills already exists, ask whether to re-run it (recommended: no) and skip to step 2 on no.
If the Skill tool refuses the call, stop and tell the user to run /setup-matt-pocock-skills, then /setup-playbook again.
2. Instructions file
The playbook keeps one instructions file: AGENTS.md, which the playbook's other skills also write to. Claude Code reads it natively when no CLAUDE.md exists. When CLAUDE.md also exists, Claude Code reads only CLAUDE.md: tell the user, and offer to add an @AGENTS.md line to it.
3. Extensions
Check which extensions are installed: a skill folder alongside this one, or the name in your available skills.
| Extension | Sub-block | Doc file | Seed |
property-testing | ### Testing | docs/agents/testing.md | testing.md |
create-verification-skill | ### Verification | docs/agents/verification.md | verification.md |
Draft the ## Playbook extensions block for AGENTS.md, including a sub-block only for an installed extension:
## Playbook extensions
### Testing
Property-based testing extends `tdd` and `diagnosing-bugs`. See `docs/agents/testing.md`.
### Verification
The `verify-<app>` skill proves changes in the running app for `implement`, `implement-spec`, `pr`, `triage`, `diagnosing-bugs` and `retro`. See `docs/agents/verification.md`.Draft each installed extension's doc file from its seed. Show the drafts and let the user edit before writing. Then write: update the ## Playbook extensions block and each sub-block in place when they exist, create them otherwise, and leave ## Agent skills and every other section as they are. Done when every installed extension has its sub-block and doc file. When none is installed, skip this step and say so in step 4.
4. Done
Name each extension wired in, the skill it extends, and the doc file holding its rules. Those files can be edited directly later; re-run this skill after installing a new extension.
When Verification is wired in and no verify-* skill exists: if the app runs, tell the user to run /create-verification-skill in a new session; otherwise, tell them it comes once the walking skeleton runs.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

