scdenney/open-science-skills · plugin/skills/vlm-ocr/SKILL.md

vlm-ocr skillA

vlm-ocr is agent-read markdown (skill) from scdenney/open-science-skills: OCR a scanned or image-only corpus with vision-language models, in three phases — evaluate compares candidate OCR systems against stratified human ground truth and picks one on measured CER/WER; run builds the production pipeline (model selection, image handling, prompts, architecture, batching, accuracy evaluation, reproducibility); clean corrects the raw OCR text with LLM and rule-based passes, quality diagnostics, multilingual handling, and span-level provenance. Use when the question is whic.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add scdenney/open-science-skills/vlm-ocr@git:20260905.c12f077
Exact content
mdr add scdenney/open-science-skills/vlm-ocr@sha256:d877ee7fb92ca7a3

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_oczjmcm3gmh4yk7s.svg)](https://markdownregistry.com/a/art_oczjmcm3gmh4yk7s)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260905.c12f077 latest2026-09-05 c12f077 49,876 BA view · diff
git:20260902.da5a2632026-09-02 da5a263 49,845 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (49876 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

GitHub

scdenney/open-science-skills · 54 stars · license NOASSERTION · pushed 2026-09-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_oczjmcm3gmh4yk7s
GET https://markdownregistry.com/api/v1/resolve?ref=scdenney/open-science-skills/vlm-ocr
GET https://markdownregistry.com/api/v1/blob/d877ee7fb92ca7a3a3321ee52e9b29d7dc1b22a3244a5406b0e4c796f9c8f940