proffesor-for-testing__agentic-qe/docs/releases/v3.7.13.md

v3.7.13 Release Notes

Release Date: 2026-03-07

Highlights

Three skill validation improvements inspired by analysis of the Claude Blog skill-creator system: trigger optimization, A/B version comparison, and skill intent classification.

Added

• Trigger Optimizer (src/validation/trigger-optimizer.ts) — Analyzes skill descriptions and tags to detect false positive/negative activation risks. Calculates Jaccard similarity across the skill fleet, identifies confusable skills, and generates actionable suggestions to improve trigger precision. Includes 23 unit tests.
• Version Comparator (src/validation/version-comparator.ts) — A/B testing between skill versions using Cohen's d effect size and confidence scoring. Produces per-test-case comparisons and Markdown reports for data-driven skill improvement decisions. Includes 29 unit tests.
• Skill Intent Classification — New skill_intent frontmatter field classifies skills as capability_uplift (fills model gaps, needs regression testing as models improve), encoded_preference (encodes team workflows, needs fidelity verification), or hybrid (combines both intents).

Changed

• ADR-056 updated with Phase 6 (Blog-Inspired Improvements) documenting the three new features.
• Validation module index and top-level package exports now include TriggerOptimizer, VersionComparator, and all associated types.
• Skill frontmatter schema (skill-frontmatter.schema.json) updated across all 3 copies (docs, assets, .claude).