Well-documented PaddleOCR plugin with credential handling and workspace containment, worth installing for OCR tasks in D
Code quality7
README documents a dev workflow (pnpm install/check, compileall, pack dry-run) and committed lib/ artifacts, but no test suite or CI config is visible.
Security8
Tokens are stored via DSH Credentials and never returned to the browser, with real-path workspace containment and an explicit data-boundary disclosure, though remote calls still send file bytes to an external service.
Utility8
Provides two native OCR tools (text recognition and document/layout parsing) plus a GUI, addressing a common need for extracting text and tables from images and PDFs.
Maintenance7
Last updated 2026-08-15, not archived, and the README references a COMPATIBILITY.md tracking current DSH window results, indicating ongoing upkeep.
Docs8
README covers install commands, prerequisites, GUI setup steps, a one-prompt agent install, data boundaries, and development commands, though it lacks usage examples of tool outputs.
Generated by AI after reading the project README, as a decision aid; neutral scores are given when information is thin. Not an official endorsement.
PaddleOCR skills for DeepSeek Harness with native tools and GUI configuration
How popular is dsh-PaddleOCR-Skills?
dsh-PaddleOCR-Skills has 4 stars and 0 forks on GitHub, last updated 2026-08-15.
What license does dsh-PaddleOCR-Skills use?
dsh-PaddleOCR-Skills is distributed under the Apache-2.0 license.
Is dsh-PaddleOCR-Skills compatible with DeepSeek Harness?
dsh-PaddleOCR-Skills is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
/10类依据
项目类型技能
功能/10类文件与数据
规则置信度High
System reads GitHub Topics first, then compares against the in-site category dictionary and word-root rules. Current match:agent-skills、ocr、paddleocr。
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | The strongest vision add-on plugin for DeepSeek Harness, adding vision capability to text-only models like DeepSeek and GLM, paste an image and get structured JSON evidence (OCR, layout, semantics).
[dsh] A more powerful visual toolkit for text-only models: one-line install and use, paste images for direct recognition, multi-image Q&A, screenshot-to-frontend UI restoration, and more|DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.