image-to-text SKILL.md skillA
image-to-text from godot-fun/gai is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add godot-fun/gai/image-to-text@git:20261101.d8fbf4cPins git:20261101.d8fbf4c in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- godot-fun/gai
- Path
.agents/skills/image-to-text/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261101.d8fbf4c, committed Nov 1, 2026
- First version recorded
- Sep 28, 2026
- Size
- 3,239 bytes
- Repository stars
- 202
- License
- MIT
Converts one or more images into faithful text descriptions or OCR with the local 1.3B MiniCPM-V 4.6 GGUF model through llama.cpp, automatically preferring an available Vulkan GPU and falling back to CPU. Use when the user asks to describe, caption, compare, transcribe, inspect, or extract visible details and text from PNG, JPEG, WebP, GIF, BMP, or TIFF images without a GPU or remote vision API.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Image to Text Run the official `openbmb/MiniCPM-V-4.6-gguf` Q4_K_M model locally with llama.cpp. Do not send images to remote APIs. ## Rules Read and follow [dependency-manager](../dependency-manager.md) before running commands. - Run `.ai/image-to-text/image_to_text.py` through the default `python` manifest entry only. - Load the language model and multimodal projector only from `.dependency/minicpm-v-4.6/model`. - Before inference, check the `llama-cpp-gpu` runtime with `--list-devices`. Prefer it when a Vulkan device is reported; otherwise use `llama-cpp-cpu`. - Use `--gpu` or `-GPU` to require GPU inference and fail when unavailable. - Use `--cpu` to bypass detection and force CPU inference for troubleshooting or comparison. - Preserve observable facts and clearly distinguish uncertainty from fact. - Pass related images after one `--images` or `--image` option; both names are equivalent. ## Usage ```powershell .dependency/python/python.exe .ai/image-to-text/image_to_text.py --images C:\path\photo.png ``` ```powershell …
Read the whole file at its exact version.
How to install
mdr add godot-fun/gai/image-to-text@sha256:696a8a8f577bf597The line at the top of this page pins the label git:20261101.d8fbf4c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_hzoa3htj42c6cr6p)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Sep 28, 2026 and Nov 1, 2026, about one every 34 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261101.d8fbf4c latest | 2026-11-01 | d8fbf4c | 3,239 B | A | view · diff |
| git:20260928.e246cdd | 2026-09-28 | e246cdd | 3,251 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3239 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
godot-fun/gai · 202 stars · license MIT · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_hzoa3htj42c6cr6p GET https://markdownregistry.com/api/v1/resolve?ref=godot-fun/gai/image-to-text GET https://markdownregistry.com/api/v1/blob/696a8a8f577bf59706fbc46fc5f139e0df716e54326844d2e0747ee5ee33095b
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.