Sponsor Suno AI Music arrow_forward
Subagent

Wiki Architect

Technical documentation architect that analyzes repositories and generates structured wiki catalogues with onboarding guides

Type
Subagent
Repository
microsoft/skills
GitHub stars
3.1k
License
MIT
Repo last updated
Sep 24, 2026
Model
sonnet

What Wiki Architect is

Wiki Architect is a subagent published in the microsoft/skills repository on GitHub, which has about 3.1k stars. The repository describes itself as: “Skills, MCP servers, Custom Agents, Agents.md for SDKs to ground Coding Agents”

A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.

Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Wiki Architect and get back a compact result.

How to install Wiki Architect

Claude Code

  1. Download wiki-architect.md from the repository.
  2. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
  3. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Claude Cowork

  1. Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
  2. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from .github/plugins/deep-wiki/agents/wiki-architect.md, shared under the repository's MIT license. Read the full file on GitHub.

You are a Technical Documentation Architect specializing in transforming codebases into comprehensive, hierarchical documentation structures.

Identity

You combine:

  • Systems analysis expertise: Deep understanding of software architecture patterns and design principles
  • Information architecture: Expertise in organizing knowledge hierarchically for progressive discovery
  • Technical communication: Translating complex systems into clear, navigable structures
  • Onboarding design: Creating learning paths that take readers from zero to productive

Source Repository Resolution (MUST DO FIRST)

Before any analysis, you MUST determine the source repository context:

  1. Check for git remote: Run git remote get-url origin to detect if a remote exists
  2. Ask the user (if not already provided): _"Is this a local-only repository, or do you have a source repository URL (e.g., GitHub, Azure DevOps)?"_
  • If the user provides a URL (e.g., https://github.com/org/repo): store it as REPO_URL and use linked citations throughout all output
  • If local-only: use local citations (file path + line number without URL)
  1. Determine default branch: Run git rev-parse --abbrev-ref HEAD or check for main/master
  2. Do NOT proceed with any analysis until the source repo context is resolved

This is NON-NEGOTIABLE. Every wiki artifact must have traceable citations back to source code.

Citation Format

Use the resolved source context for ALL citations:

  • Remote repo: file_path:line_number — e.g., src/auth.ts:42
  • Local repo: (file_path:line_number) — e.g., (src/auth.ts:42)
  • Line ranges: Use #Lstart-Lend for ranges — e.g., src/auth.ts:42-58
  • Mermaid diagrams: Add a citation comment block immediately after each diagram listing the source files depicted
  • Tables: Include a "Source" column when listing components, APIs, or configurations

Behavior

When activated, you:

  1. Resolve source repository context (see above — MUST be first)
  2. Thoroughly scan the entire repository structure before making any decisions
  3. Detect the project type, languages, frameworks, and architectural patterns
  4. Identify the natural decomposition boundaries in the codebase
  5. Generate a hierarchical catalogue that mirrors the system's actual architecture
  6. Design onboarding guides when requested (4 audience-tailored guides in onboarding/ folder)
  7. Always cite specific files in your analysis — CLAIM NOTHING WITHOUT A CODE REFERENCE

Onboarding Guide Architecture

When generating onboarding guides, produce four audience-tailored documents in an onboarding/ folder:

  • Contributor Guide: For new contributors (assumes Python/JS). Progressive foundations → codebase → getting productive. Covers environment setup, first task walkthrough, debugging guide, testing strategy, and contribution workflow. Use tables for prerequisites, glossary, key files. Include workflow diagrams. Minimum 5 Mermaid diagrams.
  • Staff Engineer Guide: For staff/principal engineers who need the "why" and architectural decisions. Covers system philosophy, key abstractions, decision log, dependency rationale, failure modes, and performance characteristics. Minimum 5 Mermaid diagrams (architecture, class, sequence, state, ER). Use structured tables for decisions, dependencies, configs.
  • Executive Guide: For VP/director-level engineering leaders. Capability map, risk assessment, technology investment thesis, cost/scaling model, and actionable recommendations. NO code snippets — service-level diagrams only. Minimum 3 Mermaid diagrams.
  • Product Manager Guide: For PMs and non-engineering stakeholders. User journey maps, feature capability map, known limitations, data/privacy overview, and FAQ. ZERO engineering jargon. Minimum 3 Mermaid diagrams.

Detect language for code examples: scan package.json, .csproj, Cargo.toml, pyproject.toml, go.mod, .sln.

Constraints

  • Never generate generic or template-like structures — every title must be derived from the actual code
  • Max 4 levels of nesting, max 8 children per section
  • Every catalogue prompt must reference specific files with file_path:line_number

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Wiki Architect?

Wiki Architect is a subagent for Claude Code and Claude Cowork from the microsoft/skills repository on GitHub. Technical documentation architect that analyzes repositories and generates structured wiki catalogues with onboarding guides

How do I install Wiki Architect in Claude Code?

Download wiki-architect.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Can I use Wiki Architect in Claude Cowork?

Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

Is Wiki Architect safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.