doc-generation

Generate or update package documentation with strict ordering and README-last rules.

3|Updated Mar 17, 2026
One-click install
npx skills add https://github.com/transreal/claudecode --skill doc-generation-transreal
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: doc-generation
Source: https://github.com/transreal/claudecode/tree/main/Claude%20Directives/skills/doc-generation
Command: npx skills add https://github.com/transreal/claudecode --skill doc-generation-transreal

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill prevents documentation drift and incomplete updates by enforcing a strict, LLM-optimized generation process for claudecode package docs, including correct ordering, resumption after limits, and safe README handling.

Core Features & Use Cases

  • Strict doc queue ordering: Ensures setup.md, user_manual.md, api.md, and examples/example.md are updated first, with README.md always generated last.
  • README correctness and compliance: Guarantees the required README structure and enforces that acknowledgments, disclaimers, and licenses appear only at the end in the correct order.
  • Resumable generation under limits: Supports continuation behavior when generation hits token/usage limits, including partial vs full regeneration rules.
  • API-first documentation references: Treats api.md as the single source of truth so Claude generates code and docs based on authoritative function signatures and options.

Quick Start

Use the doc-generation skill to update package documentation by instructing an AI to run ClaudeCreateDocumentation or ClaudeUpdateDocumentation with the appropriate target files and update mode.

Frequently Asked Questions about doc-generation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I prevent documentation drift when updating package docs?

To prevent documentation drift, enforce strict doc queue ordering and treat api.md as the single source of truth. This ensures setup.md, user_manual.md, api.md, and examples are updated first, with README.md always generated last.

How do I resume documentation generation after hitting token limits?

Documentation generation supports resumption after hitting token limits by applying partial versus full regeneration rules. This continuation behavior safely resumes the workflow without losing previously generated content or breaking the strict file ordering.

What is the best way to update README files safely during doc generation?

Safe README updates require constrained integration using only overview-level changes, generating README.md last in the doc queue. This enforces correct structure and ensures acknowledgments, disclaimers, and licenses appear only at the end in the proper order.

How do diff-based updates work for API reference documentation?

Diff-based updates maintain stable documentation structures by routing content to the correct files and applying changes only where needed. Using api.md as the authoritative source, this approach generates code and docs based on validated function signatures and options.

Can I use automated documentation generation for multiple markdown files?

Automated documentation generation supports multiple markdown files by enforcing a strict processing queue. It routes content to setup.md, user_manual.md, api.md, examples/example.md, and README.md sequentially, ensuring correct ordering and compliance across the package documentation.