agentleFS
Sign inStart free
MCamnerMCamner/mq-image-analyze/skills/visual-architecture-analysis/SKILL.md

visual-architecture-analysis

Skill1 starsChanged 22 days agoMITView on GitHub

Use when adding or changing mq-image-analyze features for architecture diagrams, infrastructure topology screenshots, terminal screenshots, OCR pipelines, or visual observations consumed by mq-mcp.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when visual analysis feeds architecture or review workflows.

    line 8
  2. Distinctive:

    Prefer structured JSON observations over prose.

    line 44
  3. Distinctive:

    Keep OCR text bounded and avoid claiming certainty for low-quality images.

    line 46
  4. Distinctive:

    Add schema fields additively unless a major version bump is intended.

    line 47
  5. Distinctive:

    Update examples when JSON output changes.

    line 56

≈ “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

Visual Architecture Analysis

Use this skill when visual analysis feeds architecture or review workflows.

Evals

Should trigger

  • "add OCR for architecture diagrams"
  • "analyze this infra topology screenshot"
  • "extract diagram observations for mq-mcp"
  • "parse this terminal screenshot pipeline"

Should not trigger

  • "review a UI screenshot for usability" → use screenshot-ui-review
  • "general image analysis" → use visual-reasoning
  • "change MCP tool schemas" → use mcp-tools-maintainer

Boundary

mq-image-analyze owns visual observation: objects, layout, OCR, topology hints, palette, screenshot structure and machine-readable visual facts.

It must not generate final review findings, own architecture memory, or make architecture decisions. mq-mcp consumes the observations and performs cognition.

Files To Inspect

  • mq_image_analyze/cli/
  • mq_image_analyze/vision/
  • mq_image_analyze/reasoning/
  • docs/json-schema.md
  • docs/mcp-tools.md
  • examples/
  • tests/test_analyze_ui.py
  • tests/test_json_schema.py

Output Rules

  • Prefer structured JSON observations over prose.
  • Include limitations and confidence where detection is heuristic.
  • Keep OCR text bounded and avoid claiming certainty for low-quality images.
  • Add schema fields additively unless a major version bump is intended.

Verification

python -m pytest tests/test_json_schema.py tests/test_analyze_ui.py -q
bash scripts/validate.sh

Update examples when JSON output 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