legal-ocr

github:cat-xierluo/legal-skills · first committed 2026-05-20 · source · badge

本技能应在用户需要 OCR、扫描识别、图片文字识别、文档识别，或将 PDF、图片、Office 文档、URL 转换为 Markdown 时使用。检测到法律材料时可进行保守的法律术语与文书结构优化。不要用于法律事实判断、补写缺失内容、语义改写、印章深度识别或图表实体分析。

Skill Health: not yet scored

Listed, not yet scored. This skill has no public model test yet. It is in the scoring queue; submitted skills go first, then the most-installed.

Version history

8 commits to this file on GitHub (newest first).

2026-09-18 · commit dfacabf · feat: 本地 RapidOCR 兜底三件套（pdf-processor 双层 PDF / legal-ocr 转 Markdown）+ pdf-organizer 页引用模型 (#168)
2026-07-10 · commit 4d30bad · [w1] feat(legal-ocr): v1.5.0 PDF 原生文本层双路径 (#41)
2026-06-14 · commit 0c7bb33 · feat(legal-ocr): v1.4.1→1.4.4 修复 cron 跑批 Invalid port 死循环
2026-06-08 · commit 0ef1f6a · Revert "chore: archive removed skills (mineru-ocr, paddle-ocr, svg-book-illustrator, yuandian-law-search)"
2026-06-08 · commit d854146 · chore: archive removed skills (mineru-ocr, paddle-ocr, svg-book-illustrator, yuandian-law-search)
2026-06-06 · commit 2876174 · feat(legal-ocr): auto-retry on transient network errors
2026-06-03 · commit bc106eb · refactor(legal-ocr): v1.3.2 archive 移除 input 副本，改为 metadata 记录
2026-05-20 · commit b22a2fa · feat(legal-ocr): 新增统一 OCR Skill v1.3.1

Archived snapshots