A curated catalog of well-defined terms, methodologies, and frameworks that serve as reference points when communicating with Large Language Models (LLMs).
Visit the Semantic Anchors website →
Features:
- 📊 Interactive Treemap Visualization - Explore 46+ semantic anchors
- 🎯 Role-Based Filtering - Filter by 12 professional roles
- 🔍 Real-Time Search - Find anchors by name, tags, or proponents
- 🌙 Dark/Light Theme - Comfortable viewing in any environment
- 🌍 Bilingual UI - English/German interface (content in English)
Semantic anchors are well-defined terms, methodologies, or frameworks that act as shared vocabulary between humans and LLMs. They trigger specific, contextually rich knowledge domains within an LLM's training data.
- "TDD, London School" → Activates: outside-in testing, mock-heavy approach, interaction-based verification
- "Clean Architecture" → Activates: Uncle Bob's layered design, dependency rule, use cases as center
- "SOLID Principles" → Activates: S.O.L.I.D. breakdown, object-oriented design patterns
- Precision - Reduce ambiguity by referencing established knowledge
- Efficiency - Activate complex frameworks with minimal tokens
- Consistency - Ensure LLMs interpret concepts as the community intends
- Context Compression - Convey rich context concisely
The catalog is organized as:
docs/
├── anchors/ # 46+ individual anchor files
│ ├── tdd-london-school.adoc
│ ├── clean-architecture.adoc
│ └── ...
├── categories/ # 11 MECE-compliant categories
├── roles/ # 12 professional roles
└── metadata/ # Generated metadata for website
Find anchors relevant to your profession:
- Software Developer / Engineer
- Software Architect
- QA Engineer / Tester
- DevOps Engineer
- Product Owner / Manager
- Business Analyst / Requirements Engineer
- Technical Writer / Documentation Specialist
- UX Designer / Researcher
- Data Scientist / Statistician
- Consultant / Coach
- Team Lead / Engineering Manager
- Educator / Trainer
We welcome contributions! See our Contributing Guide for:
- How to propose new semantic anchors
- Quality criteria for anchors
- Testing methodology with LLMs
- Development setup
- Test your anchor with an LLM:
What concepts do you associate with '<anchor name>'? - Verify quality criteria: Precise, Rich, Consistent, Attributable
- Create an issue using our Propose New Anchor template
- Node.js 20+
- npm
# Clone repository
git clone https://github.com/LLM-Coding/Semantic-Anchors.git
cd Semantic-Anchors
# Install website dependencies
cd website
npm install
# Run development server
npm run dev
# → http://localhost:5173/
# Run tests
npm run test
# Build for production
npm run build# Extract metadata from anchor files
cd scripts
npm install
node extract-metadata.js
# Validate anchors
npm run validate
# Build website
cd website
npm run build- Product Requirements (PRD) - Project vision and user stories
- Architecture (arc42) - Complete technical architecture
- Specifications - Use cases, API spec, acceptance criteria
- ADRs - Architecture Decision Records with Pugh matrices
- Project Status - Current implementation status
Built with:
- Vite - Fast, modern build tool
- Apache ECharts - Interactive treemap visualization
- Tailwind CSS - Utility-first styling
- AsciiDoc - Content format with metadata attributes
- GitHub Pages - Hosting and deployment
See ADRs for detailed decision rationale with Pugh matrix analysis.
- MECE analysis of categories
- Role mapping for all anchors
- Split README into individual files
- Metadata extraction scripts
- Interactive treemap visualization
- Role-based filtering
- Real-time search
- i18n (EN/DE)
- Dark/Light theme
- 60 passing tests
- GitHub Actions workflow
- Issue templates
- Contributing guide
- Documentation updates
- GitHub Copilot validation workflow
- Advanced search features
- Anchor detail view
- Category visualization improvements
- 46 Semantic Anchors
- 12 Professional Roles
- 11 MECE-compliant Categories
- 60 Passing Tests
- 2 Languages (EN/DE UI)
This project is licensed under the MIT License.
- Architecture & Design: Claude Sonnet 4.5 (AI-assisted)
- Maintainer: @rdmueller
- Community: All contributors proposing and improving semantic anchors
- Website: https://llm-coding.github.io/Semantic-Anchors/
- Issues: https://github.com/LLM-Coding/Semantic-Anchors/issues
- Discussions: https://github.com/LLM-Coding/Semantic-Anchors/discussions
- Contributing: CONTRIBUTING.md
Star History