mineru-document-extraction SKILL.md skillA
mineru-document-extraction from jialuohu/codex-toolbox is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add jialuohu/codex-toolbox/mineru-document-extraction@git:20260920.46ff053Pins git:20260920.46ff053 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- jialuohu/codex-toolbox
- Path
plugins/research-tools/skills/mineru-document-extraction/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260920.46ff053, committed Sep 20, 2026
- First version recorded
- Jul 14, 2026
- Size
- 5,405 bytes
- Repository stars
- 13
- License
- none declared
Use MinerU for one complex, scanned, OCR-heavy, or layout-sensitive local document, including bounded pages and checksum-verified extraction artifacts.
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 Document Extraction Extract one local document into an explicit review directory. Preserve the source and treat `mineru-run.json` as the extraction contract. ## Route the document - Use this skill for complex, scanned, OCR-heavy, table/formula-rich, or layout-sensitive documents, including multi-column pages and mixed text, figures, and OCR. - Prefer a simpler local text extractor for straightforward born-digital documents when layout reconstruction has no value. - Reject URLs and directories. Download or select exactly one supported local file before running the wrapper. - Use Zotero tools instead when the task is primarily about an item already saved in the user's Zotero library. ## Run quality-first extraction Before the first parse on a device, run the toolbox's read-only doctor: ```bash <toolbox-root>/scripts/setup-mineru.sh --check ``` If the doctor is not ready, report the missing runtime, accelerator, disk, or model state. Do not run `--install` or `--download-models` unless the user separately requests that setup action. Require a fresh, empty output directory outside every Git checkout and outside any Obsidian vault, then run: ```bash …
Read the whole file at its exact version.
How to install
mdr add jialuohu/codex-toolbox/mineru-document-extraction@sha256:3b41c730b1687beaThe line at the top of this page pins the label git:20260920.46ff053, 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_euojsxmebbq6q7py)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Jul 14, 2026 and Sep 20, 2026, about one every 34 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260920.46ff053 latest | 2026-09-20 | 46ff053 | 5,405 B | A | view · diff |
| git:20260906.9af3950 | 2026-09-06 | 9af3950 | 5,115 B | A | view · diff |
| git:20260714.e68d884 | 2026-07-14 | e68d884 | 5,270 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 (5405 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
jialuohu/codex-toolbox · 13 stars · license none declared · pushed 2026-10-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_euojsxmebbq6q7py GET https://markdownregistry.com/api/v1/resolve?ref=jialuohu/codex-toolbox/mineru-document-extraction GET https://markdownregistry.com/api/v1/blob/3b41c730b1687bea41f5817d419e7da58572292f73c66f1c89b4a0a9b5d57c68
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.