agentleFS
Sign inStart free
MCamnerMCamner/mq-image-analyze/skills/repo-aware/SKILL.md

repo-aware

Skill1 starsChanged 22 days agoMITView on GitHub

Use when inspecting, explaining, planning, reviewing, or changing mq-image-analyze with repository-specific context.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Use this skill to ground work in mq-image-analyze's actual architecture, contracts, tests, and release flow.

    line 8
  2. Distinctive:

    Use focused checks when possible:

    line 63
  3. Very specific:

    No model weights, .env, or credentials in git.

    line 81
  4. Distinctive:

    Keep visual tools read-only by default.

    line 82
  5. Distinctive:

    Do not silently omit detections in exhaustive mode.

    line 83
  6. Distinctive:

    Update docs and tests whenever CLI, MCP, JSON, or skill behavior changes.

    line 84

≈ “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

Repo Aware

Use this skill to ground work in mq-image-analyze's actual architecture, contracts, tests, and release flow.

Evals

Should trigger

  • "explain mq-image-analyze's architecture"
  • "what surfaces does this repo have?"
  • "plan a change that spans the repo"
  • "I'm new here — where do I start?"

Should not trigger

  • "change the CLI" → use cli-maintainer
  • "change the JSON schema" → use json-contract-maintainer
  • "is it ready to release?" → use release-readiness

What This Repo Is

mq-image-analyze is the visual perception layer for the MQ ecosystem. It analyzes images, screenshots, composition, palettes, UI structure, reverse prompts, and visual differences through CLI, web, and MCP surfaces.

Primary surfaces:

  • mq_image_analyze/vision/ for object, palette, composition, UI, architecture, semantic, and content signals
  • mq_image_analyze/pipelines/ for OCR and architecture observation
  • mq_image_analyze/reasoning/ for reverse prompts and comparisons
  • mq_image_analyze/cli/ for mq-image commands
  • mq_image_analyze/mcp/ for MCP server and tool contracts
  • mq_image_analyze/web/ for the web UI/server package
  • docs/ for architecture, CLI, JSON schema, MCP tools, safety, model setup, integration, and release docs
  • skills/ for agent-facing visual reasoning skills
  • tests/ for CLI, schema, MCP, web package, provider, composition, palette, comparison, and safety coverage

First Inspection

Start with:

git status --short
rg --files
sed -n '1,220p' README.md
sed -n '1,220p' pyproject.toml
sed -n '1,220p' docs/architecture.md

For behavior changes, inspect the matching CLI, pipeline, docs, and tests.

Verification

Use focused checks when possible:

python -m compileall mq_image_analyze -q
python -m pytest -q
bash scripts/validate.sh

For release-critical changes:

bash release-check.sh

Guardrails

  • Preserve stable JSON contracts unless intentionally versioning a breaking change.
  • No model weights, .env, or credentials in git.
  • Keep visual tools read-only by default.
  • Do not silently omit detections in exhaustive mode.
  • Update docs and tests whenever CLI, MCP, JSON, or skill behavior changes.

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