What problem does it solve? Teams repeatedly make the same mistakes because corrections and successful patterns from conversations are never captured. This Skill analyzes conversations for user corrections, praise, and edge cases, then proposes structured updates to persistent knowledge files so learnings survive across sessions. ## Core Features & Use Cases - Confidence-Rated Signal Detection: Classifies learnings as HIGH (user corrections like "no" or "wrong"), MEDIUM (praise or edge cases), or LOW (accumulated preferences) with explicit thresholds for when to propose changes. - Routed Knowledge Persistence: Directs learnings to the right target: agent-specific history files, team decision inboxes, or skill improvement recommendations. - Approval-Gated Writes: Always presents proposed changes in a structured summary and waits for user confirmation before modifying any files. - Use Case: After a user corrects an agent for using grep instead of code search tools, the Skill captures a HIGH-confidence constraint and appends it to the agent's history.md so the mistake is never repeated. ## Quick Start Ask the assistant to reflect on this session and capture any learnings from corrections or feedback into the squad knowledge files.
