feat: add AgentSkill for bi-directional anchor translation#132
Merged
rdmueller merged 3 commits intoMar 7, 2026
Conversation
Adds a skill following the AgentSkills.io specification that enables agents to: 1. Recognize verbose descriptions and identify the semantic anchor term 2. Suggest relevant anchors when users ask for methodology/guidance Includes: - SKILL.md with frontmatter and instructions - references/catalog.md with 50+ anchors organized by category Compatible with Claude Code, Codex, Cursor, and other skills-compatible agent products.
Contributor
WalkthroughDrei Dokumentationsänderungen: neue Skill‑Dokumentation Änderungen
Geschätzter Review‑Aufwand🎯 2 (Einfach) | ⏱️ ~12 Minuten 🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
When adding new anchors, contributors must also update the AgentSkill catalog to keep it in sync.
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@skill/semantic-anchor-translator/references/catalog.md`:
- Around line 1-209: The file "Semantic Anchors Catalog" (catalog.md) is written
in Markdown but project policy requires AsciiDoc; convert the entire document to
AsciiDoc (rename to catalog.adoc), replacing Markdown headings (# → =, ## → ==,
### → ===), bold syntax (**Text** → *Text*), inline code/backticks → plain text,
convert links to AsciiDoc link: syntax (e.g.,
link:https://github.com/LLM-Coding/Semantic-Anchors[Semantic Anchors]) and keep
lists as hyphenated lists; ensure sections like "TDD, London School" and entries
(e.g., "Testing Pyramid", "Clean Architecture") preserve content and formatting,
and add a short comment or pragma to ignore the LanguageTool false-positive on
the line containing "Explain concept simply, identify gaps, refine
understanding" if required by your linter.
In `@skill/semantic-anchor-translator/SKILL.md`:
- Around line 1-69: The file SKILL.md is in Markdown with YAML frontmatter but
the project requires AsciiDoc; convert SKILL.md to SKILL.adoc by removing YAML
frontmatter and translating it to AsciiDoc document attributes (e.g., :name:,
:description:, :author:, :version:, :source:), convert Markdown headings (e.g.,
"# Semantic Anchor Translator", "## Two Modes", "### Recognition Mode") to
AsciiDoc heading syntax (==, ===, ====), convert bold/inline formatting and
blockquotes to AsciiDoc equivalents, rewrite the Markdown table under "Quick
Category Index" into AsciiDoc table syntax, update links like
"[references/catalog.md]" and external URLs to AsciiDoc link form, and ensure
any examples/blockquote lines follow AsciiDoc literal or quote conventions; keep
the same content and headings (Semantic Anchor Translator, Catalog Reference,
Quick Category Index) and save as .adoc.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yml
Review profile: CHILL
Plan: Pro
Run ID: c5842a05-e32d-46ca-8cfc-b46de376b3c8
📒 Files selected for processing (2)
skill/semantic-anchor-translator/SKILL.mdskill/semantic-anchor-translator/references/catalog.md
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@CLAUDE.md`:
- Around line 277-290: Der Abschnitt "⚠️ AgentSkill Sync Required" benutzt
Markdown (###, ```, - [ ]) und muss in AsciiDoc umgewandelt: ersetze die
Markdown-Überschrift durch die passende AsciiDoc-Überschrift für denselben
Titel, ersetze den gefenced codeblock um
"skill/semantic-anchor-translator/references/catalog.md" durch einen
AsciiDoc-Source-Block ([source,text] und ---- ... ----), konvertiere die
fettgedruckten/Listen-Elemente (**Checklist for new anchors:** und - [ ]) in
AsciiDoc-Notation (*Checklist for new anchors:* und * [ ] ...) und entferne die
```-Marken, sodass keine MD040-Codeblock-Warnung mehr auftritt; suche nach dem
Text "AgentSkill enables AI agents" und
"skill/semantic-anchor-translator/references/catalog.md" als Ankerpunkte zum
Patch.
- Remind to update skill catalog when adding new anchors - Add path instructions for skill/ directory
Contributor
There was a problem hiding this comment.
🧹 Nitpick comments (1)
.coderabbit.yml (1)
17-31: Sync-Regel und Pflichtfelder im selben Block vervollständigen.Guter Zusatz, aber hier fehlen noch zwei wichtige Fälle:
- Der Katalog-Sync sollte auch Umbenennungen/Entfernungen abdecken.
- Bei den Pflichtfeldern fehlt
:related:.Vorgeschlagene Anpassung
- Pflichtfelder: :categories:, :roles:, :proponents: + Pflichtfelder: :categories:, :roles:, :related:, :proponents: @@ - Wenn ein neuer Anchor hinzugefügt wird, muss auch + Wenn ein Anchor hinzugefügt, umbenannt oder entfernt wird, muss auch skill/semantic-anchor-translator/references/catalog.md aktualisiert werden, damit AI-Agenten den neuen Anchor erkennen können.Based on learnings: Applies to docs/anchors/*.adoc : Each semantic anchor file must include AsciiDoc attributes for metadata:
:categories:,:roles:,:related:,:proponents:, and optionally:tags:🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.coderabbit.yml around lines 17 - 31, Update the docs/anchors sync rules: in the instructions block that applies to "docs/anchors/**/*.adoc" ensure the Pflichtfelder list includes :related: (making the required attributes :categories:, :roles:, :related:, :proponents: and optional :tags:), and extend the catalog sync note for skill/semantic-anchor-translator/references/catalog.md to explicitly handle not only additions but also renames and deletions so the AgentSkill catalog stays in sync with renamed or removed anchor files.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Nitpick comments:
In @.coderabbit.yml:
- Around line 17-31: Update the docs/anchors sync rules: in the instructions
block that applies to "docs/anchors/**/*.adoc" ensure the Pflichtfelder list
includes :related: (making the required attributes :categories:, :roles:,
:related:, :proponents: and optional :tags:), and extend the catalog sync note
for skill/semantic-anchor-translator/references/catalog.md to explicitly handle
not only additions but also renames and deletions so the AgentSkill catalog
stays in sync with renamed or removed anchor files.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yml
Review profile: CHILL
Plan: Pro
Run ID: ed5b0c50-64f6-4563-9250-ad188c87436f
📒 Files selected for processing (1)
.coderabbit.yml
Member
|
hey! This is a cool skill! I will review it over the weekend... |
Author
|
Thanks @rdmueller! And this is a great opportunity for me to see coderabbit in action. It makes me wanting to try it myself! |
Member
|
thanx. I will now merge the PR, but we also have to add some docs about the skill. Regarding coderabbit: you can ask claude to install it for you or even use the https://llm-coding.github.io/vibe-coding-risk-radar/ skill (see the docs for details) to do it. |
Member
|
Would you like to post about this new skill on linkedIn? Then I can repost it. |
This was referenced Mar 7, 2026
5 tasks
This was referenced Apr 6, 2026
This was referenced Jun 1, 2026
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
3 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.
Summary
Adds a skill following the AgentSkills.io specification that enables AI agents to work bi-directionally with semantic anchors:
What's included
Compatibility
The skill follows the AgentSkills.io specification and works with:
Example usage
Recognition mode:
Guidance mode:
Why this matters
This makes the Semantic Anchors catalog practically useful for AI-assisted development — agents can now help users discover and apply the right terminology, improving communication precision.
Summary by CodeRabbit
Dokumentation
Chores