agentleFS
Sign inStart free
MCamnerMCamner/mq-image-analyze/skills/cli-maintainer/SKILL.md

cli-maintainer

Skill1 starsChanged 22 days agoMITView on GitHub

Use when changing mq-image CLI commands, flags, output, doctor checks, serve commands, or command documentation.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Use this skill for the mq-image command surface.

    line 8
  2. Distinctive:

    Keep human output compact and useful.

    line 56
  3. Very specific:

    Keep --json machine-readable with no ANSI decoration.

    line 57
  4. Very specific:

    Update docs/cli.md and README command examples when flags change.

    line 59
  5. Distinctive:

    Add tests for new flags, modes, or output markers.

    line 60
  6. Distinctive:

    Run the full validation script before release:

    line 71

≈ “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

CLI Maintainer

Use this skill for the mq-image command surface.

Evals

Should trigger

  • "add a --foo flag to mq-image analyze"
  • "the doctor command output changed"
  • "document a new serve command"
  • "change an exit code for missing images"

Should not trigger

  • "change the analyze JSON schema" → use json-contract-maintainer
  • "change MCP tool behavior" → use mcp-tools-maintainer
  • "update the README only" → use docs-maintainer

Core Files

  • mq_image_analyze/cli/analyze.py
  • mq_image_analyze/cli/analyze_ui.py
  • mq_image_analyze/cli/compare.py
  • mq_image_analyze/cli/doctor.py
  • mq_image_analyze/cli/serve.py
  • mq_image_analyze/cli/serve_mcp.py
  • mq_image_analyze/cli/__init__.py
  • docs/cli.md
  • README.md
  • tests/test_cli.py
  • tests/test_doctor.py

Command Surface

Known commands:

  • mq-image analyze <image>
  • mq-image analyze <image> --json
  • mq-image analyze <image> --mode local-fast|local-deep|cloud-verify
  • mq-image analyze-ui <screenshot>
  • mq-image compare <before> <after>
  • mq-image serve --port 8000
  • mq-image mcp
  • mq-image doctor
  • mq-image doctor --json
  • mq-image --version

Change Rules

  • Keep human output compact and useful.
  • Keep --json machine-readable with no ANSI decoration.
  • Preserve exit behavior for failed image paths and missing dependencies.
  • Update docs/cli.md and README command examples when flags change.
  • Add tests for new flags, modes, or output markers.

Verification

python -m pytest tests/test_cli.py tests/test_doctor.py -q
mq-image --help
mq-image --version
mq-image doctor --json

Run the full validation script before release:

bash scripts/validate.sh

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.

Check your setup, free