update-claude-md
Skill1 starsChanged 2 months agoMITView on GitHub
Update the project's CLAUDE.md with conventions and patterns from recent branch changes. Args: [<path-to-CLAUDE.md>]
7 other projects use a version of this.
Adopted by
Most recently taken up by
- loonylabs-dev/claude-setuptheir own version, first seen Nov 1, 2026
- loonylabs/claude-setuptheir own version, first seen Oct 17, 2026
- gigamonkey/dot-claudetheir own version, first seen Oct 16, 2026
- mcorreiab/skillstheir own version, first seen Oct 9, 2026
- birdmanmandbir/skillstheir own version, first seen Oct 9, 2026
- 15yotsuka/claude-skillstheir own version, first seen May 22, 2026
Used with
Projects with it also use codebase-design, domain-modeling and 3 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
GoogleSkillcodebase-design
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
Also in 3 projects that use this
- GoogleSkill
domain-modeling
Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
Also in 3 projects that use this
- +3 more from google
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- megamott/vibe-skills★ 28same name
- birdmanmandbir/skills★ 1same name
- mcorreiab/skills★ 1same name
- 15yotsuka/claude-skills★ 0same name
- gigamonkey/dot-claude★ 0same name
- loonylabs-dev/claude-setup★ 0same name
- loonylabs/claude-setup★ 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 repository17 other files it gives its agents.
- check-drySkill
- check-testsSkill
- create-commit-messageSkill
- create-unit-testsSkill
- deslop-proseSkill
- deslopSkill
- fanout-reviewSkill
- fix-security-auditSkill
- framework-upgrade-guideSkill
- generate-adrSkill
- learnSkill
- optimizeSkill
- pr-descriptionSkill
- resolve-merge-conflictsSkill
- security-checkSkill
- ship-itSkill
- takeawaysSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
4
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 26
Locate CLAUDE.md: Use $ARGUMENTS as the path if provided.
- Distinctive: line 31
Read the current CLAUDE.md in full.
- Very specific: line 32
Run git diff main...HEAD (or master...HEAD) to get the branch diff.
- Distinctive: line 62
After showing the diff, ask: "Apply these changes?"
- Distinctive: line 69
If no CLAUDE.md is found, stop and report the paths checked.
- Distinctive: line 70
Do not apply changes until the user approves.
“Common” is measured: kept by at least 6 in 10 of the 5 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
<!-- Note: $ARGUMENTS is substituted by Claude commands only. In Copilot,
the user must include their argument inline in the prompt; the skill
body sees the literal text "$ARGUMENTS" unsubstituted. -->Arguments
[<path-to-CLAUDE.md>]
- Optional. Explicit path to the CLAUDE.md to update; defaults to searching the repo root and
.claude/. - Examples:
/update-claude-md,/update-claude-md packages/api/CLAUDE.md
Copilot CLI note:
$ARGUMENTSdoes not substitute in skills; include the argument inline in your prompt.
Update CLAUDE.md
Analyze recent branch changes and propose additions to the project CLAUDE.md.
Scope
- Locate CLAUDE.md: Use
$ARGUMENTSas the path if provided; otherwise search the repo root and.claude/for aCLAUDE.mdfile. - Diff source: Changes between this branch and
main/master.
Task
- Read the current CLAUDE.md in full.
- Run
git diff main...HEAD(ormaster...HEAD) to get the branch diff. - Identify additions worth documenting: only stable, reusable conventions:
- New CLI commands, scripts, or tooling patterns introduced
- New architectural patterns or module conventions
- Non-obvious configuration or environment constraints
- Public API changes (new endpoints, changed contracts, new env vars)
- New dependencies and why they were added
- Gotchas, workarounds, or constraints discovered during the work
- Filter out:
- One-off fixes unlikely to recur
- Implementation details (function bodies, variable names)
- Anything already documented in CLAUDE.md
- Obvious information derivable from reading the code
Output
Show proposed additions as a diff; do not edit any files yet:
### Update: <path-to-CLAUDE.md>
**Why:** <one-line reason>
```diff
+ <addition: one line per concept>
Group by section if adding to multiple parts of the file. If nothing new is worth documenting, say so and explain why.
After showing the diff, ask: **"Apply these changes?"**
## Rules
- **Never delete or rewrite existing content**: append or update only.
- **Match the existing CLAUDE.md's style** by example, not by paraphrase. Before drafting, scan the file for: heading depth (does it use `##` or `###` for new sections?), bullet style (`-` vs `*`), whether prose paragraphs or bullets dominate, whether code identifiers are backticked, whether examples use fenced code blocks or inline references. Mirror those choices in your additions.
- One line per concept: CLAUDE.md is part of the prompt; brevity matters. A "line" is one bullet or one short sentence. If you need 3+ lines to explain a concept, the concept is two concepts; split it.
- If no CLAUDE.md is found, stop and report the paths checked.
- Do not apply changes until the user approves.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.