openclaw-refactor-docs

Refactor OpenClaw documentation pages with source-audited fact preservation and verification.

Updated Jun 19, 2026
One-click install
npx skills add https://github.com/AmirulAndalib/Vilvona-AI --skill openclaw-refactor-docs-amirulandalib
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openclaw-refactor-docs
Source: https://github.com/AmirulAndalib/Vilvona-AI/tree/main/.agents/skills/openclaw-refactor-docs
Command: npx skills add https://github.com/AmirulAndalib/Vilvona-AI --skill openclaw-refactor-docs-amirulandalib

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Rewriting a large documentation page risks silently dropping accurate behavior details like config defaults, precedence rules, and error handling. This Skill provides a structured workflow to refactor OpenClaw docs pages while auditing every existing fact against source code so nothing correct is lost. ## Core Features & Use Cases - Fact Inventory and Audit: Builds a working inventory of config fields, commands, defaults, limits, and troubleshooting details from the old page, then decides to keep, move, or delete each one with source-backed justification. - Page-Type Restructuring: Splits mixed pages into topic, guide, reference, and troubleshooting pages, moving exhaustive contracts to reference pages and symptom-driven material to troubleshooting pages. - Source-of-Truth Verification: Checks behavior-sensitive claims against schemas, CLI implementations, tests, and protocol docs, then runs docs validation commands like docs:check-links and docs:check-mdx. - Use Case: When a plugin docs page has grown into a 2000-line wall mixing setup guides, config tables, and debugging notes, use this Skill to split it into a concise guide plus reference pages without losing any verified behavior facts. ## Quick Start Refactor the OpenClaw docs page at docs/plugins/codex-harness.md, splitting exhaustive config details into a reference page while preserving all verified behavior facts.

Frequently Asked Questions about openclaw-refactor-docs

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

FAQPage Schema
How do I refactor a large documentation page without losing information?

Create a fact inventory of the old page covering config fields, defaults, commands, and troubleshooting details before rewriting. For each fact, decide to keep it, move it to a named destination page, or delete it only when source code proves it obsolete.

How to split a mixed docs page into guide and reference pages?

Classify the page type first, then keep the 80/20 path and decision-making content in the main page. Move exhaustive field tables, defaults, and precedence rules to a reference page, and symptom-driven material to a troubleshooting page, with links from the main page.

Does this skill work with the openclaw-docs skill?

Yes, it builds directly on openclaw-docs and requires reading that skill first for page types, style, examples, and verification guidance. This skill adds the rewrite workflow on top of those standards.

How are documentation claims verified against source code?

Behavior-sensitive claims are checked against the nearest authoritative source: schemas and manifests for config fields, CLI implementations and tests for commands, and runtime source for lifecycle and permission behavior. Existing docs serve only as secondary evidence.

What validation runs after a docs refactor?

Run pnpm docs:list, git diff --check on touched files, oxfmt checks, docs:check-mdx, docs:check-links, and docs:check-i18n-glossary when navigation or labels changed. Commands and examples from the page should also be executed when feasible.