Documentation Orchestration Patterns

VerifiedSafe

Orchestrates parallel generation of technical documentation (APIs, code, READMEs, architecture, user guides) by coordinating specialized agents. Helps produce comprehensive, consistent documentation quickly across large codebases.

Sby Skills Guide Bot
DocumentationAdvanced
6/2/2026
Claude CodeCursorWindsurfCopilotCodex
#documentation#orchestration#api-documentation#code-documentation#architecture-documentation

Recommended for

Automated summary

This skill automates the generation of various documentation types (API, code, README, architecture) by orchestrating parallel agent tasks for efficient and comprehensive documentation.

Strengths

  • Parallel documentation generation
  • Covers multiple documentation styles (API, code, README, architecture)
  • Ensures consistency across documents
  • Reduces manual effort significantly

Limitations

  • Requires a clear project structure
  • May need manual review for accuracy
  • Complex to set up for small projects
When to use it

Use this skill when you need to generate or update comprehensive documentation for a large project with multiple components.

When not to use it

Do not use it for very small projects or when documentation requirements are minimal and direct writing is faster.

Security analysis

Safe
Quality score90/100

The skill describes documentation orchestration patterns and includes example shell commands and Python code for parallel task management. No destructive, obfuscated, or exfiltrating actions are present. The commands use a specific CLI tool (cc-mirror) for task management, which does not pose an inherent security risk.

No concerns found

How this analysis is made

Examples

Document REST API Endpoints
Document all REST API endpoints
Document Utils Module
Add documentation to the utils module
Create a README
Create a README for this project

Documentation Orchestration Patterns

┌─────────────────────────────────────────────────────────────┐
│                                                             │
│   Good documentation is parallel-friendly.                  │
│   Multiple sections, generated simultaneously.              │
│                                                             │
└─────────────────────────────────────────────────────────────┘

Load when: API documentation, code documentation, README generation, architecture docs, user guides Common patterns: Endpoint Discovery, Batch JSDoc Generation, Comprehensive README

Table of Contents

  1. API Documentation
  2. Code Documentation
  3. README Generation
  4. Architecture Documentation
  5. User Guides

API Documentation

Pattern: Endpoint Discovery and Documentation

User Request: "Document all REST API endpoints"

Phase 1: EXPLORE
└─ Explore agent: Find all route definitions

Phase 2: FAN-OUT (Parallel documentation by domain)
├─ Agent A: Document auth endpoints
├─ Agent B: Document user endpoints
├─ Agent C: Document product endpoints
└─ Agent D: Document order endpoints

Phase 3: REDUCE
└─ General-purpose agent: Compile into unified OpenAPI/Swagger spec

Pattern: Interactive Documentation

Phase 1: PIPELINE (Foundation)
├─ Explore agent: Extract all endpoints with types
└─ General-purpose agent: Generate OpenAPI spec

Phase 2: FAN-OUT (Enhancement)
├─ Agent A: Add example requests
├─ Agent B: Add example responses
└─ Agent C: Add authentication examples

Phase 3: PIPELINE
└─ General-purpose agent: Setup Swagger UI / Redoc

Code Documentation

Pattern: Batch JSDoc/Docstring Generation

User Request: "Add documentation to the utils module"

Phase 1: EXPLORE
└─ Explore agent: Find all undocumented functions

Phase 2: MAP (Parallel documentation)
├─ Agent A: Document file1.ts functions
├─ Agent B: Document file2.ts functions
└─ Agent C: Document file3.ts functions

Phase 3: PIPELINE
└─ General-purpose agent: Verify consistency, generate type docs

Pattern: Module Overview Generation

Phase 1: EXPLORE
└─ Explore agent: Map module structure, exports, dependencies

Phase 2: PIPELINE
├─ General-purpose agent: Write module overview
├─ General-purpose agent: Document public API
└─ General-purpose agent: Add usage examples

README Generation

Pattern: Comprehensive README

User Request: "Create a README for this project"

Phase 1: FAN-OUT (Parallel information gathering)
├─ Explore agent: Project structure and technologies
├─ Explore agent: Build and run scripts (package.json, Makefile)
├─ Explore agent: Environment variables and config
├─ Explore agent: Test setup and commands
└─ Explore agent: Existing docs and comments

Phase 2: REDUCE
└─ General-purpose agent: Synthesize into structured README

Sections:
- Overview and purpose
- Quick start
- Installation
- Configuration
- Usage examples
- Development setup
- Testing
- Contributing

Architecture Documentation

Pattern: C4 Model Documentation

User Request: "Document the system architecture"

Phase 1: FAN-OUT (Parallel level documentation)
├─ Agent A: Context diagram (system + external actors)
├─ Agent B: Container diagram (applications, data stores)
├─ Agent C: Component diagram (internal components)
└─ Agent D: Code diagram (critical classes/modules)

Phase 2: REDUCE
└─ General-purpose agent: Compile into architecture doc with diagrams

Pattern: Decision Record Generation

Phase 1: EXPLORE
└─ Explore agent: Find architectural patterns in code

Phase 2: FAN-OUT
├─ Agent A: Document decision 1 (why this database?)
├─ Agent B: Document decision 2 (why this framework?)
└─ Agent C: Document decision 3 (why this structure?)

Each ADR includes:
- Context
- Decision
- Consequences
- Alternatives considered

User Guides

Pattern: Feature-Based Guides

User Request: "Write user documentation for the dashboard"

Phase 1: EXPLORE
└─ Explore agent: Map dashboard features and capabilities

Phase 2: FAN-OUT (Parallel feature guides)
├─ Agent A: Guide for feature 1 (with screenshots)
├─ Agent B: Guide for feature 2
├─ Agent C: Guide for feature 3
└─ Agent D: Troubleshooting guide

Phase 3: REDUCE
└─ General-purpose agent: Compile into user manual with TOC

Task Management for Documentation

Structure documentation work with parallel generation:

# Create documentation tasks
npx cc-mirror tasks create --subject "Audit existing docs" --description "Review current documentation state..."
npx cc-mirror tasks create --subject "Document API endpoints" --description "REST API documentation..."
npx cc-mirror tasks create --subject "Document components" --description "React component docs..."
npx cc-mirror tasks create --subject "Document utilities" --description "Helper function docs..."
npx cc-mirror tasks create --subject "Review consistency" --description "Ensure consistent style..."
npx cc-mirror tasks create --subject "Verify examples" --description "Test all code examples..."

# Parallel doc generation after audit
npx cc-mirror tasks update 2 --add-blocked-by 1
npx cc-mirror tasks update 3 --add-blocked-by 1
npx cc-mirror tasks update 4 --add-blocked-by 1
npx cc-mirror tasks update 5 --add-blocked-by 2,3,4
npx cc-mirror tasks update 6 --add-blocked-by 5
# Spawn parallel documentation agents (sonnet for well-structured work)
Task(subagent_type="general-purpose", prompt="Task 2: Document API endpoints...",
     model="sonnet", run_in_background=True)
Task(subagent_type="general-purpose", prompt="Task 3: Document components...",
     model="sonnet", run_in_background=True)
Task(subagent_type="general-purpose", prompt="Task 4: Document utilities...",
     model="sonnet", run_in_background=True)

Output Formats

| Doc Type | Format | Tool | | ------------ | ------------------- | ---------------------- | | API docs | OpenAPI/Swagger | YAML/JSON | | Code docs | JSDoc/docstrings | Inline | | READMEs | Markdown | .md files | | Architecture | Markdown + diagrams | Mermaid/PlantUML | | User guides | Markdown/HTML | Static site generators |


─── ◈ Documentation ─────────────────────

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/documentation-orchestration-patterns-mm5t8ckb/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/documentation-orchestration-patterns-mm5t8ckb' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/documentation-orchestration-patterns-mm5t8ckb/download' --output '.skill-downloads/documentation-orchestration-patterns-mm5t8ckb/SKILL.md.part' && mv '.skill-downloads/documentation-orchestration-patterns-mm5t8ckb/SKILL.md.part' '.skill-downloads/documentation-orchestration-patterns-mm5t8ckb/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/documentation-orchestration-patterns-mm5t8ckb/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills