skill-forge-evolvelisted

# Skill Evolution & Improvement ## Process ### Step 1: Diagnose the Issue Ask the user or analyze logs to identify the problem category: **Category A: Triggering Issues** - Under-triggering: Skill doesn't activate when it should - Over-triggering: Skill activates when it shouldn't - Mis-triggering: Wrong sub-skill activates **Category B: Execution Issues** - Incomplete workflows: Skill stops before finishing - Incorrect output: Results don't match expectations - Missing error handling: Failures not handled gracefully - Performance: Too slow or too many token used **Category C: Architecture Issues** - Missing capability: New use case not covered - Scale issues: Skill too large, needs decomposition - Cross-reference problems: Links to non-existent files **Category D: Quality Issues** - Inconsistent results: Different outputs for same input - Vague instructions: Claude interprets differently each time - Missing examples: No concrete guidance ### Step 2: Apply Fix by Category #### Fix: Under-Triggering 1. Read current description 2. Identify missing trigger phrases 3. Add domain keywords and paraphrases 4. Add file type mentions if relevant 5. Test with 5 queries that should now trigger **Common causes:** - Description too generic - Missing common paraphrases - Technical jargon without lay terms **Fix template:** ```yaml # Before (under-triggers) description: Analyzes code quality # After (specific triggers) description: > Static code analysis and quality assessmen