ab-cleanup
Skill193 starsChanged 58 days agoMITView on GitHub
Clean up a repo already using AB Method - compact the domain and architecture docs to their budgets, split pattern docs by topic, remove disposable task leftovers, and migrate the structure index to 4.0. Use when docs have grown too large, after upgrading AB Method, or when the user asks to clean up.
In this repository36 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ab-analyze-backendSkill
- ab-analyze-frontendSkill
- ab-analyze-projectSkill
- ab-create-goalSkill
- ab-create-roadmapSkill
- ab-create-task-from-handoffSkill
- ab-create-taskSkill
- ab-extend-goalSkill
- ab-extend-taskSkill
- ab-mastermindSkill
- ab-resume-taskSkill
- ab-start-roadmapSkill
- ab-start-taskSkill
- ab-update-architectureSkill
- adopt-or-buildSkill
- change-mapSkill
- codebase-designSkill
- critique-planSkill
- domain-modelSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- improve-codebase-architectureSkill
- prototype-uiSkill
- prSkill
- reconcile-roadmapSkill
- request-refactor-planSkill
- review-implementationSkill
- review-prSkill
- sync-architectureSkill
- tddSkill
- to-issuesSkill
- to-prdSkill
- ubiquitous-languageSkill
- write-a-skillSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Follow the workflow defined in .ab-method/core/ab-cleanup.md exactly — it contains the full process, output format, and rules.
- Very specific: line 10
Before doing anything, check .ab-method/structure/index.yaml.
- Very specific: line 12
Locating
.ab-method/: Every .ab-method/... path — here and inside the workflow files — is resolved in this order: - Very specific: line 14
The project root (the current working directory) first: If <project>/.ab-method/...
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
This skill runs the AB Method ab-cleanup workflow.
Follow the workflow defined in .ab-method/core/ab-cleanup.md exactly — it contains the full process, output format, and rules.
Before doing anything, check .ab-method/structure/index.yaml. It defines where this workflow reads from and writes to. Paths are user-configurable; never hardcode them.
Locating .ab-method/. Every .ab-method/... path — here and inside the workflow files — is resolved in this order:
- The project root (the current working directory) first. If
<project>/.ab-method/...exists, use it. A project's own.ab-method/structure/index.yamlis how it customises its paths, so it always wins — check for it even when the bundled copy is right there. - Only if the project has no such file (AB Method installed as a plugin rather than with
npx ab-method), read the bundled copy:../../../.ab-method/relative to thisSKILL.md.
The bundled copy is read-only reference material. Every path the index or a workflow names (docs/..., CONTEXT.md, UBIQUITOUS_LANGUAGE.md, ...) is relative to the project root — never to the folder the bundled files live in. Never write inside that folder.
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.