← Back to Skills Marketplace
145
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install pic2md
Description
Image to Markdown - extract text from images (PNG, JPG, WebP) to Markdown with OCR. Use when reading text from screenshots, photos, scanned pages, or any ima...
Usage Guidance
This skill appears coherent for doing OCR via the MinerU CLI, but it uploads images to MinerU's cloud for processing. Before installing or using it: 1) Do not send sensitive or confidential images unless you trust mineru.net's privacy policy and retention practices. 2) Verify the mineru-open-api package source (npm/Go repo) and publisher identity; prefer official releases and check repository/maintainer information on the homepage https://mineru.net. 3) Install and run the CLI initially in an isolated environment (container/VM) to inspect behavior and network traffic. 4) If you need on-device/offline OCR for sensitive data, consider local OCR tools (e.g., Tesseract) instead. 5) If you want additional assurance, ask the skill author for checksums or signed releases and review the mineru-open-api repository code before trusting it.
Capability Analysis
Type: OpenClaw Skill
Name: pic2md
Version: 1.0.0
The pic2md skill is a utility for performing OCR on images using the mineru-open-api tool. It functions by uploading images to the MinerU cloud API (mineru.net), a behavior that is explicitly documented in the SKILL.md file. The installation procedures via npm, uv, and go are standard, and the instructions for the AI agent are consistent with the stated purpose of image-to-markdown conversion without any signs of malicious intent, data theft, or unauthorized execution.
Capability Assessment
Purpose & Capability
Name/description: image→Markdown OCR. Required binary: mineru-open-api. Install entries (npm/uv/go) produce the mineru-open-api binary. All requested artifacts map to the stated purpose; no unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md instructs the agent to run mineru-open-api flash-extract against local files or URLs. This is within the OCR scope, but the CLI uploads images to MinerU's cloud API — so user data (images) will be transmitted off-host. The instructions do not ask the agent to read unrelated files, environment variables, or other system state.
Install Mechanism
Install spec uses public package ecosystems (npm, uv, go install) to install mineru-open-api, which is a normal/traceable mechanism but still carries the usual supply-chain risks (npm/go packages are third-party code). No direct download-from-random-URL or archive extraction is specified.
Credentials
No environment variables, credentials, or config paths are requested. The lack of secrets is proportionate to the stated functionality. The SKILL.md claims no API key or auth is required.
Persistence & Privilege
Skill is not always-enabled and does not request elevated persistence. There is no instruction to modify other skills or system-wide settings. The skill does rely on an external CLI binary being present.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install pic2md - After installation, invoke the skill by name or use
/pic2md - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of pic2md skill.
- Extracts text from images (PNG, JPG, WebP, BMP, TIFF) to Markdown using OCR.
- Supports both local image files and URLs; no API key or authentication required.
- Allows language hints (default: Chinese, use --language en for English).
- Processes images up to 10MB via MinerU Open API; processed data is not stored.
- Ideal for extracting or reading text from screenshots, scanned pages, and document photos.
Metadata
Frequently Asked Questions
What is Pic2md?
Image to Markdown - extract text from images (PNG, JPG, WebP) to Markdown with OCR. Use when reading text from screenshots, photos, scanned pages, or any ima... It is an AI Agent Skill for Claude Code / OpenClaw, with 145 downloads so far.
How do I install Pic2md?
Run "/install pic2md" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Pic2md free?
Yes, Pic2md is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Pic2md support?
Pic2md is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Pic2md?
It is built and maintained by tanis90 (@tanis90); the current version is v1.0.0.
More Skills