vlm-ocr SKILL.md skillA
vlm-ocr from scdenney/open-science-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add scdenney/open-science-skills/vlm-ocr@git:20261018.4ed74bePins git:20261018.4ed74be in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- scdenney/open-science-skills
- Path
codex/vlm-ocr/SKILL.md- Versions recorded
- 6
- Latest version
- git:20261018.4ed74be, committed Oct 18, 2026
- First version recorded
- Sep 2, 2026
- Size
- 78,339 bytes
- Repository stars
- 69
- License
- a license file GitHub does not identify
OCR scanned or image-only corpora with vision-language models in four phases: `triage` inventories the scans, identifies script and language, and shortlists models by script, hardware, and data constraints; `evaluate` picks a system by measured CER/WER against ground truth, using born-digital twins, a second reader, and decision rules set in advance; `run` builds the production pipeline; and `clean` removes model artifacts, audits what every cleaning rule deletes, corrects with rule-based and…
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
# VLM-OCR: Scanned Corpora from Page Images to Research-Usable Text ## Instructions This skill covers the whole path from a corpus of page images to text an analysis can consume: knowing what the scans are and which models can read them (`triage`), choosing an OCR system by measurement (`evaluate`), running the chosen model across the corpus (`run`), and correcting and documenting its output (`clean`). **Use this skill only for scanned or image-only documents.** Born-digital PDFs, Word files, and anything carrying an embedded text layer belong to `$doc-to-markdown`, which extracts the text directly and needs no model at all. A PDF yielding under ~300 extractable characters per page is a scan. So is a PDF whose text is an invisible layer over page-sized images: that is an earlier OCR, usually worse than a current model, and `triage` detects it. …
Read the whole file at its exact version.
How to install
mdr add scdenney/open-science-skills/vlm-ocr@sha256:41f53509480d7a26The line at the top of this page pins the label git:20261018.4ed74be, 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_zsnnj5kn4i67xp4d)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Sep 2, 2026 and Oct 18, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261018.4ed74be latest | 2026-10-18 | 4ed74be | 78,339 B | A | view · diff |
| git:20261018.b6541ff | 2026-10-18 | b6541ff | 75,645 B | A | view · diff |
| git:20261017.4336785 | 2026-10-17 | 4336785 | 74,005 B | A | view · diff |
| git:20261017.134d358 | 2026-10-17 | 134d358 | 72,785 B | A | view · diff |
| git:20261008.697c89f | 2026-10-08 | 697c89f | 47,237 B | A | view · diff |
| git:20260902.da5a263 | 2026-09-02 | da5a263 | 49,042 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 (78339 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
scdenney/open-science-skills · 69 stars · license a license file GitHub does not identify · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_zsnnj5kn4i67xp4d GET https://markdownregistry.com/api/v1/resolve?ref=scdenney/open-science-skills/vlm-ocr GET https://markdownregistry.com/api/v1/blob/41f53509480d7a26a430e1f28c58f8cd8e5528f4040dc7e1d2ac122e5ccacbbb
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.
More from scdenney/open-science-skills
Every file in scdenney/open-science-skills