mineru-pdf-parser SKILL.md skillA
mineru-pdf-parser from fission21/miji is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add fission21/miji/mineru-pdf-parser@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- fission21/miji
- Path
skills/mineru-pdf-parser/SKILL.md- Versions recorded
- 3
- Latest version
- v1.0.0, committed Sep 1, 2026
- First version recorded
- Aug 27, 2026
- Size
- 4,244 bytes
- Repository stars
- 14
- License
- MIT
用 MinerU 解析 PDF 为 Markdown/JSON 时用。含国内模型下载、M1 内存调优、踩坑速查。.
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
# MinerU PDF 解析（Mac M1 部署 + 使用） ## 触发条件 - 需要把 PDF（含扫描件/图片型 PDF）解析成 Markdown、JSON、结构化文本 - 用户发来 PDF 要提取内容/做知识库 - MinerU 报模型缺失/下载失败 ## 环境（2026-08-27 实测，macOS Apple Silicon） - 位置：`<你的工作目录>/mineru-venv/`（独立 venv，mineru 3.4.5） - 模型目录：`<你的工作目录>/mineru-models/`（15 个文件 1.0GB，sha256 全部验证过） - 配置：`~/mineru.json` → `models-dir.pipeline: <你的工作目录>/mineru-models` - 中文公式支持默认关（`MINERU_FORMULA_CH_SUPPORT` 未设时用 unimernet_small 而非 pp_formulanet） ## 基本用法 ```bash unset PYTHONPATH # 必须！否则加载 Hermes venv 的包 <你的工作目录>/mineru-venv/bin/mineru \ -p "输入.pdf" -o 输出目录 -b pipeline ``` - `-b pipeline`：本地模型解析（默认 hybrid-engine 需要 VLM 模型，别用） - 输出：`输出目录/<文件名>/auto/` 下含 `*.md`、`*_model.json`、`*_span.pdf`、`images/` - 252 页书全量解析约 4-6 分钟（M1 Pro，**原生文字版**） - **扫描版中文书慢 3-4 倍**：走 OCR 逐页识别，实测 484 页扫描书 >20 分钟——属正常，别当卡死杀进程；窗口 32 全程稳定不崩 - 长书推荐后台跑：任务尾加 `echo "MINERU_EXIT=$?"` 便于判定成功；启动后先确认过了模型加载阶段（早崩都是 PYTHONPATH/模型缺失类），之后等完成通知即可 - 大文件可拆段并行（2 worker 实测 2.1x，32GB 上限 2 个）：见 MiJi 主 skill「大文件并行解析」与 `tools/split_pdf.py` ## ⚠️ 关键坑（全部实测踩过） ### 1. 模型下载失败（国内网络） …
Read the whole file at its exact version.
How to install
mdr add fission21/miji/mineru-pdf-parser@sha256:d8944feb5ab7fc24The line at the top of this page pins the label v1.0.0, 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_zsguzn5bfaqy5twj)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Aug 27, 2026 and Sep 1, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-09-01 | 3eeb4c7 | 4,244 B | A | view · diff |
| v1.0.0 | 2026-08-27 | 2fab4b7 | 3,709 B | A | view · diff |
| v1.0.0 | 2026-08-27 | f0a159e | 3,724 B | A | view |
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 (4244 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
fission21/miji · 14 stars · license MIT · pushed 2026-09-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_zsguzn5bfaqy5twj GET https://markdownregistry.com/api/v1/resolve?ref=fission21/miji/mineru-pdf-parser GET https://markdownregistry.com/api/v1/blob/d8944feb5ab7fc242c86743949e22266548926a2a5eb42fa0ea0585738e7bf64
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.