ocr-super-surya SKILL.md skillA

ocr-super-surya from aktsmm/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add aktsmm/agent-skills/ocr-super-surya@git:20261004.e1c4ed1

Pins git:20261004.e1c4ed1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
aktsmm/agent-skills
Path
ocr-super-surya/SKILL.md
Versions recorded
4
Latest version
git:20261004.e1c4ed1, committed Oct 4, 2026
First version recorded
Jul 5, 2026
Size
8,378 bytes
Repository stars
26
License
a license file GitHub does not identify

GPU-optimized OCR using Surya. Use when extracting text from images/screenshots, recovering image-only content in PDFs or slides, or inspecting multilingual document layouts. Preserve source locations and report recognition gaps separately from verified text.

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

# OCR Super Surya

GPU-optimized OCR using [Surya](https://github.com/datalab-to/surya).

## When to Use

- **OCR**, **extract text from image**, **text recognition**, **画像から文字**
- Extracting text from screenshots, photos, or scanned images
- Processing PDFs with embedded images
- Multi-language document OCR (90+ languages including Japanese)

## Extraction and Verification

1. Confirm the input scope and a non-public output location for sensitive material; preserve source files and do not bypass document protection. Text redaction does not anonymize retained images or authorize redistribution.
2. Extract native PDF/slide text first, including slide notes where present. A nonempty text layer can still omit screenshots, diagrams, or image-only pages; inventory those gaps before selecting OCR targets. For image targets, resolve the highest-resolution original before recognizing: chat attachments and thumbnails are downscaled re-encodes, so locate the original capture by timestamp, then crop the region of interest and upscale 4-7x (LANCZOS). Dense CJK glyphs collapse at screen scale.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add aktsmm/agent-skills/ocr-super-surya@sha256:72f23cc36be2102a

The line at the top of this page pins the label git:20261004.e1c4ed1, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_blzkmr77qjy4a67f.svg)](https://markdownregistry.com/a/art_blzkmr77qjy4a67f)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, between Jul 5, 2026 and Oct 4, 2026, about one every 30 days.

versioncommittedcommitsizeaudit
git:20261004.e1c4ed1 latest2026-10-04 e1c4ed1 8,378 BA view · diff
git:20260909.40ebe5d2026-09-09 40ebe5d 7,912 BA view · diff
git:20260905.653bd152026-09-05 653bd15 7,466 BA view · diff
git:20260705.848fd9b2026-07-05 848fd9b 5,797 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the 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 (8378 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

aktsmm/agent-skills · 26 stars · license a license file GitHub does not identify · pushed 2026-11-04 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_blzkmr77qjy4a67f
GET https://markdownregistry.com/api/v1/resolve?ref=aktsmm/agent-skills/ocr-super-surya
GET https://markdownregistry.com/api/v1/blob/72f23cc36be2102a5e9c1cb2a69715f63213c2a6d50070c159d1be17a37cc071

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 aktsmm/agent-skills

agentic-workflow-guide SKILL.md skill
aktsmm/agent-skills · agentic-workflow-guide/SKILL.md · Design, review, and debug agent workflows, and decide when a request should use a prompt, instruction, skill, agent, or…
git:20261104.b6d2e8b · audit A · 26 stars
ai-cli-benchmark SKILL.md skill
aktsmm/agent-skills · ai-cli-benchmark/SKILL.md · Design, run, and review fair performance, token, and cost comparisons across GitHub Copilot CLI, Codex CLI, and direct…
git:20261022.387b228 · audit A · 26 stars
analyze-copilot-sessions SKILL.md skill
aktsmm/agent-skills · analyze-copilot-sessions/SKILL.md · Analyze historical VS Code GitHub Copilot Chat sessions by model, reasoning effort, AIU, time, reliability, workflow…
git:20261026.133d3e3 · audit A · 26 stars
animated-infographic SKILL.md skill
aktsmm/agent-skills · animated-infographic/SKILL.md · Create reproducible animated infographic GIFs from structured data or measured results, with audience-language labels…
git:20261004.e1c4ed1 · audit A · 26 stars
archify SKILL.md skill
aktsmm/agent-skills · archify/SKILL.md · Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable…
v3.0 · audit A · 26 stars
ascii-banner SKILL.md skill
aktsmm/agent-skills · ascii-banner/SKILL.md · Generate ASCII-art text banners for terminals, READMEs, and CLI startup messages. Use when a user asks for an ASCII…
git:20261001.2b7a422 · audit A · 26 stars
azure-advisor-report SKILL.md skill
aktsmm/agent-skills · azure-advisor-report/SKILL.md · Generate Azure environment monthly report (Markdown + PowerPoint) from Azure Advisor and Cost Management API. Use when…
git:20261004.de613c1 · audit A · 26 stars
azure-env-builder SKILL.md skill
aktsmm/agent-skills · azure-env-builder/SKILL.md · [Alpha] Experimental Azure environment builder for infrastructure and deployment design. Use when building Azure…
git:20261004.e1c4ed1 · audit A · 26 stars
azure-infra-validation SKILL.md skill
aktsmm/agent-skills · azure-infra-validation/SKILL.md · Build and validate Azure infrastructure in a lab or sandbox using Azure CLI and official Microsoft docs. Use when…
git:20261022.c08e9e0 · audit A · 26 stars
azure-screenshot-mask SKILL.md skill
aktsmm/agent-skills · azure-screenshot-mask/SKILL.md · Mosaic environment-sensitive areas (tenant name, user avatar, subscription name / ID, resource group, internal…
git:20261004.e1c4ed1 · audit A · 26 stars
azure-troubleshooting SKILL.md skill
aktsmm/agent-skills · azure-troubleshooting/SKILL.md · Investigate Azure incidents and service degradations with a read-only workflow using Azure CLI, Resource Health…
git:20261004.e1c4ed1 · audit A · 26 stars
azure-update-customer-pptx SKILL.md skill
aktsmm/agent-skills · azure-update-customer-pptx/SKILL.md · Build a customer-facing Azure Update PowerPoint from Azure Updates MCP results, including customer classification…
git:20261014.48a6cca · audit A · 26 stars

Every file in aktsmm/agent-skills

Browse by kind, by grade A, or by owner.