← Back to list

introspect
by genomewalker
⭐ 0🍴 0📅 Jan 25, 2026
SKILL.md
name: introspect description: Soul self-examination (Svadhyaya) execution: task
Introspect
Self-examination for partnership improvement.
Process
-
Gather context
soul_contextfor overall healthrecall --tag correctionfor recent corrections (what I got wrong)recall --tag outcomefor feedback (what helped vs didn't)recall --tag preferencefor user preferences (am I following them?)recall --tag insightfor patterns learned
-
Examine through 5 lenses
- vedana (sensation): Where is friction in our partnership?
- jnana (knowledge): Am I applying stored wisdom?
- darshana (vision): Do my actions align with user preferences?
- vichara (inquiry): What patterns recur? What mistakes repeat?
- prajna (wisdom): What have I truly learned?
-
Synthesize
- State: healthy | struggling | growing
- Key insight: one sentence
- Improvement: one concrete change
-
Record & Output
- Store insight via
learn_insightif generalizable - Output 5-10 line summary
- End with:
KEY_INSIGHT: [one-line]
- Store insight via
Example Output
Soul State: growing
Recent corrections (2): Remembered to use Grep tool, avoided AI slop
Outcomes: 3 worked, 1 failed (cache approach didn't scale)
Preferences followed: concise responses ✓, no shortcuts ✓
Friction: Sometimes still verbose in explanations
Recurring: Tendency to over-explain before acting
Learning: User prefers action over discussion
KEY_INSIGHT: Act first, explain only if asked
Score
Total Score
50/100
Based on repository quality metrics
✓SKILL.md
SKILL.mdファイルが含まれている
+20
○LICENSE
ライセンスが設定されている
0/10
○説明文
100文字以上の説明がある
0/10
○人気
GitHub Stars 100以上
0/15
○最近の活動
3ヶ月以内に更新がある
0/10
○フォーク
10回以上フォークされている
0/5
✓Issue管理
オープンIssueが50未満
+5
✓言語
プログラミング言語が設定されている
+5
○タグ
1つ以上のタグが設定されている
0/5
Reviews
💬
Reviews coming soon