Is the Image (Synthadoc) skill free?

Yes. The skill itself is free from axoviq-ai/synthadoc. SkillProof publishes the install command and an independent test verdict at no cost.

How do I install Image (Synthadoc)?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Image (Synthadoc) with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Image (Synthadoc)

Synthadoc-internal Python module that base64s an image to a vision LLM for text extraction

by axoviq-ai · axoviq-ai/synthadoc

Tested · Didn't pass

Read why it failed Download source ↗

Test report

Verdict: Tested · Didn't pass
Tested: Jul 17, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 090e6eb

This is a library module for the Synthadoc engine, not a Claude Code skill: its frontmatter is entry/class/triggers (not the CC name+description contract), and importing scripts/main.py from a bare install throws ModuleNotFoundError: No module named 'synthadoc'. It also needs a vision provider object wired in at construction, so it cannot run in Claude Code at all. Since Claude already reads image text natively and this only adds a broken indirection, it is worse than no skill for a CC user.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 3/5
Triggers reliably 4/5
Output vs. baseline 2/10
Docs & honesty 3/5

What Image (Synthadoc) does

A component of the Synthadoc wiki engine that base64-encodes an image and passes it to a supplied vision LLM to extract text. It is not a standalone Claude Code skill: it uses a non-standard entry/class frontmatter and hard-imports the synthadoc package, so it cannot be loaded or run from ~/.claude/skills.

How to install Image (Synthadoc)

git clone https://github.com/axoviq-ai/synthadoc.git
mkdir -p ~/.claude/skills
cd synthadoc && cp -r synthadoc/skills/image ~/.claude/skills/image  # copies, but the skill is non-functional standalone

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Image (Synthadoc)

/image Synthadoc-internal Python module that base64s an image to a vision LLM for text extraction

It also activates on plain-language prompts like these:

Please read the text contained within this image.
Extract all the text from this document scan.
Could you transcribe the words in this picture?

Frequently asked questions

Is the Image (Synthadoc) skill free?: Yes. The skill itself is free from axoviq-ai/synthadoc. SkillProof publishes the install command and an independent test verdict at no cost.
Does Image (Synthadoc) work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Tested · Didn't pass. This is a library module for the Synthadoc engine, not a Claude Code skill: its frontmatter is entry/class/triggers (not the CC name+description contract), and importing scripts/main.py from a bare install throws ModuleNotFoundError: No module named 'synthadoc'. It also needs a vision provider object wired in at construction, so it cannot run in Claude Code at all. Since Claude already reads image text natively and this only adds a broken indirection, it is worse than no skill for a CC user.
How do I install Image (Synthadoc)?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Image (Synthadoc) with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.