feat(skill): add anchor-prior-test skill for vetting anchor candidates#587
Merged
rdmueller merged 1 commit intoJun 9, 2026
Merged
Conversation
A clean-room procedure that empirically tests whether a term is a strong semantic anchor - probing recognition, anchor-action, attribution and name ambiguity across model tiers via `claude -p --setting-sources ""` - and emits a verdict against the four criteria, a tier rating, and a ready-to-paste proposal or rejection. Operationalises the CONTRIBUTING litmus test; relates to LLM-Coding#329. Includes the Morphological Box run as a worked example. Bumps the semantic-anchors plugin to 0.3.0. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Contributor
|
Caution Review failedThe pull request is closed. ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yml Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (11)
WalkthroughDie Pull Request fügt eine vollständige Dokumentation für die neue „Anchor Prior Test"-Skill zur empirischen Überprüfung semantischer Anker-Kandidaten hinzu und erhöht die Plugin-Version auf 0.3.0. Die Dokumentation wird parallel in zwei Verzeichnissen (Plugin und Root) mit identischem Inhalt bereitgestellt. ChangesAnchor Prior Test Skill Release
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Possibly related PRs
Suggested reviewers
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Adds a new skill
anchor-prior-test— a clean-room procedure that empirically tests whether a candidate term is a strong semantic anchor before it is proposed, instead of guessing.It operationalises the manual litmus test in
CONTRIBUTING.adoc("ask the LLM what it associates") into a rigorous, multi-model method and emits a structured verdict.How it works
claude -p --setting-sources "" --strict-mcp-configfrom a neutral directory, so the project's ownCLAUDE.md/memory cannot bias the result. (Sub-agents are contaminated; the skill explains why.)Why
Contents
skill/anchor-prior-test/SKILL.md+references/(clean-room, probe-battery, scoring, worked-example)references/worked-example.mddocuments a full run on the Morphological Box candidate (Haiku/Sonnet/Opus)plugins/semantic-anchors/skills/, version bumped0.2.0 → 0.3.0Companion to the article in #586 (the why); this skill is the how.
🤖 Generated with Claude Code
Summary by CodeRabbit
Dokumentation
Chores