← Back to Skills Marketplace
Image Ocr
by
wangziiiiii
· GitHub ↗
· v1.0.1
· MIT-0
333
Downloads
1
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install siliconflow-image-ocr
Description
SiliconFlow OCR for screenshots, receipts, forms, and tables with mixed Chinese/English extraction. Use when users ask 提取图片文字/识别截图/OCR表格/票据识别. Supports local...
Usage Guidance
This skill sends entire images (local files are base64-encoded into data: URIs) and prompts to SiliconFlow's API; do not use it with images that contain highly sensitive personal, financial, or legal data unless you trust SiliconFlow and your key handling. Note the registry metadata omits the required SILICONFLOW_API_KEY — you'll need to set the env var or put the key at ~/.openclaw/secrets/siliconflow_api_key (recommend file permissions 600). If you require offline OCR or must avoid external transmission, do not install. Otherwise: verify the vendor URL, generate an API key with appropriate scope/rotation, inspect network policy and logs, and consider running the script in a sandboxed environment first.
Capability Analysis
Type: OpenClaw Skill
Name: siliconflow-image-ocr
Version: 1.0.1
The skill provides legitimate OCR functionality using the SiliconFlow API. The script `scripts/paddleocr_vl.py` implements standard multi-modal request logic, handling local file reading and remote URL processing without any signs of obfuscation, data exfiltration, or unauthorized execution. Credential handling for the API key follows the documented OpenClaw patterns (environment variables or local secret files), and the network communication is restricted to the official SiliconFlow endpoint.
Capability Assessment
Purpose & Capability
Name/description (image OCR for screenshots/receipts/forms, Chinese/English) matches the included script and instructions. The script calls SiliconFlow's OCR model and accepts local files, URLs, or base64 inputs — all coherent with the stated purpose.
Instruction Scope
SKILL.md and the script instruct the agent to read an API key (env var or a local file) and to POST images (local files encoded as data: URIs or remote URLs) to https://api.siliconflow.cn/v1/chat/completions. This is expected for a hosted OCR service, but it means image contents (possibly sensitive) are sent to an external service.
Install Mechanism
No install spec or remote downloads. The skill is instruction-only with one bundled Python script; nothing will be downloaded or installed by the registry metadata.
Credentials
Runtime requires a single service credential (SILICONFLOW_API_KEY or a local file at ~/.openclaw/secrets/siliconflow_api_key), which is proportionate for a remote API. However, the registry metadata incorrectly lists no required env vars — this mismatch should be fixed so users know an API key is required before use.
Persistence & Privilege
always is false; the skill does not request elevated or permanent platform-wide privileges and does not modify other skills. It only reads its recommended credential file when present.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install siliconflow-image-ocr - After installation, invoke the skill by name or use
/siliconflow-image-ocr - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Sync latest local fixes and docs
v1.0.0
Launch public skill with clearer landing copy
Metadata
Frequently Asked Questions
What is Image Ocr?
SiliconFlow OCR for screenshots, receipts, forms, and tables with mixed Chinese/English extraction. Use when users ask 提取图片文字/识别截图/OCR表格/票据识别. Supports local... It is an AI Agent Skill for Claude Code / OpenClaw, with 333 downloads so far.
How do I install Image Ocr?
Run "/install siliconflow-image-ocr" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Image Ocr free?
Yes, Image Ocr is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Image Ocr support?
Image Ocr is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Image Ocr?
It is built and maintained by wangziiiiii (@wangziiiiii); the current version is v1.0.1.
More Skills