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

visual-reasoning

Skill1 starsChanged 22 days agoMITView on GitHub

Use when analyzing an image for objects, palette, composition, mood, visual hierarchy, and prompt intent.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user wants to understand what an image contains and why it works visually.

    line 8

≈ “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 Reasoning

Use this skill when the user wants to understand what an image contains and why it works visually.

Evals

Should trigger

  • "what's in this image and why does it work?"
  • "analyze the palette and composition"
  • "detect the objects in this photo"
  • "describe the mood and visual hierarchy"

Should not trigger

  • "turn it into a prompt" → use reverse-prompt
  • "review a UI screenshot" → use screenshot-ui-review
  • "score composition quality" → use image-quality-audit

Core workflow

  1. Inspect image metadata (format, resolution)
  2. Detect objects (YOLOv8n)
  3. Extract dominant palette
  4. Estimate brightness and contrast
  5. Analyze composition (rule-of-thirds, symmetry, visual weight, depth)
  6. Generate structured reverse prompt
  7. Return both human-readable and JSON output

Inputs

  • image_path — local path to image file (jpg, png, webp)
  • output_format — text (default) or json

Outputs

  • objects — detected labels with confidence
  • palette — dominant hex colors
  • brightness — dark / mid-tone / bright
  • contrast — low / moderate / high
  • depth — shallow / moderate / deep
  • composition — balance, alignment, symmetry score
  • reverse_prompt — single-string prompt reconstructed from signals

Prefer

  • Deterministic output — same image, same result
  • Explainable labels — no vague descriptions
  • Compact summaries — useful in agent context windows
  • JSON contracts — stable shape for integrations

Avoid

  • Generating new images
  • Making unverifiable aesthetic claims
  • Overwriting source files
  • External API calls without explicit configuration

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