AI readiness toolkit

v1.35.0 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 1mo Developer Productivity

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Summary

AI summary

Updates Other Changes, feat, and refactor across a mixed release.

Changes in this release

Type	Severity	Summary	CVE
Feature
Feature	Low	Adds decoration sweep and directness-claim audit on semantic-compress (A/B-gated). Adds decoration sweep and directness-claim audit on semantic-compress (A/B-gated). Source: llm_adapter@2026-06-04 Confidence: high	—
Feature	Low	Addresses skill-forge review findings (judge-tier, runner coupling, Phase A drift, prune discipline). Addresses skill-forge review findings (judge-tier, runner coupling, Phase A drift, prune discipline). Source: llm_adapter@2026-06-04 Confidence: high	—
Feature	Low	Restructures /assess report for human skim and AI detail. Restructures /assess report for human skim and AI detail. Source: llm_adapter@2026-06-04 Confidence: high	—
Refactor
Refactor	Low	Removes shipped example-forge-report from skill-forge (docs no longer ship). Removes shipped example-forge-report from skill-forge (docs no longer ship). Source: llm_adapter@2026-06-04 Confidence: high	—
Refactor	Low	Compresses /understand to a validated behavioral equivalent. Compresses /understand to a validated behavioral equivalent. Source: llm_adapter@2026-06-04 Confidence: high	—
Refactor	Low	Performs decoration sweep + claim audit on skill-forge (A/B-gated prune). Performs decoration sweep + claim audit on skill-forge (A/B-gated prune). Source: granite4.1:30b@2026-06-04-audit Confidence: low	—

Full changelog

📦 Standalone skill ZIPs (claude.ai, Claude Desktop, Cowork, any Agent-Skills assistant): https://github.com/bjcoombs/ai-native-toolkit/releases/tag/standalone-skills-v1.35.0

What's Changed

Features

feat: Decoration sweep + directness-claim audit on semantic-compress (A/B-gated) by @bjcoombs in https://github.com/bjcoombs/ai-native-toolkit/pull/153
feat: Address skill-forge review findings (judge-tier, runner coupling, Phase A- drift, prune discipline) by @bjcoombs in https://github.com/bjcoombs/ai-native-toolkit/pull/155
feat: Restructure /assess report for human skim + AI detail by @bjcoombs in https://github.com/bjcoombs/ai-native-toolkit/pull/158

Other Changes

refactor: Decoration sweep + claim audit on skill-forge (A/B-gated prune) by @bjcoombs in https://github.com/bjcoombs/ai-native-toolkit/pull/152
refactor: Remove shipped example-forge-report from skill-forge (result docs don't ship) by @bjcoombs in https://github.com/bjcoombs/ai-native-toolkit/pull/154
refactor: Compress /understand to validated behavioural equivalent by @bjcoombs in https://github.com/bjcoombs/ai-native-toolkit/pull/156

Full Changelog: https://github.com/bjcoombs/ai-native-toolkit/compare/v1.32.0...v1.35.0

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track AI readiness toolkit

Get notified when new releases ship.

About AI readiness toolkit

All releases →