add-to-claude
Skill0 starsChanged 4 months agoMITView on GitHub
Validate whether something belongs in CLAUDE.md before adding it
In this repository21 other files it gives its agents.
- add-to-rulesSkill
- audit-claudeSkill
- audit-rulesSkill
- autopilotSkill
- better-planSkill
- design-autoSkill
- designSkill
- execute-autoSkill
- executeSkill
- facts-extSkill
- factsSkill
- questionsSkill
- research-autoSkill
- researchSkill
- review-autoSkill
- structure-autoSkill
- structureSkill
- wiki-captureSkill
- wiki-ingestSkill
- wiki-lintSkill
- wiki-querySkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- Distinctive: line 6
Before adding anything to CLAUDE.md, apply this test:
- Distinctive: line 10
Would I get it right from training?: If the standard/common approach matches what this project does, it does NOT belong in CLAUDE.md — I'll …
- Very specific: line 14
Is it universal or scoped?: If it only applies to one area (e.g.
- Very specific: line 16
Is it already covered?: Check existing rules in .claude/rules/ and existing CLAUDE.md content.
- Distinctive: line 20
Conditional rules: If a rule only matters in a specific context (e.g.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Before adding anything to CLAUDE.md, apply this test:
- Is it obvious from the code? Grep the codebase. If the pattern is visible in existing files (imports, naming, structure), it does NOT belong in CLAUDE.md — I can derive it by reading code.
- Would I get it right from training? If the standard/common approach matches what this project does, it does NOT belong in CLAUDE.md — I'll default to the right thing anyway.
- Does it cause a compile error or visible bug if wrong? If yes → add to CLAUDE.md under "Will Not Compile Without Knowing". If it's a subtler issue (code smell, convention drift) → add under "Will Not Catch in Review". If neither → it belongs in a path-scoped rule or nowhere.
- Is it universal or scoped? If it only applies to one area (e.g. one adapter, the test harness, or a single subsystem) → it belongs in a path-scoped rule in
.claude/rules/, not CLAUDE.md. - Is it already covered? Check existing rules in
.claude/rules/and existing CLAUDE.md content. Do not duplicate.
If it passes all tests, add it as a single concise line to the appropriate section.
Conditional rules: If a rule only matters in a specific context (e.g. when editing a certain module, when a flag is set, when building for a target), wrap it in:
<important-if {condition}>{rule}</important-if>This tells future reads to only apply the rule when the condition is met.
If it fails any test, suggest the right home:
- Scoped convention →
.claude/rules/{area}.mdwithpaths:frontmatter - Behavioral preference → memory (feedback type)
- Repeatable process →
.claude/skills/ - Stage-specific context →
.claude/agents/
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.

