analyze
CommandAnalyze user corrections and log them into the error notebook
Run a thorough scan of the entire memory ecosystem. Recommended weekly or after major changes.
Run a thorough scan of the entire memory ecosystem. Recommended weekly or after major changes.
Includes everything from `/check` (quick health check) plus the following:
=== Full Health Check ===
--- Basic (same as /check) ---
{Quick health check output}
--- Commands ---
- commands/: {N} commands
- [OK] diary.md -- reflection diary
- [WARNING] {file} -- overlaps with {other file}
- [BROKEN] {file} -- references non-existent path
--- Memory Files ---
- memory/: {N} files, {total} lines
- [OK] {file} ({N} lines) -- indexed in MEMORY.md
- [ORPHAN] {file} -- not in MEMORY.md index
- [FAT] {file} has {N} lines, suggest splitting
--- Cross-References ---
- [OK] MEMORY.md -> memory/ -> skills -> references/ chain intact
- [DUPLICATE] "{rule}" appears in both CLAUDE.md and MEMORY.md
- [CONFLICT] trigger "{phrase}" used by both {cmd A} and {skill B}
--- Environment ---
- settings.json: OK (hooks configured)
- hooks/: {N} scripts
- sessions/: OK
- skills/: OK
--- Git Repos ---
- [CLEAN] {repo} -- synced with remote
- [DIRTY] {repo} -- {N} uncommitted files
- [BEHIND] {repo} -- {N} commits behind remote
Suggestions:
1. ...
2. ...Claude Code 的記憶系統 | A memory system built with hooks + markdown. Zero dependencies.
Analyze user corrections and log them into the error notebook
Pause the SessionEnd auto-commit hook when refactoring core engine files.
Help decide when to use `/compact` based on the current conversation state.
Review the error notebook — flip through past corrections before working
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.