Use when completing significant work to extract learnings. Use when user says "reflect", "what did we learn", "capture learnings". Use after resolving complex problems or discovering patterns.
View on GitHubSelect agents to install to:
npx add-skill https://github.com/wayne930242/Reflexive-Claude-Code/blob/main/plugins/rcc/skills/reflecting/SKILL.md -a claude-code --skill reflectingInstallation paths:
.claude/skills/reflecting/# Reflecting ## Overview **Reflecting IS converting experience into reusable knowledge.** Analyze what worked, what failed, and encode learnings into the appropriate component (law, skill, rule, or documentation). **Core principle:** Experience without reflection is wasted. Capture it before context is lost. **Violating the letter of the rules is violating the spirit of the rules.** ## Task Initialization (MANDATORY) Before ANY action, create task list using TaskCreate: ``` TaskCreate for EACH task below: - Subject: "[reflecting] Task N: <action>" - ActiveForm: "<doing action>" ``` **Tasks:** 1. Analyze conversation 2. Identify learnings 3. Classify each learning 4. Integrate into components 5. Verify integration 6. Generate summary Announce: "Created 6 tasks. Starting execution..." **Execution rules:** 1. `TaskUpdate status="in_progress"` BEFORE starting each task 2. `TaskUpdate status="completed"` ONLY after verification passes 3. If task fails → stay in_progress, diagnose, retry 4. NEVER skip to next task until current is completed 5. At end, `TaskList` to confirm all completed ## Task 1: Analyze Conversation **Goal:** Review the conversation to identify significant events. **Look for:** - **Successes:** Patterns that led to good outcomes - **Failures:** Errors, multiple attempts, dead ends - **Discoveries:** New insights about the project/domain - **Repetitions:** Actions performed multiple times **Document each event:** ``` Event: [What happened] Context: [When/where it occurred] Outcome: [Success/failure/discovery] ``` **Verification:** Listed at least 3 significant events. ## Task 2: Identify Learnings **Goal:** Extract actionable learnings from events. **For each event, ask:** - What would have prevented this failure? - What made this succeed that could be repeated? - What did we learn that applies beyond this task? **Learning format:** ```yaml Learning: context: [When this applies] insight: [What was learned] evidence: [Specific ev