pdf-to-markdown SKILL.md skillA
pdf-to-markdown from jin-bo/guanlan is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add jin-bo/guanlan/pdf-to-markdown@git:20261017.db3d7c4Pins git:20261017.db3d7c4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- jin-bo/guanlan
- Path
skills/pdf-to-markdown/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261017.db3d7c4, committed Oct 17, 2026
- First version recorded
- Jun 10, 2026
- Size
- 9,295 bytes
- Repository stars
- 14
- License
- Apache-2.0
Convert documents (PDF, DOCX, PPTX, XLSX, EPUB, HTML, images) to Markdown using a tiered backend strategy: MinerU first, then marker-pdf, then a pure-python pypdf fallback. Trigger on: "convert PDF to markdown", "PDF to markdown", "DOCX/Word to markdown", "PPTX to markdown", "XLSX/Excel to markdown", "convert document to markdown", "transform to text", "mineru", "marker-pdf", "extract markdown from PDF", or any mention of a .pdf/.docx/.pptx/.xlsx/.epub/.html/image file when markdown output is…
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
# Document to Markdown ## Overview Converts documents to high-quality Markdown using a **tiered backend strategy** — the best available tool wins, and the script degrades gracefully when a tool is missing or fails: | Tier | Backend | Command | When it runs | Strength | |---|---|---|---|---| | 1 | **MinerU** (4.x preferred, 3.x supported) | `mineru parse` / `mineru -p` | Used first whenever on `PATH` | Highest-fidelity layout, tables, formulas, OCR | | 2 | **marker-pdf** | `marker_single` | Fallback if MinerU missing/fails | Strong layout + optional Gemini LLM cleanup | | 3 | **pure-python** | `pypdf` | Last resort | Plain text-layer extraction (PDF only, no OCR) | With the default `--backend auto`, the script tries tiers **1 → 2 → 3** in order, moving to the next one when a backend is **unavailable** (not installed) *or* **fails** (non-zero exit / no output). It prints which backend produced the result on `stderr` (`[done] backend=...`) and the output `.md` path on `stdout`. Force a single tier with `--backend mineru|marker|python`. ## Supported Input Formats | Category | Extensions | MinerU | marker | python | |---|---|:--:|:--:|:--:| | PDF | `.pdf` | ✅ | ✅ | ✅ | …
Read the whole file at its exact version.
How to install
mdr add jin-bo/guanlan/pdf-to-markdown@sha256:c19f7d29e019f3c8The line at the top of this page pins the label git:20261017.db3d7c4, 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_2g5hbtuvvvaihxho)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jun 10, 2026 and Oct 17, 2026, about one every 129 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261017.db3d7c4 latest | 2026-10-17 | db3d7c4 | 9,295 B | A | view · diff |
| git:20260610.f3f3ec8 | 2026-06-10 | f3f3ec8 | 6,435 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 (9295 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
jin-bo/guanlan · 14 stars · license Apache-2.0 · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_2g5hbtuvvvaihxho GET https://markdownregistry.com/api/v1/resolve?ref=jin-bo/guanlan/pdf-to-markdown GET https://markdownregistry.com/api/v1/blob/c19f7d29e019f3c871b11432013fc19c85c15c964d1021f55f3f556ae321969c
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.