agentleFS
timfewitimfewi/unix-agent-skills/skills/agent/host-cli-usage/SKILL.md

host-cli-usage

Skill2 starsChanged 9 days agoMITView on GitHub

Use for unfamiliar CLI syntax, rejected arguments, missing command environments, or translating an API operation into a shell invocation.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use installed help for the command and relevant subcommand.

    line 8
  2. Distinctive:

    After an argument rejection, correct the invocation from help or the manual instead of guessing flag spellings.

    line 13

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Resolve the installed contract

Use installed help for the command and relevant subcommand; an API schema or remembered example may describe a different interface. Inspect command -v or type -a when aliases, wrappers, or multiple versions could explain the result. Use the prescribed launcher, not an unwrapped substitute.

After an argument rejection, correct the invocation from help or the manual instead of guessing flag spellings. API fields may become positional arguments. Confirm an unfamiliar mapping with a small, authorized invocation before multiplying it in a loop. Do not repeat probes for a known contract.

GNU, BSD, BusyBox, and wrapper commands can share a name. A missing GNU banner or rejected --version does not identify BSD. Check available flags and the actual executable; the operating system alone does not determine the userland.

Missing environments

Non-interactive shells may lack interactive environment hooks. Check the documented wrapper or project environment before declaring a tool absent. Where authorized, use the declared per-command environment entrypoint.

An unapproved automatic hook is not necessarily a denial of manual execution, but neither grants permission. Never use manual entry to bypass an explicit denial. Installing replacements, changing the system, or trusting recurring hooks requires the applicable authorization.

Distinguish an empty result from invocation failure. Return the working invocation and decisive result, or the specific environment or approval gap.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.