agentleFS
Sign inStart free
MCamnerMCamner/mq-image-analyze/skills/reverse-prompt/SKILL.md

reverse-prompt

Skill1 starsChanged 22 days agoMITView on GitHub

Use when turning an image into a reusable prompt for image generation, visual design, or cinematic direction.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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 to convert an image into a structured prompt that captures its visual character.

    line 8
  2. Distinctive:

    Run visual-reasoning on the image

    line 28

≈ “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

Reverse Prompt

Use this skill to convert an image into a structured prompt that captures its visual character.

Evals

Should trigger

  • "turn this image into a generation prompt"
  • "give me a prompt to recreate this style"
  • "cinematic prompt from this frame"
  • "reverse-engineer a prompt for this art"

Should not trigger

  • "score the image quality" → use image-quality-audit
  • "what objects are in it?" → use visual-reasoning
  • "review this UI screenshot" → use screenshot-ui-review

Core workflow

  1. Run visual-reasoning on the image
  2. Extract subject, environment, lighting, palette, composition
  3. Translate signals into prompt language
  4. Return single-string prompt and token list

Inputs

  • image_path — local path to image file

Outputs

  • prompt — complete prompt string
  • tokens — individual prompt components

Include in prompt

  • Subject / objects
  • Environment and setting
  • Palette description
  • Lighting (inferred from brightness + contrast)
  • Composition style
  • Depth / focus treatment
  • Mood and tone

Avoid

  • Claiming exact camera or lens data unless EXIF confirms it
  • Overfitting prompt language to a single model provider
  • Hallucinated details not visible in the image

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