메뉴
Use when the user wants to remove low-value learned skills, clean up unused skills, or reduce the learned skill library size
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | memento-prune |
| description | Use when the user wants to remove low-value learned skills, clean up unused skills, or reduce the learned skill library size |
Remove learned skills that are no longer useful. Never auto-deletes — always confirms with user.
Read metrics.json (global and project). Flag skills matching ANY:
utility < utility_threshold AND usage_count >= min_samples_for_judgment (proven low value)last_used older than prune_after_days_unused days from today (abandoned)Show each candidate with reasoning:
Prune candidates:
1. learned-bad-pattern (global)
Utility: 0.20 (1/5) — below threshold 0.40
Last used: 2026-01-15 — 69 days ago
Reason: low utility + unused
2. learned-old-approach (project)
Utility: — (0/0) — never used
Last used: 2026-01-20 — 64 days ago
Reason: abandoned (never used, 64 days old)
Ask: "Delete these skills? You can choose individually (e.g., 'just 1') or all."
For each confirmed deletion:
learned-{name}/ skill directoryEven if called programmatically, always show the list and wait for confirmation.
Use when memento-reflect identifies a reusable pattern worth capturing, or when the user explicitly wants to create a new learned skill from a task execution pattern
Use when a learned skill has low utility score, has been failing, or the user wants to improve an existing learned skill based on failure analysis
Use after completing any significant task to self-evaluate what worked or failed, update learned skill metrics, and discover reusable patterns worth capturing as new skills
Use when the user wants to see an overview of their learned skills, check utility scores, or identify skills that need optimization or pruning