RTFM Testing
v1.0.0Validates documentation usability by spawning context-free agents to complete tasks using only the docs, identifying gaps for improvement.
⭐ 2· 1.1k·0 current·0 all-time
by@zscole
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The files (SKILL.md, TESTER.md, GAPS.md) describe a doc-testing methodology and the runtime instructions are limited to spawning a fresh tester agent with provided documentation. The skill declares no environment variables, binaries, config paths, or install steps — everything requested is proportional to the stated purpose. The only minor metadata oddity is there is no human-friendly description/homepage and the source is 'unknown', which reduces provenance but doesn't contradict purpose.
Instruction Scope
The SKILL.md and TESTER.md instruct the agent to run sessions_spawn with the TESTER prompt and only use the provided docs. They do not direct the agent to read local files, system environment variables, or contact external endpoints beyond the platform's session API. One operational caution: any documentation you paste into the tester will be visible to the spawned agent (and may be logged by the platform), so do not include secrets or sensitive configuration in the docs you submit.
Install Mechanism
There is no install specification and no code files to execute; this is an instruction-only skill, which is the lowest-risk install model.
Credentials
The skill requests no environment variables, credentials, or config paths. This is appropriate for a documentation-testing tool. The only proportionality consideration is user-supplied content: docs given to the tester should not contain secrets or private keys.
Persistence & Privilege
The skill does not request persistent presence (always: false) and uses normal autonomous invocation (disable-model-invocation: false), which is expected for a utility skill. It does not attempt to modify other skills or system-wide settings.
Assessment
This skill appears to do what it says: spawn a fresh tester agent and report documentation gaps. Before using it: (1) do not paste secrets, credentials, or private config into the documentation you test — those will be visible to the spawned agent and may be logged; (2) confirm your platform's sessions_spawn behavior and logs/retention so you know who can read tester outputs; (3) because the package metadata lacks a homepage/source, prefer running it on non-production, sandboxed content first to build trust; and (4) if you want to automate CI checks, ensure the tester runs under an account with limited permissions and that outputs are stored in a secure place.Like a lobster shell, security has layers — review code before you run it.
latestvk97954xj3gs571qxywn0g0kjch80pfx8
License
MIT-0
Free to use, modify, and redistribute. No attribution required.