CLI Anything

Generate or refine agent-usable CLIs for existing software/codebases using the CLI-Anything methodology. Use when the user wants to turn a GUI app, desktop t...

Security Scan

The skill's code, instructions, and file layout are coherent with its stated purpose (inspecting a local CLI-Anything repo and helping package/verify harnesses); it doesn't request credentials or external downloads, but it does instruct installing and running local harness code, which has normal side‑effect risks.

Purpose & Capability

Name/description match the delivered artifacts: SKILL.md, two small helper scripts, and reference docs all focus on inspecting a local CLI-Anything checkout and guiding harness selection or packaging. No unrelated env vars, binaries, or offsite endpoints are requested.

Instruction Scope

Instructions direct the agent to read specific workspace paths and to verify/install harness Python packages and run CLI entrypoints (e.g., pip install -e, cli-anything-gimp). That's appropriate for this skill's purpose but gives the agent permission to install packages and execute code from the local repo; that can have side effects and should be done only with trusted code or in a sandbox.

Install Mechanism

There is no install spec (instruction-only skill) and bundled Python scripts are small and local. Nothing in the package downloads or extracts remote archives or pulls code from untrusted URLs.

Credentials

The skill requests no environment variables, credentials, or config paths beyond workspace paths it documents. The only environment impact is potentially installing Python dependencies into the execution environment, which is consistent with verifying harnesses but should be deliberate.

Persistence & Privilege

always:false and no request to modify other skills or global agent settings. The skill may be invoked autonomously by the model per platform defaults, but it does not escalate privileges or demand permanent presence.

Assessment

This skill appears to do what it claims: inspect a local CLI-Anything repo and help select, verify, or package harnesses. Before allowing it to install or run anything, consider: 1) only use it if you trust the local CLI-Anything checkout (its harnesses run code); 2) prefer running installs and CLI verifications in an isolated environment (container or VM) to avoid modifying your system Python or causing side effects; 3) review harness code (setup.py, entry points, tests) before permitting pip install -e or executing entrypoints; and 4) require explicit user confirmation before the agent publishes or pushes artifacts externally. If you want stricter safety, deny automated installation/execution and ask for a dry-run listing of commands the skill would run.

Use this skill to work with the local CLI-Anything/ repository in the workspace and turn its methodology into something usable from OpenClaw.

What this skill is for

Use it for three common cases:

1. Assess feasibility — inspect a target app/repo and decide whether CLI-Anything is a good fit.
2. Use an existing harness — work with one of the repo's prebuilt agent-harness examples.
3. Wrap for OpenClaw — turn CLI-Anything guidance or an existing harness into an OpenClaw skill/workflow.

Local source of truth

The repository is expected at:

• /root/.openclaw/workspace/CLI-Anything

Read these first when needed:

• CLI-Anything/README.md — overall platform and examples
• CLI-Anything/cli-anything-plugin/HARNESS.md — generation methodology and quality bar
• CLI-Anything/cli-anything-plugin/README.md — plugin behavior and expected output layout

For a fast survey of bundled examples, read references/bundled-harnesses.md.

Core workflow

1) Classify the user's request

Decide which path applies:

• Methodology request: user wants to understand or apply CLI-Anything generally
• Existing harness request: user wants to use/demo one of the included examples like GIMP or LibreOffice
• Packaging request: user wants an OpenClaw skill or ClawHub package derived from CLI-Anything

2) Inspect prerequisites

Before promising execution, check:

• Python 3.10+
• target software presence if using a real harness backend
• whether the request is about:
  • building a harness
  • running a generated CLI
  • packaging/publishing

3) Prefer existing harnesses before generation

If the repo already includes a matching harness under <software>/agent-harness/, use that as the baseline instead of pretending generation has to happen from scratch.

4) For OpenClaw packaging, separate method from implementation

CLI-Anything itself is not a native OpenClaw skill package. When adapting it:

• keep the OpenClaw SKILL.md focused on when to use and how to navigate the local repo
• move large methodology text into references
• do not claim that /plugin or /cli-anything slash commands are directly available inside OpenClaw unless you have actually wired them up

Practical guidance

When the user wants to use an existing bundled harness

1. Locate <software>/agent-harness/
2. Read its setup.py, package layout, and local README/SOP file
3. Identify hard dependencies on the real software backend
4. Install or verify Python requirements only as needed
5. Validate the CLI entry point and a minimal command

When the user wants to make a new app agent-native

Use CLI-Anything as methodology, not magic:

1. Analyze backend engine, data model, existing CLI/API hooks
2. Define command groups and state model
3. Create or refine agent-harness/
4. Add tests and a TEST.md
5. Install the resulting package to PATH
6. Verify real backend execution, not mock-only behavior

When the user wants an OpenClaw skill

There are two good outputs:

• Method skill: teaches OpenClaw how to use CLI-Anything on local repos
• Harness skill: wraps one generated CLI or one concrete software target

Default to a method skill unless the user clearly wants a single app workflow.

Rules

• Do not say CLI-Anything is already a native OpenClaw skill unless you created that wrapper.
• Do not promise a generated CLI works until you verify its entry point and real backend dependencies.
• Treat third-party generated code as reviewable output, not automatically trusted output.
• For publishing, require explicit user intent before pushing anything external.
• If packaging for ClawHub, keep the skill lean and point to local references instead of pasting huge docs into SKILL.md.

Useful script

Use scripts/inspect_cli_anything.py to quickly inspect the local repo and enumerate bundled harnesses. It prints JSON with:

• whether the repo exists
• discovered harnesses
• whether each harness has setup.py, package directory, README, and E2E tests

Run:

python3 /root/.openclaw/workspace/skills/cli-anything/scripts/inspect_cli_anything.py

Use scripts/recommend_harness.py to rank the bundled harnesses and suggest good first validation targets.

Run:

python3 /root/.openclaw/workspace/skills/cli-anything/scripts/recommend_harness.py

Helpful local paths

• Repo root: /root/.openclaw/workspace/CLI-Anything
• Plugin docs: /root/.openclaw/workspace/CLI-Anything/cli-anything-plugin
• Example harnesses: /root/.openclaw/workspace/CLI-Anything/*/agent-harness

Reference files

• references/bundled-harnesses.md — quick map of included examples
• references/openclaw-adaptation-notes.md — how to package CLI-Anything ideas into OpenClaw skills
• references/validated-example-gimp.md — first locally verified runnable example