Skip to content
Agentmart
Submit a tool

architecture-docs

Generate or update architecture documentation from repositories, product docs, infrastructure files, and code.

Skill by shrivatsas

IndexedMIT★ 2
Write a review

Chalk Labs

Need help deploying architecture-docs?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/shrivatsas-architecture-docs

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Generate or update architecture documentation from repositories, product docs, infrastructure files, and code. Use when asked for high-level architecture, C4 diagrams, system context, container/component/deployment views, arc42 documentation, Excalidraw-ready architecture, Mermaid architecture diagrams, architecture decisions, runtime views, quality attributes, risks, or an architecture package synthesized from existing docs and source.

Use cases: frontend, devops

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/architecture-docs

What's inside

Skill name
architecture-docs
Description
Generate or update architecture documentation from repositories, product docs, infrastructure files, and code. Use when asked for high-level architecture, C4 diagrams, system context, container/component/deployment views, arc42 documentation, Excalidraw-ready architecture, Mermaid architecture diagrams, architecture decisions, runtime views, quality attributes, risks, or an architecture package synthesized from existing docs and source.
License
MIT
Metadata
short-description: Generate C4 and arc42 architecture docs
Instructions
57 lines in SKILL.md · view on GitHub

Files (5)

  • SKILL.md
  • openai.yaml · agents/
  • arc42.md · references/
  • c4.md · references/
  • mermaid-excalidraw.md · references/

SKILL.md (first lines)

# Architecture Docs

Use this skill to synthesize architecture documentation from a codebase and its docs. It supports:

- **C4**: diagram-first context, container, component, and deployment views.
- **arc42**: narrative architecture documentation with goals, constraints, decisions, runtime flows, quality requirements, risks, and glossary.
- **Combined package**: C4 diagrams referenced from or embedded into arc42.

## Workflow

1. **Discover source material**
   - Search before reading deeply: use `rg --files`, then targeted `rg` for product names, architecture, infra, auth, integrations, deployment, SLOs, metrics, permissions, and feature docs.
   - Read primary local sources first: product README, workspace docs, backend/frontend READMEs, service docs, infra/Terraform, API routers, package files, and existing architecture docs.
   - For large repos, summarize by domain instead of reading every source file.

2. **Establish the boundary**
   - Identify users/actors, in-scope system, adjacent products, external systems, data stores, identity providers, async workers, observability, and deployment platform.
   - Separate documented fact from inference. Explicitly mark uncertain deployment/runtime assumptions.

3. **Select output mode**
   - If the user asks for diagrams, Excalidraw, C4, or high-level architecture: produce C4.
   - If the user asks for arc42, architecture docs, decisions, risks, or onboarding/reference material: produce arc42.
   - If the user asks for a complete architecture set/package: produce both and cross-reference them.

4. **Create artifacts**
   - Prefer Markdown files in an appropriate docs/architecture location, unless the user names a path.
   - For C4, include Mermaid `flowchart` blocks that can be pasted into Excalidraw.
   - For arc42, reference C4 diagrams rather than duplicating every diagram inline unless the user requests a single self-contained file.

5. **Review before final**
   - Check diagrams for basic Mermaid syntax hazards.
   - Check that claims are traceable to source docs or clearly labeled as assumptions.
   - Include unresolved questions or doc reconciliation items when sources disagree.

## Reference Files

Read only the reference needed for the requested output:

- `references/c4.md`: C4 output guidance and diagram checklist.
- `references/arc42.md`: arc42 section structure and content checklist.
- `references/mermaid-excalidraw.md`: Mermaid conventions for Excalidraw import.

## Output Standards

- Keep diagrams coarse enough for architecture discussion; avoid mirroring every class, table, endpoint, or file.
- Use business/domain labels, then add technology in secondary text.
- Include the operationally important things: auth, permissions, data stores, async work, external dependencies, observability, and deployment uncertainty.
- For healthcare, financial, legal, or other sensitive domains, call out privacy, auditability, access control, data retention, and external data handling.
- Do not treat generated architecture as authoritative if the repo docs conflict. Surface the conflict directly.

## Suggested Filenames

- C4: `architecture-c4.md`, `<product>-c4-architecture.md`, or `<product>-c4-architecture-excalidraw.md`
- arc42: `architecture-arc42.md` or `<product>-arc42-architecture.md`
- Combined index: `architecture.md`

From shrivatsas/dev-setup, MIT.

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Jun 1, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from shrivatsas

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get architecture-docs running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying architecture-docs?

CallGet help
Cite this page

architecture-docs skill. Agent Mart. https://agentmart.dev/skills/shrivatsas-architecture-docs (last updated 2026-10-24)