LLM-Coding · rdmueller · Mar 9, 2026 · Mar 9, 2026 · Mar 9, 2026
diff --git a/docs/agentskill.adoc b/docs/agentskill.adoc
@@ -0,0 +1,135 @@
+= AgentSkill: Semantic Anchor Translator
+
+The Semantic Anchors project includes an **AgentSkill** that teaches AI coding assistants to recognize and suggest semantic anchors during your work.
+
+== What does it do?
+
+The skill operates in two modes:
+
+=== Recognition Mode (verbose -> anchor)
+
+When you describe a concept in your own words, the AI identifies the matching semantic anchor:
+
+[quote]
+____
+*You:* "I want to categorize things so they don't overlap and cover everything" +
+*AI:* You're describing **MECE Principle** (Mutually Exclusive, Collectively Exhaustive).
+____
+
+=== Guidance Mode (question -> anchors)
+
+When you ask for methodology advice, the AI suggests relevant anchors:
+
+[quote]
+____
+*You:* "How should I document architecture decisions?" +
+*AI:* For architecture decisions: **ADR according to Nygard** or **MADR**. Both provide lightweight templates for capturing context, decision, and consequences.
+____
+
+== Installation
+
+The skill follows the https://agentskills.io[agentskills.io] specification and can be used with any compatible AI coding assistant.
+
+=== Claude Code
+
+Add to your project's `CLAUDE.md`:
+
+[source]
+----
+## Skills
+
+Use the semantic-anchor-translator skill from:
+https://github.com/LLM-Coding/Semantic-Anchors/tree/main/skill/semantic-anchor-translator
+----
+
+Or reference the skill's `SKILL.md` directly in your project configuration.
+
+=== GitHub Copilot
+
+Add to `.github/copilot-instructions.md` in your repository:
+
+[source]
+----
+## Semantic Anchors
+
+When the user describes a concept verbosely, identify the precise
+semantic anchor term. When asked for methodology advice, suggest
+relevant anchors from the catalog.
+
+Reference: https://github.com/LLM-Coding/Semantic-Anchors/blob/main/skill/semantic-anchor-translator/references/catalog.md
+----
+
+=== Cursor
+
+Add to `.cursor/rules` or `.cursorrules` in your project:
+
+[source]
+----
+## Semantic Anchors
+
+Use the semantic-anchor-translator skill to recognize and suggest
+established terminology. Catalog:
+https://github.com/LLM-Coding/Semantic-Anchors/blob/main/skill/semantic-anchor-translator/references/catalog.md
+----
+
+=== Amazon Kiro
+
+Add to your project's `specs/` directory or include in a spec file:
+
+[source]
+----
+## Semantic Anchors
+
+When the user describes a concept verbosely, identify the precise
+semantic anchor term. When asked for methodology advice, suggest
+relevant anchors from the catalog.
+
+Reference: https://github.com/LLM-Coding/Semantic-Anchors/blob/main/skill/semantic-anchor-translator/references/catalog.md
+----
+
+=== Other AI Tools
+
+Any AI coding assistant that supports custom instructions or system prompts can use the skill. Point it to the catalog at:
+
+https://github.com/LLM-Coding/Semantic-Anchors/blob/main/skill/semantic-anchor-translator/SKILL.md
+
+== Catalog Overview
+
+The skill covers **90+ semantic anchors** across these categories:
+
+[cols="1,3"]
+|===
+| Category | Key Anchors
+
+| Testing & Quality
+| TDD Chicago/London, BDD, Testing Pyramid, Mutation Testing, Property-Based Testing, Test Double
+
+| Software Architecture
+| Clean Architecture, Hexagonal, DDD, arc42, C4, ADR, MADR, CQRS, EDA
+
+| Design Principles
+| SOLID (5 sub-principles), GoF Design Patterns (23 sub-patterns), DRY, SPOT, YAGNI
+
+| Problem-Solving
+| Five Whys, Feynman Technique, Rubber Duck Debugging, Devil's Advocate, Cynefin
+
+| Requirements Engineering
+| MoSCoW, EARS, User Story Mapping, JTBD, Impact Mapping
+
+| Communication
+| BLUF, Pyramid Principle, MECE, Chatham House Rule, Socratic Method
+
+| Documentation
+| Diataxis Framework, Docs-as-Code
+
+| Strategic Planning
+| Wardley Mapping, Pugh Matrix
+|===
+
+The full catalog with descriptions, proponents, and core concepts is available at https://github.com/LLM-Coding/Semantic-Anchors/blob/main/skill/semantic-anchor-translator/references/catalog.md[catalog.md on GitHub].
+
+== Contributing
+
+When you add a new anchor to the catalog, please also update the AgentSkill catalog at `skill/semantic-anchor-translator/references/catalog.md` so AI agents can discover it.
+
+See link:#/contributing[Contributing] for the full contribution workflow.
diff --git a/docs/agentskill.de.adoc b/docs/agentskill.de.adoc
@@ -0,0 +1,135 @@
+= AgentSkill: Semantic Anchor Translator
+
+Das Semantic Anchors Projekt enthält einen **AgentSkill**, der KI-Coding-Assistenten beibringt, semantische Anker während der Arbeit zu erkennen und vorzuschlagen.
+
+== Was macht er?
+
+Der Skill arbeitet in zwei Modi:
+
+=== Erkennungsmodus (ausführlich -> Anker)
+
+Wenn du ein Konzept in eigenen Worten beschreibst, identifiziert die KI den passenden semantischen Anker:
+
+[quote]
+____
+*Du:* "Ich möchte Dinge so kategorisieren, dass sie sich nicht überlappen und alles abdecken" +
+*KI:* Du beschreibst das **MECE Principle** (Mutually Exclusive, Collectively Exhaustive).
+____
+
+=== Beratungsmodus (Frage -> Anker)
+
+Wenn du nach Methodik-Empfehlungen fragst, schlägt die KI relevante Anker vor:
+
+[quote]
+____
+*Du:* "Wie sollte ich Architekturentscheidungen dokumentieren?" +
+*KI:* Für Architekturentscheidungen: **ADR nach Nygard** oder **MADR**. Beide bieten leichtgewichtige Templates für Kontext, Entscheidung und Konsequenzen.
+____
+
+== Installation
+
+Der Skill folgt der https://agentskills.io[agentskills.io]-Spezifikation und kann mit jedem kompatiblen KI-Coding-Assistenten verwendet werden.
+
+=== Claude Code
+
+Füge in die `CLAUDE.md` deines Projekts hinzu:
+
+[source]
+----
+## Skills
+
+Use the semantic-anchor-translator skill from:
+https://github.com/LLM-Coding/Semantic-Anchors/tree/main/skill/semantic-anchor-translator
+----
+
+Oder referenziere die `SKILL.md` des Skills direkt in deiner Projektkonfiguration.
+
+=== GitHub Copilot
+
+Füge in `.github/copilot-instructions.md` in deinem Repository hinzu:
+
+[source]
+----
+## Semantic Anchors
+
+When the user describes a concept verbosely, identify the precise
+semantic anchor term. When asked for methodology advice, suggest
+relevant anchors from the catalog.
+
+Reference: https://github.com/LLM-Coding/Semantic-Anchors/blob/main/skill/semantic-anchor-translator/references/catalog.md
+----
+
+=== Cursor
+
+Füge in `.cursor/rules` oder `.cursorrules` in deinem Projekt hinzu:
+
+[source]
+----
+## Semantic Anchors
+
+Use the semantic-anchor-translator skill to recognize and suggest
+established terminology. Catalog:
+https://github.com/LLM-Coding/Semantic-Anchors/blob/main/skill/semantic-anchor-translator/references/catalog.md
+----
+
+=== Amazon Kiro
+
+Füge in das `specs/`-Verzeichnis deines Projekts oder in eine Spec-Datei hinzu:
+
+[source]
+----
+## Semantic Anchors
+
+When the user describes a concept verbosely, identify the precise
+semantic anchor term. When asked for methodology advice, suggest
+relevant anchors from the catalog.
+
+Reference: https://github.com/LLM-Coding/Semantic-Anchors/blob/main/skill/semantic-anchor-translator/references/catalog.md
+----
+
+=== Andere KI-Tools
+
+Jeder KI-Coding-Assistent, der benutzerdefinierte Anweisungen oder System-Prompts unterstützt, kann den Skill nutzen. Verweise auf den Katalog unter:
+
+https://github.com/LLM-Coding/Semantic-Anchors/blob/main/skill/semantic-anchor-translator/SKILL.md
+
+== Katalogübersicht
+
+Der Skill umfasst **90+ semantische Anker** in folgenden Kategorien:
+
+[cols="1,3"]
+|===
+| Kategorie | Wichtige Anker
+
+| Testing & Qualität
+| TDD Chicago/London, BDD, Testing Pyramid, Mutation Testing, Property-Based Testing, Test Double
+
+| Software-Architektur
+| Clean Architecture, Hexagonal, DDD, arc42, C4, ADR, MADR, CQRS, EDA
+
+| Design-Prinzipien
+| SOLID (5 Unterprinzipien), GoF Design Patterns (23 Untermuster), DRY, SPOT, YAGNI
+
+| Problemlösung
+| Five Whys, Feynman Technique, Rubber Duck Debugging, Devil's Advocate, Cynefin
+
+| Requirements Engineering
+| MoSCoW, EARS, User Story Mapping, JTBD, Impact Mapping
+
+| Kommunikation
+| BLUF, Pyramid Principle, MECE, Chatham House Rule, Socratic Method
+
+| Dokumentation
+| Diataxis Framework, Docs-as-Code
+
+| Strategische Planung
+| Wardley Mapping, Pugh Matrix
+|===
+
+Der vollständige Katalog mit Beschreibungen, Vertretern und Kernkonzepten ist unter https://github.com/LLM-Coding/Semantic-Anchors/blob/main/skill/semantic-anchor-translator/references/catalog.md[catalog.md auf GitHub] verfügbar.
+
+== Mitwirken
+
+Wenn du einen neuen Anker zum Katalog hinzufügst, aktualisiere bitte auch den AgentSkill-Katalog unter `skill/semantic-anchor-translator/references/catalog.md`, damit KI-Agenten ihn finden können.
+
+Siehe link:#/contributing[Mitwirken] für den vollständigen Beitrags-Workflow.
diff --git a/scripts/render-docs.js b/scripts/render-docs.js
@@ -64,5 +64,8 @@ renderFile(path.join(ROOT, 'CONTRIBUTING.de.adoc'), path.join(WEB_PUBLIC, 'CONTR
 
 renderFile(path.join(ROOT, 'docs/changelog.adoc'), path.join(WEB_DOCS, 'changelog.html'))
 
+renderFile(path.join(ROOT, 'docs/agentskill.adoc'), path.join(WEB_DOCS, 'agentskill.html'))
+renderFile(path.join(ROOT, 'docs/agentskill.de.adoc'), path.join(WEB_DOCS, 'agentskill.de.html'))
+
 // all-anchors.adoc uses include:: directives — resolved automatically in Node.js
 renderFile(path.join(ROOT, 'docs/all-anchors.adoc'), path.join(WEB_DOCS, 'all-anchors.html'))
diff --git a/website/src/components/header.js b/website/src/components/header.js
@@ -38,6 +38,7 @@ export function renderHeader() {
                 <a href="#/about" class="nav-link text-[var(--color-text-secondary)] hover:text-[var(--color-text)] transition-colors" data-route="/about" data-i18n="nav.about">${i18n.t('nav.about')}</a>
                 <a href="#/contributing" class="nav-link text-[var(--color-text-secondary)] hover:text-[var(--color-text)] transition-colors" data-route="/contributing" data-i18n="nav.contributing">${i18n.t('nav.contributing')}</a>
                 <a href="#/changelog" class="nav-link text-[var(--color-text-secondary)] hover:text-[var(--color-text)] transition-colors" data-route="/changelog" data-i18n="nav.changelog">${i18n.t('nav.changelog')}</a>
+                <a href="#/agentskill" class="nav-link text-[var(--color-text-secondary)] hover:text-[var(--color-text)] transition-colors" data-route="/agentskill" data-i18n="nav.agentskill">${i18n.t('nav.agentskill')}</a>
               </div>
               <div class="flex items-center gap-3">
                 <button
@@ -142,6 +143,7 @@ export function renderHeader() {
             <a href="#/about" class="nav-link mobile-nav-link px-3 py-2 rounded-md text-[var(--color-text-secondary)] hover:text-[var(--color-text)] hover:bg-[var(--color-bg-secondary)] transition-colors" data-route="/about" data-i18n="nav.about">${i18n.t('nav.about')}</a>
             <a href="#/contributing" class="nav-link mobile-nav-link px-3 py-2 rounded-md text-[var(--color-text-secondary)] hover:text-[var(--color-text)] hover:bg-[var(--color-bg-secondary)] transition-colors" data-route="/contributing" data-i18n="nav.contributing">${i18n.t('nav.contributing')}</a>
             <a href="#/changelog" class="nav-link mobile-nav-link px-3 py-2 rounded-md text-[var(--color-text-secondary)] hover:text-[var(--color-text)] hover:bg-[var(--color-bg-secondary)] transition-colors" data-route="/changelog" data-i18n="nav.changelog">${i18n.t('nav.changelog')}</a>
+            <a href="#/agentskill" class="nav-link mobile-nav-link px-3 py-2 rounded-md text-[var(--color-text-secondary)] hover:text-[var(--color-text)] hover:bg-[var(--color-bg-secondary)] transition-colors" data-route="/agentskill" data-i18n="nav.agentskill">${i18n.t('nav.agentskill')}</a>
           </div>
         </div>
       </nav>

diff --git a/website/src/main.js b/website/src/main.js
@@ -103,6 +103,7 @@ function initApp() {
   addRoute('/about', renderAboutPage)
   addRoute('/contributing', renderContributingPage)
   addRoute('/changelog', renderChangelogPage)
+  addRoute('/agentskill', renderAgentSkillPage)
   addRoute('/all-anchors', renderAllAnchorsPage)
 
   const app = document.querySelector('#app')
@@ -188,6 +189,15 @@ function renderChangelogPage() {
   loadDocContent('docs/changelog.adoc')
 }
 
+function renderAgentSkillPage() {
+  const pageContent = document.getElementById('page-content')
+  if (!pageContent) return
+
+  pageContent.innerHTML = renderDocPage()
+  updateActiveNavLink()
+  loadDocContent('docs/agentskill.adoc')
+}
+
 function renderAllAnchorsPage() {
   const pageContent = document.getElementById('page-content')
   if (!pageContent) return
@@ -393,6 +403,8 @@ function handleLanguageChange() {
     loadDocContent('CONTRIBUTING.adoc')
   } else if (currentRoute === '/changelog') {
     loadDocContent('docs/changelog.adoc')
+  } else if (currentRoute === '/agentskill') {
+    loadDocContent('docs/agentskill.adoc')
   } else if (currentRoute === '/all-anchors') {
     loadDocContent('docs/all-anchors.adoc')
   } else if (currentRoute === '/') {

diff --git a/website/src/translations/de.json b/website/src/translations/de.json
@@ -9,6 +9,7 @@
   "nav.about": "Über",
   "nav.contributing": "Mitwirken",
   "nav.changelog": "Änderungsprotokoll",
+  "nav.agentskill": "AgentSkill",
   "main.heading": "Semantic Anchors erkunden",
   "main.subheading": "Ein kuratierter Katalog klar definierter Begriffe, Methoden und Frameworks für effektive LLM-Kommunikation.",
   "main.aboutLink": "Über",

diff --git a/website/src/translations/en.json b/website/src/translations/en.json
@@ -9,6 +9,7 @@
   "nav.about": "About",
   "nav.contributing": "Contributing",
   "nav.changelog": "Changelog",
+  "nav.agentskill": "AgentSkill",
   "main.heading": "Explore Semantic Anchors",
   "main.subheading": "A curated catalog of well-defined terms, methodologies, and frameworks for effective LLM communication.",
   "main.aboutLink": "About",