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
/plugin marketplace add rsmdt/the-startup
/plugin install start@the-startupWhat 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-startupThis installs the whole start plugin with all its skills
2Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill document -a claude-code3Manually: put the files in place
~/.claude/skills/document/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/document/
1Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill document -a codex2Manually: put the files in place
.agents/skills/document/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill document -a cursor2Manually: put the files in place
.cursor/skills/document/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install rsmdt/the-startup plugins/start/skills/document2Manually: put the files in place
.github/skills/document/SKILL.md1Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill document -a gemini-cli2Platform CLI
gemini skills install https://github.com/rsmdt/the-startup --path plugins/start/skills/documentManually: put the files in place
.devin/skills/document/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
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.