A systematic framework for restructuring project documentation to optimize AI context usage and prevent information drift.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install docs-organization
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install docs-organization using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Documentation Organization?
Documentation Organization provides a structured methodology for managing project documentation in a way that prioritizes both human readability and AI agent efficiency. This skill is a core component of the Openclaw Skills library, focusing on reducing context waste by keeping files like CLAUDE.md concise and instruction-oriented. By implementing a Single Source of Truth, developers can avoid the common pitfall of data drift where identical facts are duplicated and eventually diverge across multiple files.
The framework categorizes documentation into specific directory structures based on the project's scale, from small scripts to complex monorepos. It introduces a metadata system using YAML frontmatter to track document status and target audience, ensuring that the most relevant information is always surfaced to the right user or agent. Integrating this approach through Openclaw Skills streamlines the development lifecycle and enhances the performance of AI-assisted coding tools.
Documentation Organization Use Cases
- Slimming down a bloated CLAUDE.md or AGENTS.md file that exceeds 250 lines to save tokens.
- Restructuring documentation for medium-to-large projects to prevent lost files in flat directories.
- Setting up a professional documentation roadmap for a new project using the Openclaw Skills framework.
- Migrating from chaotic documentation to a structured, audience-based hierarchy.
- Identifying and eliminating duplicated facts that cause informational drift across multiple markdown files.
How Documentation Organization Works
- Perform a root-level noise audit by identifying and relocating non-documentation files like logs, screenshots, and temp files to an archive directory.
- Assess the project size based on source file count, deployment complexity, and operational requirements to choose the right template.
- Apply the appropriate directory structure (Small, Medium, Large, or Monorepo) to create a logical hierarchy for the documentation.
- Extract non-essential reference data, such as API tables or runbooks, from CLAUDE.md into specialized files.
- Implement a Documentation Index in the root instruction file to route both agents and humans to the correct locations efficiently.
- Update all implicit references in configuration files to reflect the new documentation paths and ensure system integrity.
Documentation Organization Setup
To implement these organizational standards using Openclaw Skills, you can begin by auditing your current structure and initializing the recommended directories with these commands:
# Check current file count at the root
ls | wc -l
# Create a standard documentation hierarchy for a large project
mkdir -p docs/{reference,runbooks,guides,product,design,plans,research,decisions,archive}
# Move non-documentation clutter to archive
mkdir -p archive/media
mv *.log archive/
mv *.png archive/media/
Documentation Organization Data Schema & Taxonomy
The skill organizes data into a tiered hierarchy based on audience and content freshness. Use the following schema to classify your documents:
| Directory | Status | Audience | Content Type |
|---|---|---|---|
| reference/ | canonical | agent, operator | API tables, DB schemas, CLI references |
| runbooks/ | canonical | operator | Deployment guides, incident response, troubleshooting |
| guides/ | canonical | user, contributor | How-to instructions and onboarding guides |
| design/ | snapshot | agent, contributor | Feature design specifications (frozen after build) |
| archive/ | archived | none | Superseded docs, old logs, and historical patches |
Each document should include standardized frontmatter to help Openclaw Skills identify its purpose:
---
status: canonical | snapshot | archived
audience: agent | operator | user | contributor
last_reviewed: YYYY-MM-DD
---
Documentation Organization Advanced Features
- Monorepo Workspace support for managing cross-repo documentation concerns at an umbrella level while keeping repo-specific docs localized.
- Anti-pattern detection to proactively identify mirrored facts that lead to documentation drift.
- Context-optimized CLAUDE.md management that enforces a 250-line limit to maximize AI agent reasoning capacity.
- Snapshot-based historical tracking for architecture decision records (ADRs) and research notes within the Openclaw Skills ecosystem.
- Metadata-driven navigation using routing tables to turn instruction files into efficient documentation indexes.
SKILL.md
Loading
Related Openclaw Skills
Kalshi Fed Futures Arb Trader
An automated trading skill that captures alpha by identifying pricing gaps between institutional CME FedWatch futures and Kalshi prediction markets.
Kalshi Fed Data Reaction Trader
An automated trading agent that executes Kalshi Fed rate market positions by analyzing market-implied CPI signals and macro data sensitivity.
Kalshi Fed Speech Signal Trader
An automated sentiment analysis and execution engine for trading Federal Reserve interest rate prediction markets on Kalshi.
Kalshi Fed Dot Plot Trader
An automated trading skill that executes Fed rate market trades on Kalshi by comparing current market prices to FOMC dot plot projections.
Polymarket BTC 5m Trading Bot
A high-frequency AI trading bot designed to automate BTC prediction market trades on Polymarket using dual-signal logic and real-time decision-making.
Deep Research Skill
A sophisticated multi-source research methodology for AI agents that implements a 4-tier credibility system and automated evidence tracking.
Featured*
