Local AI App Integration
amd/skills
Integrates local AI capabilities into applications using Embeddable Lemonade.
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…
Install Image To Text
$ npx skills add godot-fun/gai --skill image-to-text -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install godot-fun/gai image-to-text --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/godot-fun/gai.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/image-to-text .claude/skills/image-to-text && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "image-to-text" agent skill from https://github.com/godot-fun/gai/tree/main/.agents/skills/image-to-text into .claude/skills/image-to-text/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-to-text", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/godot-fun/gai/tree/main/.agents/skills/image-to-textType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add godot-fun/gai --skill image-to-text -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install godot-fun/gai image-to-text --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/godot-fun/gai.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/image-to-text .agents/skills/image-to-text && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "image-to-text" agent skill from https://github.com/godot-fun/gai/tree/main/.agents/skills/image-to-text into .agents/skills/image-to-text/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-to-text", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add godot-fun/gai --skill image-to-text -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install godot-fun/gai image-to-text --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/godot-fun/gai.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/image-to-text .cursor/skills/image-to-text && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "image-to-text" agent skill from https://github.com/godot-fun/gai/tree/main/.agents/skills/image-to-text into .cursor/skills/image-to-text/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-to-text", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/godot-fun/gai.git --path .agents/skills/image-to-text--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add godot-fun/gai --skill image-to-text -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install godot-fun/gai image-to-text --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/godot-fun/gai.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/image-to-text .gemini/skills/image-to-text && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "image-to-text" agent skill from https://github.com/godot-fun/gai/tree/main/.agents/skills/image-to-text into .gemini/skills/image-to-text/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-to-text", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install godot-fun/gai image-to-textInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add godot-fun/gai --skill image-to-text -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/godot-fun/gai.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/image-to-text .github/skills/image-to-text && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "image-to-text" agent skill from https://github.com/godot-fun/gai/tree/main/.agents/skills/image-to-text into .github/skills/image-to-text/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-to-text", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add godot-fun/gai --skill image-to-text -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install godot-fun/gai image-to-text --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/godot-fun/gai.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/image-to-text .opencode/skills/image-to-text && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "image-to-text" agent skill from https://github.com/godot-fun/gai/tree/main/.agents/skills/image-to-text into .opencode/skills/image-to-text/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-to-text", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
image-to-text- GitHub stars
- 183
- Token cost
- ~813 tokens
- SKILL.md length
- 266 words
- Files
- 1
- Skills in repo
- 36
- Repo updated
- First seen
- Licence
- MIT
At a glance
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…
- The user asks to describe
- SKILL.md covers Rules, Usage, Output guidance and Troubleshooting
- Calls python
- Extract visible details and text from PNG
What it does
Image To Text is an agent skill from godot-fun/gai. 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.
Its SKILL.md is about 810 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Media & Creative, covering LLM inference and serving and Transcription. It works with llama.cpp. The repository describes itself as: A lightweight AI agent and skill workflow framework built with Godot. The licence is MIT.
When your agent uses it
- The user asks to describe
- Extract visible details and text from PNG
- TIFF images without a GPU
- Remote vision API
Example prompts
- “Use the image-to-text skill to convert one or more images into faithful text descriptions or OCR with the local 1.3B MiniCPM-V 4.6 GGUF model…”
- “/image-to-text”
What it can do on your machine
Read from SKILL.md and the folder at commit 6394686. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Image To Text loads about 813 tokens when it runs. Until then it costs about 103 tokens; SKILL.md has 266 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from godot-fun/gai at commit 6394686, republished under its MIT licence (© godot-fun). 266 words, ~813 tokens.
Download SKILL.mdSave it as
.claude/skills/image-to-text/SKILL.md (or your agent's skills folder).- name
- image-to-text
- description
- 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.
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 skill-dependency-manager before running commands.
- Run
.ai/image-to-text/image_to_text.pythrough the defaultpythonmanifest entry only. - Load the language model and multimodal projector only from
.dependency/minicpm-v-4.6/model. - Before inference, check the
llama-cpp-gpuruntime with--list-devices. Prefer it when a Vulkan device is reported; otherwise usellama-cpp-cpu. - Use
--gpuor-GPUto require GPU inference and fail when unavailable. - Use
--cputo bypass detection and force CPU inference for troubleshooting or comparison. - Preserve observable facts and clearly distinguish uncertainty from fact.
- Pass related images after one
--imagesor--imageoption; both names are equivalent.
Usage
.dependency/python/python.exe .ai/image-to-text/image_to_text.py --images C:\path\photo.png.dependency/python/python.exe .ai/image-to-text/image_to_text.py --images before.png after.png --prompt "Compare these images and list only visible changes.".dependency/python/python.exe .ai/image-to-text/image_to_text.py --image C:\path\photo.png -GPU.dependency/python/python.exe .ai/image-to-text/image_to_text.py --image C:\path\photo.png --cpuUse --output description.md to also save UTF-8 text. See cli/image-to-text.md for copy-paste commands.
Output guidance
- General description: mention scene, subjects, actions, composition, colors, and legible text.
- OCR: preserve reading order and line breaks where practical; mark uncertain characters with
[unclear]. - Accessibility alt text: be concise and omit decorative speculation.
- Structured extraction: request JSON explicitly and validate it before presenting it as machine-readable.
- Never identify a real person from appearance alone or infer sensitive traits not explicitly visible as text.
Troubleshooting
- Missing CPU runtime: verify
.dependency/llama-cpp-cpu/llama-mtmd-cli.exeexists. - GPU unavailable: verify
.dependency/llama-cpp-gpu/llama-mtmd-cli.exeexists and--list-devicesreports a Vulkan device. Update the graphics driver if necessary. - Missing model: verify
MiniCPM-V-4_6-Q4_K_M.ggufandmmproj-model-f16.ggufexist under.dependency/minicpm-v-4.6/model. - Out of memory: close other applications or process fewer/smaller images; the official GGUF listing states approximately 2GB memory, but working memory varies with image size and context.
- Slow inference: CPU speed, core count, memory bandwidth, and image resolution directly affect latency.
© godot-fun, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/image-to-text of godot-fun/gai.
Open the folder on GitHubat commit 6394686
Compare with similar skills
Image To Text next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Image To Text this skillgodot-fun/gai | 183 | — | ~813 | Automated safety check: Pass | MIT | |
| Local AI App Integrationamd/skills | 408 | — | ~6k | Automated safety check: Pass | MIT | |
| Teach A ModelAseiel/VideoHighlighter | 165 | — | ~839 | Automated safety check: Pass | AGPL-3.0 | |
| Aider DelegateamElnagdy/delegate-skills | 2.3k | 2 repos | ~3k | Automated safety check: Pass | MIT | |
| Helmor Bump Vendorsdohooo/helmor | 1.3k | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| Qwen Mtp GgufR6410418/Jackrong-llm-finetuning-guide | 1.7k | — | ~1.7k | Automated safety check: Pass | MIT |
Similar skills
Teach A Model
Aseiel/VideoHighlighter
Train a custom VideoHighlighter action or object model from a few videos the user provides — cut into samples, sort with CLIP, review contact sheets, build, train, install only if better.
Aider Delegate
amElnagdy/delegate-skills
Delegate a coding task to Aider (aider) as a background implementer, then review its diff and land it yourself.
Helmor Bump Vendors
dohooo/helmor
Bump or upgrade the pinned versions of Helmor's bundled agent CLIs, SDKs, and supporting binaries — Claude Code + claude-agent-sdk (lockstep), Codex, Cursor SDK, OpenCode, Kimi, Pi, and gh / glab /…
Qwen Mtp Gguf
R6410418/Jackrong-llm-finetuning-guide
Complete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release.
Quantization
vllm-project/vllm-omni
Work on vLLM-Omni quantization for diffusion, autoregressive, omni, or multi-stage models.
More from godot-fun/gai
All 36 skills in this repoAI Text To Speech
godot-fun/gai
Zero-shot text-to-speech with voice cloning via IndexTTS2 (index-tts).
Audio Denoise
godot-fun/gai
Reduces background noise in a single audio file using FFmpeg afftdn.
Audio Fade
godot-fun/gai
Applies fade-in and fade-out at the start and end of a single audio file using FFmpeg.
Audio Loudness Normalization
godot-fun/gai
Normalizes a single audio file to consistent LUFS loudness with true-peak limiting using FFmpeg.
Audio Sample Rate Standardize
godot-fun/gai
Standardizes a single audio file to 44100 or 48000 Hz and exports 16-bit PCM WAV using FFmpeg.
Audio Split
godot-fun/gai
Splits a single audio file into two segments (part 1 before the split point, part 2 after) using FFmpeg.
Related
Works with
Questions about Image To Text
What does Image To Text do?
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…. Image To Text is an agent skill from godot-fun/gai.cpp, automatically preferring an available Vulkan GPU and falling back to CPU.
When should I use Image To Text?
Image To Text fits situations like: the user asks to describe; extract visible details and text from PNG; TIFF images without a GPU; remote vision API.
How do I install Image To Text in Claude Code?
Run `npx skills add godot-fun/gai --skill image-to-text -a claude-code`. Or copy the skill folder (.agents/skills/image-to-text in godot-fun/gai) into .claude/skills/image-to-text in your project. Claude Code loads it when a task matches its description.
How do I install Image To Text in Codex?
Run `npx skills add godot-fun/gai --skill image-to-text -a codex`. Or copy the skill folder (.agents/skills/image-to-text in godot-fun/gai) into .agents/skills/image-to-text in your project. Codex loads it when a task matches its description.
Can I use Image To Text in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add godot-fun/gai --skill image-to-text -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/image-to-text, .gemini/skills/image-to-text, .github/skills/image-to-text and .opencode/skills/image-to-text in your project.
What does Image To Text need to run?
Going by SKILL.md and its folder, Image To Text needs the command-line tools its instructions call (python).
Does Image To Text access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Image To Text safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Image To Text use?
Image To Text is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Image To Text use?
About 813 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Image To Text?
Skills that share tags, products or a category with Image To Text: Local AI App Integration (amd/skills, 408 stars), Teach A Model (Aseiel/VideoHighlighter, 165 stars), Aider Delegate (amElnagdy/delegate-skills, 2.3k stars) and Helmor Bump Vendors (dohooo/helmor, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Image To Text?
godot-fun (a GitHub organization) maintains it in godot-fun/gai, which has 183 GitHub stars. The repository holds 36 skills in this directory. The repository was last updated on October 10, 2026.
Source: godot-fun/gai on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.