RTFM Testing is a methodology that spawns fresh AI agents with zero context to validate whether documentation is actually usable for its intended tasks.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install rtfm-testing
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 rtfm-testing 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 RTFM Testing?
RTFM Testing solves the common problem of incomplete documentation caused by the expert blind spot. Authors often assume context or skip obvious steps that a new user wouldn't know. By utilizing the Openclaw Skills framework, this tool spawns a tester agent with zero prior knowledge and tasks it with completing a goal using only the provided documentation. If the agent fails, it identifies a documentation bug, providing actionable feedback to the developer.
This methodology transforms documentation from a static asset into a testable piece of software. It ensures that READMEs, setup guides, and tutorials are bulletproof by treating every agent confusion point as a signal for improvement. Using Openclaw Skills for this process allows developers to maintain a high bar for developer experience (DX) and technical clarity.
RTFM Testing Use Cases
- Validating READMEs and setup guides before publishing to ensure they are complete and accurate.
- Debugging user confusion by replicating their environment with a fresh agent session.
- Protecting against documentation rot after major refactors or codebase changes.
- Automating documentation quality assurance as part of a CI/CD pipeline using Openclaw Skills.
How RTFM Testing Works
- Define a specific task that a user should be able to perform after reading your documentation.
- Collect and bundle all relevant documentation files into a single context package.
- Spawn a fresh agent tester using the sessions_spawn command with the specialized TESTER.md system prompt.
- Monitor the agent as it attempts the task, noting any literal interpretations or points of failure.
- Capture gap reports and metrics to identify missing steps or unclear instructions.
- Refine the documentation based on the agent feedback and repeat the cycle until the task is completed without errors.
RTFM Testing Setup
To get started with RTFM Testing, you need to have the TESTER.md and GAPS.md files accessible to your agent. You can initiate a test run within the Openclaw Skills environment using the following command structure:
sessions_spawn(
task: "Complete the following task using ONLY the provided documentation. [TASK DESCRIPTION]\n\n---\n\n[PASTE DOCS HERE]",
agentId: "default",
label: "rtfm-test"
)
RTFM Testing Data Schema & Taxonomy
The skill utilizes a structured feedback loop to organize documentation defects and performance metrics.
| File | Purpose |
|---|---|
| TESTER.md | System prompt defining the agent's constraints and 'zero-context' behavior. |
| GAPS.md | The output specification for documenting identified flaws. |
| Metrics | Cold Start Score (cycles to completion) and Gap Count (number of issues found). |
Success is measured by a low Cold Start Score, indicating that the documentation is clear enough for a fresh agent to succeed on the first attempt.
RTFM Testing Advanced Features
- Multi-agent validation: Deploy different agent models through Openclaw Skills to see if documentation clarity is model-agnostic.
- Automated Gap Categorization: Classifies issues into missing steps, wrong assumptions, or unclear language.
- Strict Inference Control: Disables the agent's ability to use external knowledge, forcing it to rely 100% on the provided text.
- Continuous Integration: Scripted spawn cycles that validate documentation updates in real-time.
SKILL.md
Loading
Related Openclaw Skills
Bagman
Bagman is a comprehensive security framework for AI agents to manage private keys and API secrets without risking accidental exposure or theft.
Bagman
Bagman is a secure key management framework for AI agents to handle wallets, API secrets, and private keys safely.
Agentic Money
A decentralized protocol skill enabling AI agents to discover, hire, and receive payments for services via Ethereum-based escrow.
deAPI AI Media Suite
A cost-effective, decentralized AI toolkit for processing transcription, images, video, and audio through a unified API.
Model Router Manager
An intelligent multi-model routing manager that optimizes AI performance and reduces costs through automated model selection and failover logic.
Content Moderation Skill
A two-layer safety framework designed to protect AI agents from prompt injections and sensitive content violations.
Featured*
