MrCipherSmithMrCipherSmith/goodai-base/skills/claude-md-management/SKILL.md

claude-md-management

Skill0 starsChanged 5 months agoMITView on GitHub

Use when saving session learnings, coding patterns, conventions, or commands discovered during work into CLAUDE.md files.

In this repository76 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- autodoc-analystSkill
- autodoc-architectSkill
- autodoc-assemblerSkill
- autodoc-orchestratorSkill
- autodoc-scannerSkill
- autodoc-writerSkill
- brainstormSkill
- brd-creatorSkill
- caveman-modeSkill
- changelogSkill
- code-ai-reviewSkill
- code-boss-reviewSkill
- code-mobx-store-reviewSkill
- code-reviewSkill
- code-style-reviewSkill
- code-verifierSkill
- commitSkill
- constraint-driven-developmentSkill
- context-collectorSkill
- db-migrateSkill
- dependency-updateSkill
- deploySkill
- doubt-driven-developmentSkill
- feature-analyzerSkill
- feature-devSkill
- fsd-creatorSkill
- gproject-consistency-checkerSkill
- gproject-discoverySkill
- gproject-orchestratorSkill
- gproject-patterns-researcherSkill
- gproject-plannerSkill
- gproject-problem-definerSkill
- gproject-spec-writerSkill
- gproject-stack-advisorSkill
- hookifySkill
- iagoSkill
- interviewerSkill
- interviewSkill
- issue-analyzerSkill
- job-documenterSkill
- job-orchestratorSkill
- perf-checkSkill
- plan-gatekeeperSkill
- prd-creatorSkill
- pr-issue-documenterSkill
- pr-review-commentsSkill
- prSkill
- pushSkill
- review-architectureSkill
- review-backendSkill
- review-clean-codeSkill
- review-core-boundariesSkill
- review-flow-graphSkill
- review-frontend-conventionsSkill
- review-frontendSkill
- review-greptileSkill
- review-highloadSkill
- review-logicSkill
- The first 60 shown.

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 9 are distinctive, and 3 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Keep organized with clear ## headers
line 68
Distinctive:
Avoid duplication — merge with existing
line 69
Distinctive:
Remove outdated entries if contradicted
line 70
Very specific:
Use ## headers for sections
line 74
Very specific:
Use - bullet lists for items
line 75
Distinctive:
Keep entries concise (1 line each)
line 76
Distinctive:
No frontmatter in CLAUDE.md files
line 78
Distinctive:
ALWAYS show proposed changes before applying
line 83
Distinctive:
NEVER remove existing entries without explanation
line 84
Distinctive:
NEVER add entries that duplicate what's already there
line 85
Distinctive:
Keep CLAUDE.md files under 100 lines
line 86
Distinctive:
Prefer project-level for project-specific things
line 87

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

CLAUDE.md Management

Capture session insights and persist them into the appropriate CLAUDE.md file.

Arguments

/revise-claude-md — analyze session and propose updates
/revise-claude-md "specific thing" — add a specific entry
/revise-claude-md --auto — apply without asking (for pipelines)

Workflow

Step 1: Collect Session Insights

Analyze the current conversation for:

Coding patterns discovered or established
Project conventions learned (naming, structure, testing)
Build/deploy commands that work
Gotchas and pitfalls encountered
Architecture decisions made
Tool configurations set up

Step 2: Read Current CLAUDE.md Files

Project-level: <project-root>/CLAUDE.md
User-level: ~/.claude/CLAUDE.md
Project-specific user-level: ~/.claude/projects/<project-path>/CLAUDE.md

Step 3: Classify Each Insight

Type	Target
Project conventions, build commands	`<project>/CLAUDE.md`
Global preferences, workflow rules	`~/.claude/CLAUDE.md`
Project-specific personal notes	`~/.claude/projects/<path>/CLAUDE.md`

Step 4: Propose Changes

Present diff preview:

📝 Proposed CLAUDE.md updates:

[project] CLAUDE.md:
+ ## Build Commands
+ - `npm run dev` — start dev server on port 3000

[global] ~/.claude/CLAUDE.md:
+ ## Preferences
+ - Always use conventional commits

Step 5: Apply (after user approval)

Edit existing sections or append new sections
Keep organized with clear ## headers
Avoid duplication — merge with existing
Remove outdated entries if contradicted

Formatting Rules for CLAUDE.md

Use ## headers for sections
Use - bullet lists for items
Keep entries concise (1 line each)
Group by: Commands, Conventions, Architecture, Gotchas
No frontmatter in CLAUDE.md files
CLAUDE.md should be practical — commands you run, not documentation

Rules

ALWAYS show proposed changes before applying
NEVER remove existing entries without explanation
NEVER add entries that duplicate what's already there
Keep CLAUDE.md files under 100 lines
Prefer project-level for project-specific things

Download now (ZIP)

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

What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free