Arc42 Documentation logo

Arc42 Documentation

Organization
LLM-Coding
arc42-documentation

Author an arc42 architecture document with the project's cross-section traceability rules. Use when producing or extending an arc42 document — it carries the procedure the "Architecture Documentation" contract deliberately leaves out: scaffolding the with-help template, the five traceability rules arc42 does not enforce, the Chapter 11 Risks-vs-Technical-Debt structure, the ADR-to-risk-ID wiring, the Chapter 1.2-vs-10 quality-goal marking, and the six-part Quality Attribute Scenario form. The contract pins the vocabulary (arc42, C4/PlantUML, Nygard ADRs, Pugh); this skill is the how-to.

Overview

PublisherLLM-Coding
RepositorySemantic-Anchors
Skill namearc42-documentation
Stars
521
Forks
45
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by LLM-Coding on GitHub. Read the source before you install it.

Installation

Install the Arc42 Documentation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/LLM-Coding/Semantic-Anchors/tree/main/plugins/semantic-anchors/skills/arc42-documentation
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/LLM-Coding/Semantic-Anchors.git /tmp/Semantic-Anchors
mkdir -p .claude/skills
cp -r /tmp/Semantic-Anchors/plugins/semantic-anchors/skills/arc42-documentation .claude/skills/arc42-documentation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Arc42 Documentation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Arc42 Documentation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Arc42 Documentation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

arc42 Documentation Authoring

Produce an arc42 architecture document that holds together across sections — not twelve chapters written in isolation.

When to use this skill

Use it when you are creating a new arc42 document, filling empty chapters, or auditing an existing one against the project's rules. The architecture-documentation contract names what the project means by architecture documentation (arc42; C4 via PlantUML; Nygard ADRs with a 3-point Pugh matrix; six-part Quality Attribute Scenarios). This skill is the how — the procedure and the cross-section rules arc42's own templates do not enforce. Load it on demand; it is not always-on.

If you are recovering documentation from existing code rather than authoring it forward, use the socratic-code-theory-recovery skill instead — its Phase 2 synthesizes an arc42 document and applies the same rules defined here.

Step 1 — Scaffold, do not restate

Scaffold the arc42 "with-help" template into the project's src/docs/ via docToolchain downloadTemplate. Each chapter's help text is its own structural spec; the process fills the help text and then replaces it. Do not paste a chapter skeleton from memory — let the template carry the structure so it stays current with arc42.

Step 2 — Diagrams

Every context, building-block, and runtime chapter carries at least one diagram. Diagrams are PlantUML, not Mermaid. Building blocks use C4 via PlantUML's bundled C4-PlantUML standard library — the !include <C4/...> stdlib form (angle brackets), never the remote https:// URL and never a vendored file copy. Diagrams are concrete components, not generic boxes.

Step 3 — Decisions (ADRs)

Decisions are ADRs in Nygard format with a 3-point Pugh matrix (-1 / 0 / +1).

  • When the rationale is unconfirmed, set ADR Status to "Accepted (inferred)" and mark Pugh cells that need team judgement with ? rather than guessing a number.
  • Each ADR's Consequences name the risks the decision creates, referencing the Chapter 11 risk IDs (R-NNN). A decision that creates a risk not yet in Chapter 11 either adds it there or records the consequence as explicitly accepted without a tracked risk.
  • Conversely, every Chapter 8 crosscutting concept back-references the ADR that decided it.

Chapter 9 carries an in-document ADR index (ADR | Title | Status) even when the ADRs live in a separate register.

Step 4 — Cross-section traceability (the five rules)

arc42 templates do not enforce these, so this skill does. Check all five before calling a document done:

  1. Every Chapter 1.2 quality goal maps to a named approach in Chapter 4.
  2. The external systems in Chapter 3 (context) and the Chapter 5 Level-1 building-block view are the same set — one system boundary in both.
  3. Every Chapter 5 building block appears in at least one Chapter 6 runtime scenario; Chapter 6 includes at least one error/recovery scenario, not only the happy path.
  4. Chapter 9 carries the in-document ADR index (see Step 3).
  5. Each Chapter 5 building block states responsibility, interface, and source location.

Step 5 — Quality goals: Chapter 1.2 vs Chapter 10

Chapter 1.2 lists only the top 3-5 quality goals — the ones that drive architecture decisions. Chapter 10 may elaborate further characteristics; that is correct arc42, not a defect.

  • The Chapter 10 quality tree marks each characteristic as either concretising a Chapter 1.2 top goal or as a derived quality requirement.
  • Each Chapter 10 scenario cross-links back to the Chapter 1.2 goal it concretises (or is marked "derived").
  • Each Chapter 10 scenario is written in the six-part Quality Attribute Scenario form: Source, Stimulus, Artifact, Environment, Response, Response Measure. The Response Measure carries a literal figure, so the requirement is testable rather than an adjective.

Step 6 — Chapter 11: Risks and Technical Debt are two subsections

Separate them.

  • Each Risk carries probability, impact, a derived priority, and a mitigation/action cross-referencing an existing mitigation in Chapter 8 or a quality scenario where one exists. Order risks by priority.
  • Each Technical Debt item references the specific Chapter 5 building block it burdens.

Definition of done

A document is done when all five traceability rules in Step 4 hold, every Chapter 1.2 goal has a Chapter 4 approach and at least one six-part Chapter 10 scenario, every ADR's consequences reference an R-NNN (or an explicitly accepted no-risk note), and Chapter 11 separates ordered Risks from building-block-attributed Technical Debt. See references/chapter-checklist.md for a chapter-by-chapter pass.

Further reading

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Arc42 Documentation AI skill do?

Author an arc42 architecture document with the project's cross-section traceability rules. Use when producing or extending an arc42 document — it carries the procedure the "Architecture Documentation" contract deliberately leaves out: scaffolding the with-help template, the five traceability rules arc42 does not enforce, the Chapter 11 Risks-vs-Technical-Debt structure, the ADR-to-risk-ID wiring, the Chapter 1.2-vs-10 quality-goal marking, and the six-part Quality Attribute Scenario form. The contract pins the vocabulary (arc42, C4/PlantUML, Nygard ADRs, Pugh); this skill is the how-to.

Why use Arc42 Documentation on TypingMind?

Because you install it once and use it with any model. Arc42 Documentation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Arc42 Documentation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/LLM-Coding/Semantic-Anchors/tree/main/plugins/semantic-anchors/skills/arc42-documentation. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Arc42 Documentation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Arc42 Documentation?

As many as you like. As long as a model supports skills, you can use Arc42 Documentation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Arc42 Documentation AI skill free?

Yes. It is published on GitHub by LLM-Coding under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇