Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Yuleno/skills --skill document-to-markdown-visual-qagit clone --depth 1 https://github.com/Yuleno/skillsWrote 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/yuleno/skills/document-to-markdown-visual-qa)<a href="https://agentmods.dev/skills/yuleno/skills/document-to-markdown-visual-qa"><img src="https://agentmods.dev/badge/skills/yuleno/skills/document-to-markdown-visual-qa/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/yuleno/skills/document-to-markdown-visual-qa"><img src="https://agentmods.dev/badge/skills/yuleno/skills/document-to-markdown-visual-qa.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 | $0.00084 | $0.01499 |
| Opus 5.5 | $0.00034 | $0.00600 |
| Sonnet 5.5 | $0.00017 | $0.00300 |
| Haiku 4.5 | $0.00008 | $0.00150 |
Grade A, and why
document-to-markdown-visual-qa 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 1mo 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document to Markdown Visual QA
Produce one semantically faithful Markdown document for AI and human reading. Treat the source PDF and rendered pages as authority; treat every parser output as a candidate.
1. Run the visual preflight
Pause before rendering pages for a remote model or dispatching visual workers. Ask the user:
- Can the current model inspect images directly?
- If not, which visual MCP/tool is available?
- May that route receive document pages, and may it be called concurrently?
- What
max_workerslimit should apply, or should the harness choose its safe default?
Record visual_route as native, mcp:<tool-name>, or none. Proceed without visual review only when the user selects none; the final status must then be Needs Review unless every visual fidelity requirement is otherwise proven.
Completion criterion: the user has explicitly selected the route and upload/concurrency boundary for this run.
2. Check dependencies
Run:
python scripts/preflight.py --input "<source.pdf>" [--renderer-python "<python-with-pymupdf>"]
Require MarkItDown, pypdf, and pdfplumber for the baseline. Require PyMuPDF, pypdfium2, or a working pdftoppm for rendering. The conversion and rendering interpreters may differ; when the harness supplies a renderer in another Python, pass that interpreter with --renderer-python and run render_pdf.py with it. Report missing dependencies and wait for installation permission; do not install them automatically. Keep Docling and other specialized parsers optional.
Completion criterion: the preflight returns ready: true, or the user accepts an explicitly degraded route.
3. Prepare the immutable baseline
Run with the Python interpreter that contains MarkItDown:
python scripts/prepare_pdf.py "<source.pdf>"
This creates document.raw.md, an initial document.reviewed.md, a resumable manifest, and a hash-keyed work directory. Preserve document.raw.md unchanged. Generate parser candidates under the work directory when a specialized parser is available; never replace the baseline with a candidate.
What ships with it
12 files 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.
- agents/openai.yaml 267 B
- references/fidelity-rules.md 2.3 KB
- references/worker-contract.md 2.4 KB
- scripts/build_review_units.py 3.6 KB runs code
- scripts/common.py 1.8 KB runs code
- scripts/extract_pdf_images.py 2.1 KB runs code
- scripts/extract_pdf_text.py 2.5 KB runs code
- scripts/preflight.py 2.9 KB runs code
- scripts/prepare_pdf.py 4.7 KB runs code
- scripts/render_pdf.py 4.2 KB runs code
- scripts/validate_output.py 9.1 KB runs code
- scripts/validate_worker_results.py 3.9 KB runs code
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.
- 1mo ago First seen · 106 lines · 84 tokens per session scan A ff0b3b582451
document-to-markdown-visual-qa is a skill published in the GitHub repository Yuleno/skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 84 tokens to every session and 1,499 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.
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.
meta-web-to-pdf-briefing
Render a topic into a distributable PDF briefing in three steps: web search → bullet summary → styled PDF. Trigger when the user asks for a PDF briefing on a single topic.
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…