Skill Test Generator

v1.0.0

Automatically generate test documentation for existing skills that have scripts but lack testing guidance. Use when a skill has scripts/ directory but no TES...

0· 24·0 current·0 all-time
by风风@834948655
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description match what is present: the SKILL.md describes discovering scripts/ and generating TESTING.md or a testing section, and the included test_template.py implements script parsing and test-case generation. No unrelated credentials, binaries, or installs are requested.
Instruction Scope
Runtime instructions and the code focus on listing and reading files under a skill's scripts/ directory, parsing Python files with ast, and generating markdown test cases. The instructions do not direct the agent to exfiltrate data or call external endpoints. They do produce copy-paste commands which, if executed by a user, would run the target scripts — this is expected for test documentation but should be used cautiously.
Install Mechanism
No install spec is provided (instruction-only with a helper script included). There are no downloads, third-party package installs, or archive extracts; risk from installation is minimal.
Credentials
The skill requires no environment variables, credentials, or config paths. The code only reads files from the target skill directory specified by the user; this is proportionate to the stated purpose.
Persistence & Privilege
The skill is not marked always:true and does not request persistent system-wide changes. It does not attempt to modify other skills' configurations or request elevated privileges.
Assessment
This skill is coherent: it reads scripts/ and generates TESTING.md content. Before using or running generated commands, verify the target skill's scripts are from a trusted source — generated commands may execute those scripts if copied and run. The included generator only reads files and produces markdown; it does not perform network I/O or access secrets. If you plan to have the agent automatically run tests, review those test commands and test data first to avoid executing untrusted code.

Like a lobster shell, security has layers — review code before you run it.

latestvk971pf26gfz7mdqkm8rgtm9xs584pyr2

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments