| name | self-reflection |
| description | Evaluates overall effectiveness — are idle behaviors producing value, are extensions working, what's blocking improvement. Higher-level thinking about approach, not individual conversations. |
| allowed-tools | Read, Write, Edit, Grep, Glob |
Self-Reflection
The core question: "Am I actually getting better, or just going through the motions?"
What to Review
- Recent actions — read last 2-3 days of
agent-data/memories/. What happened? What idle behaviors ran (idle-state.json)? Were they useful?
- Effectiveness — did your actions work? Check
agent-data/reaction-feedback.jsonl for concrete signal. Interpret emoji names semantically.
- Experiments — propose things to try. Be specific: what, why, how you'll measure. If you see a concrete improvement to a skill, make the edit now.
- Extensions — check
local/extensions/. Any working well? Underperforming? Collecting data that hasn't been reviewed? Should you create one for a pattern you keep noticing? See EXTENSIONS.md.
- Cooldowns — any skill running too often (empty results) or too rarely? Edit its
Cooldown: line.
Hypotheses are owned by the hypothesis-review skill — don't duplicate that work here. If you notice something worth testing, note it in today's memory for hypothesis-review to pick up.
Write findings to today's memory file under ## Self-Reflection. If nothing interesting came up, say so and stop.
Idle Behavior
Cooldown: 24 hours
- Read last 2-3 days of memories + recent transcripts
- Evaluate: did actions have intended effect? How do you know?
- Review extensions and skill effectiveness
- Propose or run experiments if something needs changing
- Be honest — don't manufacture insights
