agentleFS
Sign inStart free
deathbyknowledgedeathbyknowledge/gsv/skills/image-reading/SKILL.md

image-reading

Skill131 starsChanged 4 months agoMITView on GitHub

Read and analyze images on GSV or connected targets with img2txt. Use for captions, visual questions, OCR, structured extraction, object pointing or detection, and screenshots or image files stored on another target.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. carlosbuelvas1/openclaw-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository9 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Run img2txt from the gsv target.

    line 8
  2. Very specific:

    Use --schema with JSON when the result must have a specific structure.

    line 23
  3. Very specific:

    Use --reasoning --json when query reasoning or grounding is useful.

    line 25
  4. Very specific:

    Use --stream only for unstructured caption, query, or OCR text.

    line 26

≈ “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

Read Images

Run img2txt from the gsv target. Use man img2txt for current syntax.

Choose the mode based on the task:

  • caption: Describe the image. Use --length short|normal|long.
  • query: Answer a specific visual question. Requires --prompt.
  • ocr: Extract text. Optionally use --prompt to narrow the extraction.
  • point: Return normalized coordinates for instances of an object. Requires --target.
  • detect: Return normalized bounding boxes for instances of an object. Requires --target.

Pass images directly using a local path, gsv:/path, target:/path, or [target-with-colons]:/path. Target images stream directly and do not need to be copied into GSV first.

For query and ocr, use --response-format for JSON, XML, Markdown, or CSV. Use --schema with JSON when the result must have a specific structure.

Use --reasoning --json when query reasoning or grounding is useful. Use --stream only for unstructured caption, query, or OCR text; it cannot be combined with JSON envelopes, reasoning, or structured output.

point and detect produce JSON by default.

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