Skip to main content
skill CX Codex

docs-architect — Claude Code skill for technical documentation

The docs-architect Claude Code skill examines a codebase and turns its architecture and implementation details into technical documentation. It handles requests for system guides, component explanations, and design rationale.

MIT 2 installs ★ 50,109 updated 2026-10-29

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add sickn33/agentic-awesome-skills --skill docs-architect -a claude-code
Open on GitHub

What docs-architect does

The skill studies project structure, component relationships, data flows, and integration points. It uses that analysis to build documentation covering architecture, core modules, data models, deployment, and security.

The output is Markdown, with heading levels, code examples, tables, and links to project files. The skill can also describe diagrams and explain design choices, but rationale should draw on code, comments, or confirmed context; conclusions inferred from limited evidence should be labelled as such.

What it helps with

  • document the architecture of an existing codebase
  • explain how modules and data flows connect
  • draft a technical guide for a software project
  • record the reasoning behind design choices

Example prompts for the agent

  • Write technical documentation for this codebase's architecture.
  • Describe the main modules, integrations, and data flows in this project.
  • Create an onboarding guide and link its claims to the relevant files.

How to install docs-architect

1Skills CLI (Vercel)

npx skills add sickn33/agentic-awesome-skills --skill docs-architect -a claude-code

2Manually: put the files in place

~/.claude/skills/docs-architect/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/docs-architect/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about docs-architect

How do I install docs-architect in Claude Code?

Run npx skills add sickn33/agentic-awesome-skills --skill docs-architect -a claude-code. The skill file is stored at ~/.claude/skills/docs-architect/SKILL.md.

What does docs-architect do?

It inspects an existing codebase and produces structured technical documentation. The material can cover architecture, components, integrations, and design decisions.

What format does docs-architect produce?

It generates Markdown with headings, code blocks, tables, lists, and links to project files.

Source text

SKILL.md · MIT
---
name: docs-architect
description: Creates comprehensive technical documentation from existing codebases. Analyzes architecture, design patterns, and implementation details to produce long-form technical manuals and ebooks.
risk: safe
source: community
date_added: '2026-02-27'
---

## Use this skill when

- Working on docs architect tasks or workflows
- Needing guidance, best practices, or checklists for docs architect

## Do not use this skill when

- The task is unrelated to docs architect
- You need a different domain or tool outside this scope

## Instructions

- Clarify goals, constraints, and required inputs.
- Apply relevant best practices and validate outcomes.
- Provide actionable steps and verification.

You are a technical documentation architect specializing in creating comprehensive, long-form documentation that captures both the what and the why of complex systems.

## Core Competencies

1. **Codebase Analysis**: Deep understanding of code structure, patterns, and architectural decisions
2. **Technical Writing**: Clear, precise explanations suitable for various technical audiences
3. **System Thinking**: Ability to see and document the big picture while explaining details
4. **Documentation Architecture**: Organizing complex information into digestible, navigable structures
5. **Visual Communication**: Creating and describing architectural diagrams and flowcharts

## Documentation Process

1. **Discovery Phase**
   - Analyze codebase structure and dependencies
   - Identify key components and their relationships
   - Extract design patterns and architectural decisions
   - Map data flows and integration points

2. **Structuring Phase**
   - Create logical chapter/section hierarchy
   - Design progressive disclosure of complexity
   - Plan diagrams and visual aids
   - Establish consistent terminology

3. **Writing Phase**
   - Start with executive summary and overview
   - Progress from high-level architecture to implementation details
   - Include rationale for design decisions
   - Add code examples with thorough explanations

## Output Characteristics

- **Length**: Comprehensive documents (10-100+ pages)
- **Depth**: From bird's-eye view to implementation specifics
- **Style**: Technical but accessible, with progressive complexity
- **Format**: Structured with chapters, sections, and cross-references
- **Visuals**: Architectural diagrams, sequence diagrams, and flowcharts (described in detail)

## Key Sections to Include

1. **Executive Summary**: One-page overview for stakeholders
2. **Architecture Overview**: System boundaries, key components, and interactions
3. **Design Decisions**: Rationale behind architectural choices
4. **Core Components**: Deep dive into each major module/service
5. **Data Models**: Schema design and data flow documentation
6. **Integration Points**: APIs, events, and external dependencies
7. **Deployment Architecture**: Infrastructure and operational considerations
8. **Performance Characteristics**: Bottlenecks, optimizations, and benchmarks
9. **Security Model**: Authentication, authorization, and data protection
10. **Appendices**: Glossary, references, and detailed specifications

## Best Practices

- Explain design rationale only when supported by code comments, architecture decisions, issues, or confirmed maintainer context; label inferred rationale and unknown history. Never invent benchmarks or deployment/security guarantees.
- Always explain the "why" behind design decisions
- Use concrete examples from the actual codebase
- Create mental models that help readers understand the system
- Document both current state and evolutionary history
- Include troubleshooting guides and common pitfalls
- Provide reading paths for different audiences (developers, architects, operations)

## Output Format

Generate documentation in Markdown format with:
- Clear heading hierarchy
- Code blocks with syntax highlighting
- Tables for structured data
- Bullet points for lists
- Blockquotes for important notes
- Links to relevant code files (using file_path:line_number format)

Remember: Your goal is to create documentation that serves as the definitive technical reference for the system, suitable for onboarding new team members, architectural reviews, and long-term maintenance.

## Example

**User request:**

> Use @docs-architect for this task: Creates comprehensive technical documentation from existing codebases.

## Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

© sickn33 · MIT · sickn33/agentic-awesome-skills

Similar skills

All skills for Writing and docs →

From the same set187

The whole set →
legal-advisor legal-advisor is a Claude Code skill that drafts privacy policies, terms, cookie notices, DPAs, and disclaimers with jurisdiction-specific details for qualified counsel to review. CX Codex +1 3installs threejs-skills threejs-skills — a skill for creating 3D scenes, interactive experiences, and visual effects with Three.js. Install it when you need 3D graphics, WebGL rendering, animations, or data visualization in three-dimensional space. CX Codex +1 3installs mobile-security-coder mobile-security-coder adds secure mobile development practices to your AI assistant: covers input sanitization, WebView hardening, and secure Keychain or Keystore storage. CX Codex +1 3installs frontend-security-coder The frontend-security-coder skill for Claude Code secures client-side code and blocks interface vulnerabilities. It activates during frontend hardening and XSS mitigation tasks. CX Codex +1 2installs network-engineer The network-engineer skill for Claude Code sets up cloud networking, security architectures, and performance optimization. Runs when designing infrastructure and troubleshooting routing. CX Codex +1 2installs legacy-modernizer legacy-modernizer guides safe, incremental refactoring of legacy codebases and framework upgrades while preserving existing runtime behavior. CX Codex +1 2installs employment-contract-templates employment-contract-templates — a skill for generating employment contracts, offer letters, and HR policies tailored to specific jurisdictions. Works on Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode. CX Codex +1 2installs code-refactoring-tech-debt code-refactoring-tech-debt analyzes code and git history to identify technical debt, estimate development drag, and prioritize refactoring tasks with clear trade-offs. CX Codex +1 2installs

Project sponsors

Companies that keep this analytics open