scanned-book-ocr SKILL.md skillA
scanned-book-ocr from hanzhangzzz/agent-skills-zh is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add hanzhangzzz/agent-skills-zh/scanned-book-ocr@git:20260911.2b498e3Pins git:20260911.2b498e3 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- hanzhangzzz/agent-skills-zh
- Path
scanned-book-ocr/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260911.2b498e3, committed Sep 11, 2026
- Size
- 4,426 bytes
- Repository stars
- 1
- License
- MIT
将纯图片或扫描版书籍 PDF 转为确定性、页码可追溯的文本，并在不降低识别质量的前提下基准测试并发、执行完整性校验和视觉抽检。用于整本扫描书 OCR、OCR 工具选型落地和给后续拆书/检索准备可信文本；不用于已有可靠文字层的普通 PDF，也不把未经回看原页的 OCR 当作精确引文。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 扫描书 OCR 把原始扫描 PDF 视为证据源，把 OCR 文本视为可搜索的派生层。默认运行固定版本的本地 `pdf-inspector + PP-OCRv6 Small`，不会上传页面。 ## 运行前检查 - 当前固定运行时仅支持 Apple Silicon macOS（arm64），使用 Python 3.12 或更新版本。 - 质量抽检需要 Poppler 的 `pdftoppm`；旋转纠错使用 macOS 自带 `sips`。先检查命令可用，缺失时说明依赖，不自动进行全局安装。 - 从本 SKILL.md 所在目录解析脚本路径；输入 PDF、基准报告和输出目录由任务指定，输出放在 skill/仓库目录之外。 - 只发布通用代码与合成样例。PDF、OCR 正文、纠错文件、含本地绝对路径的 manifest/基准报告、QA 图片与运行时缓存都留在本地，不随 skill 提交。 ## 核心约束 - 质量优先：先冻结模型、300 DPI 与文本规范化，再调页面并发。候选并发的逐页文本必须与单进程基线逐字节一致，否则淘汰。 - 保留页码：每页独立落盘，合并文本必须含 `=== PDF_PAGE NNNN ===` 标记。 - 可审计：`manifest.json` 记录原 PDF SHA-256、运行时版本、配置、逐页哈希、置信度、警告和耗时。 - 已完成结果可复用：转换命令检查来源哈希、运行时、DPI 和页数后返回已有 manifest；之后必须运行 validate 校验逐页及合并文件。当前不支持中途断点续跑；运行中断后保留原目录排查，使用新的输出目录重跑。 - 精确引文回看原页：OCR 可支持整书理解和候选检索，最终引用仍须核对 PDF 页面。 ## 工作流 1. 先运行 `scripts/ocr_book.py benchmark`。使用代表页测试 1/2/3 个外部进程；只从输出完全等价的配置中选择中位耗时最低者。 2. 运行 `scripts/ocr_book.py convert`。输出 `pages/`、`book.txt` 与 `manifest.json`。 3. 运行 `scripts/ocr_book.py validate --render-samples`。自动检查页数、哈希、低置信度、短页、重复页和合并文件，并渲染目录页、章节首页、固定间隔页及所有异常页。 4. 如果视觉抽检发现方向错误、噪声或实词错误，把旋转、整页替换和唯一匹配替换写进来源专属 corrections JSON，再运行 `scripts/ocr_book.py apply-corrections`；不要直接编辑页文件。应用后必须重新验证。 …
Read the whole file at its exact version.
How to install
mdr add hanzhangzzz/agent-skills-zh/scanned-book-ocr@sha256:5201355b40d0d1e9The line at the top of this page pins the label git:20260911.2b498e3, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_jp3tqvmtjzflopfo)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 11, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4426 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
hanzhangzzz/agent-skills-zh · 1 stars · license MIT · pushed 2026-10-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_jp3tqvmtjzflopfo GET https://markdownregistry.com/api/v1/resolve?ref=hanzhangzzz/agent-skills-zh/scanned-book-ocr GET https://markdownregistry.com/api/v1/blob/5201355b40d0d1e996247f6e880213ae76f454cd415e5133df8de9faacd88541
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.