Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jin-bo/guanlan/pdf-to-markdown)<a href="https://agentmods.dev/skills/jin-bo/guanlan/pdf-to-markdown"><img src="https://agentmods.dev/badge/skills/jin-bo/guanlan/pdf-to-markdown/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jin-bo/guanlan/pdf-to-markdown"><img src="https://agentmods.dev/badge/skills/jin-bo/guanlan/pdf-to-markdown.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00146 | $0.01722 |
| Opus 5 | $0.00073 | $0.00861 |
| Sonnet 5 | $0.00029 | $0.00344 |
| Haiku 4.5 | $0.00015 | $0.00172 |
Grade A, and why
pdf-to-markdown scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 | mineru |
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 |
✅ | ✅ | ✅ | |
| Word | .docx |
✅ | ✅ | — |
| PowerPoint | .pptx |
✅ | ✅ | — |
| Excel | .xlsx |
✅ | ✅ | — |
| E-book | .epub |
✅ | ✅ | — |
| Web | .html, .htm |
✅ | ✅ | — |
| Images | .png, .jpg, .jpeg, .webp, .tif, .tiff, .bmp, .gif |
✅ | ✅ | — |
The pure-python tier only handles PDFs with a text layer (no OCR). A scanned PDF with no text layer fails the python tier and requires MinerU or marker.
Quick Start
python scripts/convert.py /path/to/document.pdf # auto: mineru -> marker -> python
python scripts/convert.py /path/to/report.docx
python scripts/convert.py /path/to/slides.pptx
The output .md path is printed on stdout; progress/backend logs go to stderr.
Setup
Tier 1 — MinerU (preferred)
pip install -U "mineru[core]"
MinerU downloads its models on first run. CLI: mineru -p <input> -o <output_dir>.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 183 lines · 146 tokens per session scan A 6c11b2c8b5ed
pdf-to-markdown is a skill published in the GitHub repository jin-bo/guanlan (11 stars, last pushed 23d ago), licensed Apache-2.0. It adds 146 tokens to every session and 1,722 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.