sw:compound

What problem does it solve?

Teams and change leads lose institutional memory after diagnoses and interventions because learnings, outcomes, and cross-initiative patterns are not captured in a discoverable, structured way. This Skill provides a lightweight, guided workflow to extract non-obvious insights from diagnosis and intervention sessions, detect conflicts with prior decisions, and persist actionable learnings into the repository so future sessions start smarter.

Core Features & Use Cases

• Context detection: Reads recent files in docs/switch to determine whether the session is post-diagnosis, post-intervention, outcome recording, or pattern discovery.
• Learning extraction guidance: Prompts users to surface non-obvious, specific, and actionable insights and enforces quality through reference enforcement prompts.
• Conflict detection & resolution: Searches existing learnings and offers explicit options to update, archive, keep both, or discard when new insights conflict with prior decisions.
• Targeted saving: Appends learnings to current-diagnosis.md, updates intervention outcome notes, or creates pattern files under docs/switch/patterns with templated metadata.
• Pipeline mode: Supports an automated mode that skips interactive prompts, flags conflicts for review, and tags saves for later inspection.

Quick Start

Use the sw:compound skill to record a specific learning or outcome from your recent diagnosis, intervention, or implementation session so it is persisted to the project's switch knowledge stores.