From memento-skills
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
How this skill is triggered — by the user, by Claude, or both
Slash command
/memento-skills:memento-reflectThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Post-task self-evaluation that closes the learning loop. This is the Write phase of Read-Write Reflective Learning.
Post-task self-evaluation that closes the learning loop. This is the Write phase of Read-Write Reflective Learning.
Review the current conversation and identify:
Judge the outcome using these criteria:
Verdict: success or failure with one-sentence reasoning.
If a learned skill was used during this task, update its metrics file.
Read the appropriate metrics.json (~/.claude/memento/metrics.json for global skills, .claude/memento/metrics.json for project skills). Then update the skill entry:
usage_count: increment by 1success_count: increment if successfailure_count: increment if failurelast_used: today's dateutility: success_count / (success_count + failure_count)trigger_log: append {"task": "short description", "result": "success|failure", "date": "today"} — keep max 5 most recentWrite the updated JSON back. Create the directory and file if they don't exist yet — initialize with:
{
"version": 1,
"config": {
"utility_threshold": 0.4,
"min_samples_for_judgment": 3,
"prune_after_days_unused": 60
},
"skills": {}
}
Ask yourself: "Did I do something reusable that no existing skill covers?"
Criteria for a new skill:
If yes — tell the user what pattern you found and suggest: "Want me to capture this as a learned skill? I'll use /memento create."
If a learned skill was used but the task failed:
If the skill itself is at fault — suggest: "The {skill-name} skill may need improvement. Want me to run /memento optimize {skill-name}?"
npx claudepluginhub tmdgusya/momento --plugin memento-skillsAnalyzes skill outcome logs and user corrections, then proposes self-improvements to skill behavior and description hygiene.
Captures high/medium/low confidence patterns from conversations to prevent repeating mistakes and preserve successes. Invoke proactively after corrections, praise, edge cases, or skill-heavy sessions.
Captures high/medium/low confidence learnings from conversations via triggers like corrections, praise, edge cases. Improves skills by preventing mistakes and preserving successes. Invoke proactively after 'no/wrong', 'perfect', or session ends.