Skip to main content
skill CX Codex

document · rsmdt — Claude Code skill: what it does, how to install

Coordinates parallel documentation generation for source code, APIs, and project architecture.

MIT ★ 587 updated 2026-10-26

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add rsmdt/the-startup
/plugin install start@the-startup
Open on GitHub

What document does

The skill operates strictly as an orchestrator and delegates writing to specialist subagents instead of authoring content directly. Based on the target parameter (api, readme, audit, capture, or a directory path), it assigns perspectives and scans for stale content. It prioritizes updating existing markdown files over generating duplicate files.

Execution runs in one of three modes: Standard for parallel fire-and-forget agents, Agent Team with shared task tracking, or Dynamic Workflow executing an inline script. Knowledge capture relies on predefined templates inside templates/ covering technical patterns, external integrations, and business rules.

The orchestrator requires the supporting files in reference/ and templates/ to function, failing if these guides are missing.

What it helps with

  • audit existing repository docs for gaps and stale information
  • orchestrate parallel subagents to generate API documentation
  • update project README files with explicit file paths and line links
  • capture architecture patterns using standardized templates

Example prompts for the agent

  • /document api
  • /document src/controllers
  • /document audit

How to install document

1Plugin marketplace

/plugin marketplace add rsmdt/the-startup
/plugin install start@the-startup

This installs the whole start plugin with all its skills

2Skills CLI (Vercel)

npx skills add rsmdt/the-startup --skill document -a claude-code

3Manually: put the files in place

~/.claude/skills/document/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/document/

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

Questions about document

How to install document in Claude Code?

Run /plugin marketplace add rsmdt/the-startup in Claude Code, then run /plugin install start@the-startup to complete the installation.

What does the document skill do?

It orchestrates documentation tasks by mapping targets to specialist subagents, checking existing files, and synthesizing the resulting changes into a unified format.

When does it switch to Agent Team mode?

It suggests Agent Team whenever the target is set to audit or all, when three or more perspectives run at once, or when processing large codebases.

Source text

SKILL.md · MIT
---
name: document
description: Generate and maintain documentation for code, APIs, and project components
user-invocable: true
argument-hint: "file/directory path, 'api' for API docs, 'readme' for README, or 'audit' for doc audit"
---

## Persona

Act as a documentation orchestrator that coordinates parallel documentation generation across multiple perspectives.

**Documentation Target**: $ARGUMENTS

## Interface

DocChange {
  file: string             // path to documented file
  action: string           // Created | Updated | Added JSDoc
  coverage: string         // what was documented (e.g., "15 functions", "8 endpoints")
}

State {
  target = $ARGUMENTS
  perspectives = []        // from reference/perspectives.md
  mode: Standard | Agent Team | Dynamic Workflow
  existingDocs = []
  changes: DocChange[]
}

## Constraints

**Always:**
- Launch applicable documentation perspectives simultaneously in a single response.
- Check for existing documentation first — update rather than duplicate.
- Match project documentation style and conventions.
- Link to actual file paths and line numbers.

**Never:**
- Write documentation yourself — always delegate to specialist agents.

## Reference Materials

- reference/perspectives.md — documentation perspectives, target mapping, documentation standards
- reference/output-format.md — next-step options, coverage guidelines
- reference/knowledge-capture.md — naming conventions, update-vs-create matrix, cross-referencing
- examples/output-example.md — concrete example of expected output format

Templates in `templates/` for knowledge capture:
- `pattern-template.md` — Technical patterns
- `interface-template.md` — External integrations
- `domain-template.md` — Business rules

## Workflow

### 1. Analyze Scope

Read reference/perspectives.md. Select perspectives based on target:

match (target) {
  file | directory => [Code]
  "api"            => [API, Code]
  "readme"         => [README]
  "audit"          => [Audit]
  "capture"        => [Capture]
  empty | "all"    => all applicable perspectives
}

Scan target for existing documentation. Identify gaps and stale docs.

Ask the user to choose: Generate all | Focus on gaps | Update stale | Show analysis

### 2. Select Mode

Ask the user to choose:
  Standard (default) — parallel fire-and-forget subagents
  Agent Team — persistent teammates with shared task list and coordination
  Dynamic Workflow — one inline workflow script fans out the documenters and collects their changes

Recommend Agent Team when target is "all" or "audit", perspectives >= 3, or large codebase.
Recommend Dynamic Workflow instead when those thresholds apply but the perspectives are independent and need no coordination between documenters.

### 3. Launch Documentation

match (mode) {
  Standard => launch parallel subagents per applicable perspectives
  Agent Team => create team, spawn one documenter per perspective, assign tasks
  Dynamic Workflow => run one dynamic workflow: one documenter agent per perspective in parallel, returning every DocChange
}

For Dynamic Workflow, these instructions are the opt-in: call the Workflow tool directly with an inline script. Do not load the workflow-authoring reference or assemble the script through shell commands first — runs that detour through either stall before launching. Choose `model` and `effort` per stage from what the stage does. Mechanical stages — running a command, gathering or quoting sources, mapping text into a fixed schema — can run on a smaller, faster model at lower effort. Analysis, writing, and judging another agent's work need the strongest model. A judging stage never runs on a weaker model than the stage it judges. When unsure, omit `model` so the stage inherits the session model.

For the Capture perspective: use templates/ for consistent formatting and Read reference/knowledge-capture.md for categorization protocol.

### 4. Synthesize Results

Process results:
1. Merge with existing docs — update, don't duplicate.
2. Check consistency for style alignment.
3. Resolve conflicts between perspectives.
4. Apply changes.

### 5. Present Summary

Read reference/output-format.md and format summary accordingly.

Ask the user to choose: Address remaining gaps | Review stale docs | Done

© Rudolf S. · MIT · rsmdt/the-startup

Similar skills

All skills for Writing and docs →

document by other authors comes first.

document jsmastery-pro document is a Claude Code skill that drafts PR descriptions, changelog entries, release notes, and postmortems from project changes. Choose a document type in the command or let the agent ask. CX Codex +1 5,100installs document archcore-ai This Claude Code skill records decisions, documents existing code, and files completed research material. It activates for requests to draft an RFC, write a guide, or capture how a system currently works. CX Codex +1 ★ 78repo stars document serpro69 Updates project documentation and architectural decisions after delivering a feature or bug fix following profile guidelines. CX Codex +1 ★ 155repo stars document awrshift document turns a change into prose a human reads — a PR body, changelog entry, release note or postmortem — and files it in the right place. Drafts come only from git diff and git log. CX Codex +1 ★ 33repo stars code-documentation-analyzer Jeremy Longshore Auto-activating skill for auditing code documentation: API references, user guides, architecture docs. Triggers on phrases like "code documentation analyzer" or "code analyzer". CX Codex +1 1installs project-docs jezweb project-docs scans your codebase to generate or refresh ARCHITECTURE.md, API_ENDPOINTS.md, and DATABASE_SCHEMA.md. It helps when onboarding new contributors or updating stale project documentation. CX Codex +1 1,300installs technical-writer curiositech technical-writer structures developer docs, API references, ADRs, and runbooks using the Diátaxis framework with working code examples. CX Codex +1 221installs doc-forge rohitg00 doc-forge — a Claude Code plugin that generates code documentation, API docs, and maintains README files. The agent invokes it when you work on project documentation. ★ 2,858repo stars kb-document stjbrown kb-document is a Claude Code skill that builds and updates repository documentation in an OKF knowledge bundle, mapping architecture and code boundaries without editing source files. CX Codex +1 ★ 45repo stars GEML — a plain-text document format built to be edited in place, one section at a time geml-spec GEML — a plain-text document format built to be edited in place, one section at a time is an MCP server for Claude Code that reads and edits one named section instead of the whole file. CX Codex +1 ★ 31repo stars

From the same set50

The whole set →
feature-prioritization feature-prioritization applies RICE, MoSCoW, Kano, and value-effort frameworks to rank backlog items. Turns feature debates into structured decisions with documented rationale. CX Codex +1 ★ 587repo stars review-security review-security is a Claude Code subagent that checks code and dependency changes for vulnerabilities and supply-chain risks. It is automatically invoked for PRs affecting security-sensitive flows or dependency manifests. CX Codex ★ 587repo stars platform-operations This skill turns release and monitoring requirements into a platform operations plan. Use it when designing CI/CD workflows, production observability, or release safeguards. CX Codex +1 ★ 587repo stars build-platform build-platform is a Claude Code subagent that orchestrates delivery platforms with containers, infrastructure as code, and deployment pipelines. It supports reproducible environments and rollback-safe releases. CX Codex ★ 587repo stars api-contract-design api-contract-design is a Claude Code skill for designing and checking REST, GraphQL, or hybrid API contracts before implementation. CX Codex +1 ★ 587repo stars review-robustness review-robustness flags fragile code before merge: abstraction layers nothing needs yet, and shared state handled carelessly in async flows. Useful on PR review and for bugs that surface only under load. CX Codex ★ 587repo stars performance-analysis performance-analysis applies systematic profiling to find bottlenecks across CPU, memory, and database layers. It enforces measuring baselines before proposing optimizations. CX Codex +1 ★ 587repo stars specify-meta specify-meta is a Claude Code skill that creates specification folders and tracks requirements, solution, and plan stages. It records approvals and decisions for a task. CX Codex +1 ★ 587repo stars

Project sponsors

Companies that keep this analytics open