paperlab-source-pdf-to-html skillC
paperlab-source-pdf-to-html is agent-read markdown (skill) from equinor/neqsim.
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.
What the file says
# Skill: PaperLab Source PDF to HTML ## Purpose Convert or plan conversion of source PDFs into clean, searchable HTML for PaperLab books. Use this when lecture PDFs, public reports, exam PDFs, or standards excerpts need to be searchable by agents and linked to chapter figures, captions, and source manifests. ## Inputs - Book directory with `source_manifest.json`, or a `--source-root` folder. - PDF files from lectures, exercises, exams, public reports, or approved reference documents. - Optional OCR output for scanned/image-only PDFs. ## Workflow 1. Inventory source files with `book-source-inventory`. 2. Run `python paperflow.py book-source-pdf-html-plan <book_dir>` to create a conversion manifest. 3. Convert PDFs using the selected local converter. A robust converter should: - preserve the source PDF, - extract text and images, - fall back to OCR or PyMuPDF when table-heavy PDFs fail, - write HTML under an `_HTML/` folder next to the source category. 4. Feed converted HTML and extracted images into `technical-figure-understanding` and `figure_dossier.json`. ## Output - `source_pdf_html_plan.json` - `source_pdf_html_plan.md` …
Read the whole file at its exact version.
How to install
mdr add equinor/neqsim/paperlab-source-pdf-to-html@git:20260919.77c34a0mdr add equinor/neqsim/paperlab-source-pdf-to-html@sha256:262fad77871f257ePin 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.
[](https://markdownregistry.com/a/art_kdqdbvl65ihwefb2)
1 badge views in 30 days
Versions
Audit of the latest version
- fail: Frontmatter block present
- fail: Frontmatter declares a name
- fail: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (1825 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
equinor/neqsim · 155 stars · license Apache-2.0 · pushed 2026-09-24 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_kdqdbvl65ihwefb2 GET https://markdownregistry.com/api/v1/resolve?ref=equinor/neqsim/paperlab-source-pdf-to-html GET https://markdownregistry.com/api/v1/blob/262fad77871f257e2daa28e7ab930534e58f94d14a605b6e75f8d86c8878f8a0
Your agent 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.