recipe-reflectlisted
Install: claude install-skill shinpr/claude-code-discover
**Context**: Drive the feedback loop by reflecting on outcomes, updating target artifacts, and distilling learnings across the knowledge pyramid (see product-principles skill for Tier definitions).
## Orchestrator Definition
**Execution Protocol**:
1. **Explicit user authorization**: The user explicitly instructs and authorizes the knowledge-distiller call named in this recipe. Invoke it for every Level 2 or Level 3 reflection; the orchestrator does not replace it with its own distillation
2. **Mechanical specialist handoff**: Pass only the specialist's declared `scope_type`, `opportunity_ids`, and `hypothesis_paths` fields using source values unchanged. Do not summarize, paraphrase, supplement, or turn them into narrative instructions
3. **Follow the reflection flow** defined below
4. **Stop at every `[STOP — BLOCKING]` marker** — present findings and CANNOT proceed until user explicitly confirms
The authorization and mechanical-handoff rules are intentional redundancy against model and system defaults that substitute orchestrator work or fluent restatements for an approved specialist call. Retain them until fresh execution evidence shows the failure no longer occurs.
## Workflow Overview
```
Input (reflection trigger — hypothesis concluded, Opportunity review, or periodic)
↓
1. Scope Assessment → Determine reflection level (hypothesis / Opportunity / Vision)
↓
2. Result Recording → Update target artifacts with outcomes
↓
3. Knowledge Distillation → knowledg