cli-anything

v1.0.0

Use when the user wants OpenClaw to build, refine, test, or validate a CLI-Anything harness for a GUI application or source repository. Adapts the CLI-Anythi...

0· 84·0 current·0 all-time
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
The name/description (build/refine/test/validate CLI harnesses) matches the SKILL.md requirements: it expects a local path or repo URL, describes harness layout, testing, packaging, and validation. There are no unrelated env vars, binaries, or install steps requested.
Instruction Scope
The instructions legitimately direct the agent to read local source trees (and, when present, ../cli-anything-plugin/HARNESS.md), analyze architecture, and run tests/installation commands (e.g., pip install -e ., subprocess invocations). This is expected for a harness-builder but means the agent will access and execute code from the target repo — a potential risk if the repo is untrusted.
Install Mechanism
No install spec and no code files are included in the skill package, so nothing is written to disk by the skill itself. The only instructions that may install things are user-directed steps (e.g., pip install -e .) applied to the target repository, which is appropriate for the stated purpose.
Credentials
The skill declares no required environment variables, credentials, or config paths. The SKILL.md does not ask for secrets or unrelated credentials.
Persistence & Privilege
always is false and the skill is user-invocable. It does not request persistent system-wide privileges or modify other skills' configurations.
Assessment
This skill is instruction-only and coherent for building CLI harnesses. Before running it: (1) only use it on source trees you trust or run in an isolated environment (container/VM) because it advises installing and executing code from the target repo; (2) review any ../cli-anything-plugin/HARNESS.md referenced by the instructions if present; (3) inspect changes the agent proposes to ensure it doesn't modify unrelated files; (4) prefer running tests and installation steps manually or in sandboxed CI to limit risk from untrusted repositories.

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

latestvk9726tnk8xe49pn1r16kdcy4c5844ds9

License

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

Comments