documenting
Skill0 starsChanged 3 months agoMITView on GitHub
Use after any user-visible change or architectural decision — update user docs, dev docs, CHANGELOG and the indexes in the same session as the change.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- fynnhaupt/skillstheir own version, first seen Nov 1, 2026
- jukanntenn/harness-deepseek-harnesstheir own version, first seen Oct 7, 2026
- paulostation/claude-skillstheir own version, first seen Mar 27, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- jukanntenn/harness-deepseek-harness★ 2same name
- paulostation/claude-skills★ 2same name
- fynnhaupt/skills★ 1same 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 repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- create-ticketSkill
- creating-skillsSkill
- explaining-complexitySkill
- finding-knowledgeSkill
- git-disciplineSkill
- journalingSkill
- start-boardSkill
- werkbank-work-ticketSkill
- work-ticketsSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
0
Distinctive
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 38
Every new or renamed doc under docs/user/ or docs/dev/ gets its line in docs/INDEX.md (same commit), format: - YYYY-MM-DD — title — tags — …
- Very specific: line 43
When CLAUDE.md or a doc grows past comfortable reading, extract the detail into project skills — <tool>-reference (what things are: …
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Documenting
Docs updated "later" are docs never updated. Same session, same commit as the change.
Where what goes
docs/user/— the user's language. Task-oriented ("how do I run the monthly report"), zero jargon. If the user can't follow it, it isn't done.docs/dev/— English. Architecture, setup, decision records. A decision record states what was decided, why, what was rejected, and links the journal entry of the session that decided it (relative markdown link).CHANGELOG.md— only if this project keeps one (an adopted project may deliberately not; its CLAUDE.md says so). The user's language, https://keepachangelog.com style, newest first. What changed FOR THE USER. Internal refactors, test-only and doc-only changes are omitted.
Frontmatter — every file in docs/user/ and docs/dev/
---
title: <one line>
date: YYYY-MM-DD
tags: [tag] # from docs/TAGS.md only; new tag = add it there, same commit
summary: <one sentence>
---One schema everywhere means one grep pattern searches everything.
(Journal entries under docs/journal/ follow the journaling skill instead: same schema plus outcome, indexed in docs/journal/INDEX.md.)
Indexes — not optional
Every new or renamed doc under docs/user/ or docs/dev/ gets its line in docs/INDEX.md (same commit), format: - YYYY-MM-DD — [title](path) — tags — summary. An unindexed
doc is a bug.
When docs outgrow themselves
When CLAUDE.md or a doc grows past comfortable reading, extract the detail into project
skills — <tool>-reference (what things are: formats, locations, constants) and
<tool>-how-to (how recurring tasks are done) — each marked "extracted from X — keep in
sync". See creating-skills.
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.

