doc-gen
Generate and maintain documentation with drift detection
Best for CI pipelinesWorks with GitHubLow risk
⌘source
- author
@ruvnet- repo
- ruvnet/ruflo
- language
- TypeScript
★46kstars
5.1kforks
May 5, 2026
✦overview.md
Key Features
- ·Generate API docs via MCP worker dispatch
- ·Continuous doc maintenance with CronCreate
- ·Drift detection by comparing code vs docs
- ·Scoped generation: API or full project
- ·Store doc patterns in memory store
Use Cases
- →Automatically regenerate API documentation on code changes
- →Set up periodic documentation updates every 2 hours
- →Detect inconsistencies between code and existing docs
- →Generate full project documentation in one command
Best for
- ✓CI pipelines
- ✓projects with evolving APIs
- ✓teams using Claude Flow
Not ideal for
- !static documentation sites
- !projects without MCP infrastructure
FAQs
name
doc-gen
description
Generate and maintain documentation with drift detection
argument-hint:[--target PATH]
allowed-tools:Bash(npx *) mcp__claude-flow__hooks_worker-dispatch mcp__claude-flow__memory_store CronCreate Read Write
Generate docs via MCP worker dispatch:
mcp__claude-flow__hooks_worker-dispatch({ trigger: "document" })
For continuous doc maintenance via CronCreate:
CronCreate({ schedule: "0 */2 * * *", prompt: "Run document worker" })
Detect drift by comparing current code against existing docs and flagging inconsistencies.
Scoped generation:
- API docs:
npx @claude-flow/cli@latest hooks worker dispatch --trigger document --scope api - Full project:
npx @claude-flow/cli@latest hooks worker dispatch --trigger document --scope full
Store the approach: mcp__claude-flow__memory_store({ key: "doc-pattern", value: "APPROACH", namespace: "patterns" })
$install
1-click copynpx skills add ruvnet/ruflo --skill doc-genSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
4/ 5
very goodClear and well structured, with only minor parts that might need a second read.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
5/ 5
very highHighly actionable with clear, concrete steps that an agent can follow directly.