m42-signs

Add a new learning sign manually to the backlog or directly to CLAUDE.md

Apply approved learnings from backlog to CLAUDE.md files

Extract learnings from session transcript via parallel subagent processing

Show m42-signs plugin help and available commands

List all signs across CLAUDE.md files in the project

Interactive review of pending learnings in backlog

Show backlog status summary with counts by status

Analyze preprocessed transcript chunk for learning extraction. Use when extract command processes large transcripts in parallel.

Match learning candidates to appropriate CLAUDE.md files and detect duplicates. Use proactively when matching learnings to CLAUDE.md files, detecting duplicate learnings, or assigning learning targets.

Score and filter learning candidates by quality. Use after transcript-section-analyzer and context-matcher complete.

Analyzes transcript sections to extract learning candidates with structured metadata. Used by extract command for parallel section processing. Use proactively when extract command delegates section analysis.

Domain knowledge for extracting learnings from session transcripts. Provides learning taxonomy (8 categories), quality criteria, extraction patterns (linguistic/tool signals), and confidence scoring. Used by subagents during transcript analysis to identify and classify actionable insights.

Manages learning extraction and sign application workflows. This skill should be used when extracting learnings from session transcripts, reviewing proposed signs, or applying approved learnings to CLAUDE.md files. Triggers on "extract learnings", "review signs", "apply signs", "manage signs", "learning backlog".