memory-file-maintenance

Memory-File Maintenance

A personal AI memory file (MEMORY.md, CLAUDE.md, custom instructions) is only as good as it is current — over time it bloats with stale rules, contradicts itself, and drifts from who you actually are now. This tends it: reviews what's there, prunes the dead weight, sharpens the vague, adds the new patterns worth keeping, and sets a light maintenance habit — so your AI keeps understanding the real you. It also re-checks the privacy line on what should never be in there.

What This Skill Produces

• A health review — what in the current file is stale, contradictory, bloated, redundant, or vague — and what important context is missing
• Prune & sharpen edits — removing dead rules and tightening vague ones into clear, actionable statements
• Additions — new patterns, preferences, and lessons worth adding from how you've actually been working/deciding lately
• A conflict check — surfacing and resolving instructions that contradict each other (which confuse the AI)
• A privacy re-check — confirming no credentials, financial, health, or others' personal data has crept in
• A maintenance habit — a light cadence (a quick review every so often, add-a-line-as-you-go) so it stays current

Required Inputs

Ask for these if not provided:

• The current file — your MEMORY.md / CLAUDE.md / custom instructions (paste it)
• What's changed — how your work, preferences, or life have shifted since you wrote it
• Any friction — where the AI has been getting you wrong lately (a clue to what's stale/missing)
• New patterns — recent rules, lessons, or preferences worth capturing

Framework: Prune, Sharpen, Add, Protect

1. Review against reality. Compare what's in the file to who the person actually is now — files drift as people change.
2. Prune the dead weight. Remove stale rules, resolved situations, and redundancy — a bloated file dilutes the important stuff and confuses the AI.
3. Sharpen the vague. Turn fuzzy statements into clear, actionable ones ("be concise" → "lead with the answer, then reasoning") so they actually work.
4. Resolve contradictions. Surface instructions that conflict (a common cause of inconsistent AI behavior) and pick one.
5. Add what's missing. Capture new preferences, patterns, and lessons from how the person's actually been working — the file should grow with them.
6. Re-check privacy. Confirm nothing sensitive (credentials, financial, health, others' personal info) has crept in — and remove it if so.
7. Set a light habit. A quick periodic review plus adding a line when a new pattern emerges keeps it current without being a chore.

Output Format

Memory-file review

Prune (remove): [stale · redundant · resolved].

Sharpen (rewrite vaguer → clearer): ["[vague]" → "[clear, actionable]"].

Contradictions to resolve: [conflicting instructions → the one to keep].

Add (from recent patterns): [new preferences/rules/lessons].

Privacy check: [confirm no credentials/financial/health/others' data → remove if found].

Maintenance habit: [a quick periodic review + add-a-line-as-you-go].

Quality Checks

• [ ] Reviews the file against who the person actually is now
• [ ] Prunes stale/redundant/resolved content
• [ ] Sharpens vague statements into actionable ones
• [ ] Resolves contradictory instructions
• [ ] Adds missing recent patterns
• [ ] Re-checks for sensitive data; sets a maintenance habit

Anti-Patterns

• Only adding, never pruning (bloat).
• Leaving contradictions that confuse the AI.
• Vague rules that don't actually change behavior.
• Letting sensitive data sit in an AI-readable file.
• A one-time cleanup with no ongoing habit.

Example Trigger Phrases

• "Review my CLAUDE.md — it feels outdated."
• "Clean up my AI memory file, it's gotten bloated."
• "My custom instructions aren't working well anymore — fix them."
• "Maintain my MEMORY.md with how I've been working lately."
• "My AI keeps getting me wrong — check my context file."