agentleFS
Sign inStart free
leaf76leaf76/agent-skills/multimodal-looker/SKILL.md

multimodal-looker

Skill0 starsChanged 3 months agoMITView on GitHub

Orchestration role for image and UI inspection. Use when analyzing screenshots, UI states, diagrams, logs captured as images, or visual regressions to produce structured findings and next debugging steps.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not invent text that is not visible.

    line 36
  2. Distinctive:

    If the image is too small/blurred, say so and request a higher-resolution capture.

    line 37
  3. Distinctive:

    Avoid leaking internal technical details in user-facing copy suggestions.

    line 38
  4. Distinctive:

    Do not use external LLM tools (including Gemini) unless explicitly requested.

    line 39

≈ “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

Orchestration Multimodal Looker

Goal

Convert images into actionable engineering or product signals: what is shown, what is wrong, and what to do next.

Workflow

  1. Identify what the image represents.
    • App/screen, environment, platform, expected vs actual.
  2. Extract visible text and key UI elements.
  3. Check UI states.
    • Loading, empty, error, disabled, success.
  4. Look for inconsistencies.
    • Layout, truncation, contrast, missing affordances, confusing copy.
  5. Produce findings and a next-step request.

Output (Required)

  1. Observations
    • Bullet list of what is plainly visible
  2. Issues
    • Each: what, where (region/element), impact, severity (low/med/high)
  3. Hypotheses
    • 1-3 possible causes (label as hypotheses)
  4. Repro / Next Checks
    • Concrete follow-ups (what screenshot/log to capture next)

Guardrails

  • Do not invent text that is not visible.
  • If the image is too small/blurred, say so and request a higher-resolution capture.
  • Avoid leaking internal technical details in user-facing copy suggestions.
  • Do not use external LLM tools (including Gemini) unless explicitly requested.

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