image SKILL.md skillA

image from axoviq-ai/synthadoc is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add axoviq-ai/synthadoc/image@v1.0

Pins v1.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
axoviq-ai/synthadoc
Path
synthadoc/skills/image/SKILL.md
Versions recorded
2
Latest version
v1.0, committed Jun 26, 2026
First version recorded
Apr 11, 2026
Size
2,183 bytes
Repository stars
1,725
License
AGPL-3.0

Extract text from images using a vision LLM.

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 Skill

Base64-encodes the image and passes it to a vision-capable LLM that extracts
all text and key information. Returns the LLM's response as `result.text`.

## Setup

No pip dependency — the skill uses only the Python standard library plus a
LLM provider you supply at construction time. The provider can be any object
that implements the `complete()` interface (see below).

## Standalone usage

```python
import asyncio
from synthadoc.skills.image.scripts.main import ImageSkill

# ImageSkill REQUIRES a vision-capable provider — calling extract() without
# one raises ValueError immediately.
skill = ImageSkill(provider=my_provider)

async def main():
    result = await skill.extract("/path/to/screenshot.png")
    print(result.text)          # extracted text from the image
    print(result.metadata)      # {"tokens_input": N, "tokens_output": N}

asyncio.run(main())
```

**Provider interface** — any object with this async method:

```python
async def complete(
    messages: list,             # list of Message objects from synthadoc.skills.base
    system: str | None = None,
    temperature: float = 0.0,
    max_tokens: int = 4096,
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add axoviq-ai/synthadoc/image@sha256:4725ca318cb670a9

The line at the top of this page pins the label v1.0, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_2opiq25eujk23oef.svg)](https://markdownregistry.com/a/art_2opiq25eujk23oef)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Apr 11, 2026 and Jun 26, 2026, about one every 76 days.

versioncommittedcommitsizeaudit
v1.0 latest2026-06-26 d11681b 2,183 BA view · diff
v1.02026-04-11 d9f25ca 757 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2183 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

GitHub

axoviq-ai/synthadoc · 1,725 stars · license AGPL-3.0 · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_2opiq25eujk23oef
GET https://markdownregistry.com/api/v1/resolve?ref=axoviq-ai/synthadoc/image
GET https://markdownregistry.com/api/v1/blob/4725ca318cb670a980fd58f253e6c4966ec45f9621611ba86b981af4db7e7808

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.

More from axoviq-ai/synthadoc

AGENTS.md@synthadoc/demos/ai-research AGENTS.md file
axoviq-ai/synthadoc · synthadoc/demos/ai-research/AGENTS.md
git:20260730.1853d17 · audit B · 1,725 stars
CLAUDE.md@synthadoc/demos/ai-research CLAUDE.md file
axoviq-ai/synthadoc · synthadoc/demos/ai-research/CLAUDE.md
git:20260730.1853d17 · audit B · 1,725 stars
AGENTS.md@synthadoc/demos/history-of-computing AGENTS.md file
axoviq-ai/synthadoc · synthadoc/demos/history-of-computing/AGENTS.md
git:20260730.1853d17 · audit B · 1,725 stars
CLAUDE.md@synthadoc/demos/history-of-computing CLAUDE.md file
axoviq-ai/synthadoc · synthadoc/demos/history-of-computing/CLAUDE.md
git:20260730.1853d17 · audit B · 1,725 stars
docx SKILL.md skill
axoviq-ai/synthadoc · synthadoc/skills/docx/SKILL.md · Extract text from Microsoft Word documents
v1.0 · audit A · 1,725 stars
markdown SKILL.md skill
axoviq-ai/synthadoc · synthadoc/skills/markdown/SKILL.md · Ingest Markdown and plain text files
v1.0 · audit A · 1,725 stars
pdf SKILL.md skill
axoviq-ai/synthadoc · synthadoc/skills/pdf/SKILL.md · Extract text from PDF documents
v1.0 · audit A · 1,725 stars
pptx SKILL.md skill
axoviq-ai/synthadoc · synthadoc/skills/pptx/SKILL.md · Extract text from Microsoft PowerPoint presentations
v1.0 · audit A · 1,725 stars
session SKILL.md skill
axoviq-ai/synthadoc · synthadoc/skills/session/SKILL.md · Extract conversation turns from AI session history files (.jsonl)
v1.0 · audit A · 1,725 stars
url SKILL.md skill
axoviq-ai/synthadoc · synthadoc/skills/url/SKILL.md · Fetch and extract text from web URLs
v1.0 · audit A · 1,725 stars
web_search SKILL.md skill
axoviq-ai/synthadoc · synthadoc/skills/web_search/SKILL.md · Search the web and ingest results as wiki pages
v1.0 · audit A · 1,725 stars
xlsx SKILL.md skill
axoviq-ai/synthadoc · synthadoc/skills/xlsx/SKILL.md · Extract data from Excel and CSV files
v1.0 · audit A · 1,725 stars

Every file in axoviq-ai/synthadoc

Other files named image

image SKILL.md skill
coreyhaines31/marketingskills · skills/image/SKILL.md · When the user wants to create, generate, edit, or optimize images for marketing — blog heroes, social graphics, product…
v2.0.3 · audit A · 57,640 stars
image SKILL.md skill
phyagentos/phyagentos-core · PhyAgentOS/skills/image/SKILL.md · Unified tool for analyzing and displaying images (vision analysis and image display).
git:20260331.475dbda · audit A · 2,996 stars
image SKILL.md skill
guaardvark/guaardvark · .agents/skills/image/SKILL.md · Generate or edit images on the user's own GPU through Guaardvark: single images, instruction edits, background…
git:20261020.ca3b8f7 · audit A · 294 stars
image SKILL.md skill
cesarjoquin/marketing-skills · skills/image/SKILL.md · When the user wants to create, generate, edit, or optimize images for marketing — blog heroes, social graphics, product…
v2.0.1 · audit A · 211 stars
image SKILL.md skill
login-tb/claude-skills · skills/image/SKILL.md · Marketingbilder rechtebewusst planen, erzeugen, bearbeiten, optimieren und prüfen. Nutze diesen Skill für…
v2.0.1 · audit A · 80 stars
image SKILL.md skill
starchild-ai-agent/official-skills · image/SKILL.md · Generate, edit, cut out, and inspect images with the best hosted image models (Nano Banana 2 / Pro, GPT Image 2…
v2.1.2 · audit A · 29 stars
image SKILL.md skill
phnx-labs/agi-cli · cli/src/commands/__tests__/testdata/stats-plugin-names/agents/plugins/create/skills/image/SKILL.md · Generate an image.
git:20261006.5fb8d40 · audit B · 27 stars
image SKILL.md skill
bendrucker/claude · plugins/meme/skills/image/SKILL.md · Generate a meme by overlaying text on an image. Use when asked to make a meme, caption an image, add meme text, or…
git:20260724.2913803 · audit A · 18 stars

Browse by kind, by grade A, or by owner.