Lobster Cli Anything

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...

Security Scan

The skill's instructions, requirements, and scope are coherent with its stated purpose (building/testing CLI harnesses) and it does not request unexplained credentials or install arbitrary code itself.

Purpose & Capability

The name/description match the SKILL.md: it builds/refines/tests CLI harnesses for a target repository or local source tree. It does not ask for unrelated credentials, binaries, or config paths.

Instruction Scope

The SKILL.md instructs the agent to acquire the source tree (local path or GitHub URL), read repository docs (e.g., ../cli-anything-plugin/HARNESS.md if present), run tests, and install locally (pip install -e .). These actions are appropriate for the stated task but give the agent permission to access local files, clone remote repos, and execute the repository's code/tests — which is expected but should be treated as running untrusted code unless the source is trusted or sandboxed.

Install Mechanism

No install spec or downloaded artifacts are defined; this is an instruction-only skill. That is the lowest-risk pattern from an install-perspective.

Credentials

The skill declares no environment variables, credentials, or config paths. The runtime instructions may require filesystem and network access to clone and run the target project, but they do not demand unrelated secrets or external service tokens.

Persistence & Privilege

The skill is not always-on and is user-invocable. It does not request permanent platform privileges or ask to modify other skills or global agent settings.

Assessment

This skill appears to do what it says: build, refine, test, and validate a CLI harness by operating on a local path or cloning a GitHub repo and running code/tests. Before using it, consider: (1) the agent will access your filesystem and may read repo files such as ../cli-anything-plugin/HARNESS.md — ensure you’re comfortable with that; (2) the agent will clone/run code and tests from the target repo (network access, subprocess execution, pip install -e .) — treat untrusted repositories as potentially unsafe and run in an isolated environment (container or ephemeral VM); (3) verify there are no sensitive files or credentials in the target repo you don’t want exposed; (4) prefer running the skill with least privileges and monitor which commands the agent executes. If you need stricter controls, review the repository contents yourself before asking the agent to run tests or installs.

CLI-Anything for OpenClaw

Use this skill when the user wants OpenClaw to act like the CLI-Anything builder.

If this skill is being used from inside the CLI-Anything repository, read ../cli-anything-plugin/HARNESS.md before implementation. That file is the full methodology source of truth. If it is not available, follow the condensed rules below.

Inputs

Accept either:

• A local source path such as ./gimp or /path/to/software
• A GitHub repository URL

Derive the software name from the local directory name after cloning if needed.

Modes

Build

Use when the user wants a new harness.

Produce this structure:

<software>/
└── agent-harness/
    ├── <SOFTWARE>.md
    ├── setup.py
    └── cli_anything/
        └── <software>/
            ├── README.md
            ├── __init__.py
            ├── __main__.py
            ├── <software>_cli.py
            ├── core/
            ├── utils/
            └── tests/

Implement a stateful Click CLI with:

• one-shot subcommands
• REPL mode as the default when no subcommand is given
• --json machine-readable output
• session state with undo/redo where the target software supports it

Refine

Use when the harness already exists.

First inventory current commands and tests, then do gap analysis against the target software. Prefer:

• high-impact missing features
• easy wrappers around existing backend APIs or CLIs
• additions that compose well with existing commands

Do not remove existing commands unless the user explicitly asks for a breaking change.

Test

Plan tests before writing them. Keep both:

• test_core.py for unit coverage
• test_full_e2e.py for workflow and backend validation

When possible, test the installed command via subprocess using cli-anything-<software> rather than only module imports.

Validate

Check that the harness:

• uses the cli_anything.<software> namespace package layout
• has an installable setup.py entry point
• supports JSON output
• has a REPL default path
• documents usage and tests

Backend Rules

Prefer the real software backend over reimplementation. Wrap the actual executable or scripting interface in utils/<software>_backend.py when possible. Use synthetic reimplementation only when the project explicitly requires it or no viable native backend exists.

Packaging Rules

• Use find_namespace_packages(include=["cli_anything.*"])
• Keep cli_anything/ as a namespace package without a top-level __init__.py
• Expose cli-anything-<software> through console_scripts

Workflow

1. Acquire the source tree locally.
2. Analyze architecture, data model, existing CLIs, and GUI-to-API mappings.
3. Design command groups and state model.
4. Implement the harness.
5. Write TEST.md, then tests, then run them.
6. Update README usage docs.
7. Verify local installation with pip install -e .

Output Expectations

When reporting progress or final results, include:

• target software and source path
• files added or changed
• validation commands run
• open risks or backend limitations