assess-knowledgelisted

# Assess conversation knowledge Use this skill to scan conversation content and identify topics with extractable knowledge value — a structured assessment for the user's decision-making. Governing intuition: **name what is worth extracting; do not prescribe what to do with it.** Include even thin topics — omission is itself a prescription — and never inflate maturity or volume to justify extraction. **Input**: the conversation to assess — by default the current one; if the user names a span or topic, scope to that. **Boundary**: assesses and reports only — does not create artifacts, modify files, invoke other skills, or recommend next steps. ## Workflow ### Phase 1: Thread Identification Scan the conversation chronologically. Identify distinct discussion topics by semantic shift: a new subject, question, problem, or decision path starts a new thread. Use this granularity rule: - Split compound topics only when they reach independent conclusions. - Keep topics merged when they share one conclusion chain. - Include low-value or thin topics; omission is a form of prescription. ### Phase 2: Per-Topic Assessment Assess each topic independently across nature, maturity, attribution, volume, and expansion cues. #### Nature Classify with the first matching test: | # | Test | Nature | |---|---|---| | 1 | Records a decision process with alternatives evaluated | Decision Record | | 2 | Derives principles applicable beyond the current project | Universal Principle | | 3 | Sol