Profile My skills Saved Collections Edit profile Submit a skill

← all publishers

okraocr

@okraocr source repo

5 published skills

  1. ▌
    Okrapdf · okraocr bundle
    Use OkraPDF as a Codex-native interactive PDF panel. Trigger when the user wants to open a PDF in OkraPDF inside Codex, inspect the current PDF selection, extract or ask about a selected table/region/text span, or reproduce the MagicPath-style "select in the web app, act from the agent" workflow with `okra bridge serve`, `okra select`, `okra ask --selection`, and `okra extract --selection`.
    0
    installs
  2. ▌
    Okra Curl · okraocr
    HTTP/curl cookbook for the OkraPDF REST API — workflow-bound document uploads, passive file assets, chat completions, structured extraction, collections, and exports.
    0
    installs
  3. ▌
    Okra Wiki · okraocr
    Generate a static wiki from an OkraPDF collection — export markdown, synthesize articles, build cross-references, deploy to Cloudflare Pages or any static host.
    0
    installs
  4. ▌
    Okra Create · okraocr bundle
    Generate designed PDFs via OkraPDF's pdf-render-agent — baked-design reports (magazine, editorial, report, poster), custom agent-written HTML covers via Cloudflare Browser Rendering, or fully composed output through codemode. Triggered by "create a pdf", "generate a report", "design a cover", "make a pdf with html", or any PDF-generation task where visual quality matters.
    0
    installs
  5. ▌
    PDF Parse QA · okraocr bundle
    Block-by-block A/B testing for PDF / VLM document parsers. Bring your own PDF and your own parser (HuggingFace Qwen2.5-VL, Gemini Flash, Mistral OCR, Reducto, LlamaParse, Azure Document Intelligence, AWS Textract, Unstructured, MinerU, Docling — or anything that emits text+bbox), run them through the same hosted validator UI, vote pass/partial/fail on every block with `↑↓ 1/2/3`, export JSON, compare per-label pass-rates. Triggered by "compare PDF parsers", "pick a VLM for PDFs", "bake-off Reducto vs LlamaParse", "evaluate Qwen2.5-VL on documents", "ParseBench-style accuracy QA", "which OCR is best for my docs". No SaaS account required — adapters produce a tiny JSON file, the hosted widget at embed.okrapdf.com renders it. Inspired by Label Studio + Daloopa + Adobe Acrobat "Find Suspects" review queues.
    0
    installs