一键导入
memento-reflect
// 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 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 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 when the user wants to remove low-value learned skills, clean up unused skills, or reduce the learned skill library size
Use when the user wants to see an overview of their learned skills, check utility scores, or identify skills that need optimization or pruning
| name | memento-reflect |
| description | 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 |
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}?"