Help us improve
Share bugs, ideas, or general feedback.
From authoring
Provides best practices for creating, updating, and auditing CLAUDE.md files including constraints, commands, architecture overviews, and bloat reduction for projects.
How this skill is triggered — by the user, by Claude, or both
Slash command
/authoring:claude-md**/CLAUDE.mdThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
CLAUDE.md is a curated set of **guardrails and pointers**, not a comprehensive manual. Every line is scarce real estate. Focus on constraints and gotchas — things Claude would get wrong without guidance.
Share bugs, ideas, or general feedback.
CLAUDE.md is a curated set of guardrails and pointers, not a comprehensive manual. Every line is scarce real estate. Focus on constraints and gotchas — things Claude would get wrong without guidance.
Prioritize in order:
Root (~100-200 lines): Project-wide constraints, build/test commands, architecture. Loaded every session.
Subdirectory (<50 lines): Only create when:
Don't repeat parent CLAUDE.md content. Don't explain what's obvious from the directory name.
paths frontmatterFor each line, ask: "Would Claude's behavior change if I removed this?" If no, cut it.
Signs of bloat:
300 lines
When adding content, always propose pruning alongside additions. The file should get tighter over time, not longer.
npx claudepluginhub crouton-labs/crouton-kit --plugin authoringCreates and refactors CLAUDE.md files following best practices for size, structure, and content organization. Includes memory hierarchy, 3-tier documentation system, and conditional rules.
CLAUDE.md instruction quality: writing effective project instructions, diagnosing why Claude ignores rules, routing content to the right layer, and systematic improvement. Invoke whenever task involves any interaction with CLAUDE.md files — writing, reviewing, auditing, improving, or debugging instruction compliance.
Audits and restructures CLAUDE.md files to reduce token bloat and improve Claude compliance. Targets 2,500–3,500 tokens with a hard 5,000 limit.