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 AlterLab-IEU/AlterLab-Academic-Skills --skill alterlab-markitdowngit clone --depth 1 https://github.com/AlterLab-IEU/AlterLab-Academic-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/alterlab-ieu/alterlab-academic-skills/alterlab-markitdown)<a href="https://agentmods.dev/skills/alterlab-ieu/alterlab-academic-skills/alterlab-markitdown"><img src="https://agentmods.dev/badge/skills/alterlab-ieu/alterlab-academic-skills/alterlab-markitdown/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/alterlab-ieu/alterlab-academic-skills/alterlab-markitdown"><img src="https://agentmods.dev/badge/skills/alterlab-ieu/alterlab-academic-skills/alterlab-markitdown.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 301 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium Privilege Escalation · line 446 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00180 | $0.04182 |
| Opus 5.5 | $0.00072 | $0.01673 |
| Sonnet 5.5 | $0.00036 | $0.00836 |
| Haiku 4.5 | $0.00018 | $0.00418 |
Grade A, and why
alterlab-markitdown 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 — 431 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MarkItDown - File to Markdown Conversion
Overview
MarkItDown is Microsoft's Python package and CLI for converting documents, media, and web content to Markdown for LLM and text-analysis pipelines. It preserves structure that matters to models (headings, lists, tables, links) and is not meant for high-fidelity, human-facing document conversion. This skill targets markitdown 0.1.x (current release 0.1.8, Sept 2026; Python 3.10–3.14).
When to Use This Skill
Use this skill when the user wants to:
- Convert a PDF, Word, PowerPoint, Excel, EPUB, HTML, or Outlook file into Markdown for an LLM prompt, RAG index, or text analysis
- Batch-convert a folder of mixed document formats
- Get a YouTube transcript or audio transcription as Markdown
- Add LLM-written image descriptions, or OCR text from scans and embedded images
- Expose file conversion to an agent through the
markitdown-mcpserver
Does NOT Trigger
| Scenario | Use Instead |
|---|---|
| Ingesting many sources into a self-hosted notebook with chat, search, or podcasts | alterlab-open-notebook |
| Answering questions across the sections, figures, and tables of one PDF | alterlab-pdf-explore |
| Building a one-row-per-paper evidence table from many PDFs | alterlab-pdf-extract |
| Managing references, DOIs, or BibTeX libraries | alterlab-pyzotero |
Supported Formats
| Format | Description | Notes |
|---|---|---|
| Portable Document Format | Text-layer extraction ([pdf]); scans need OCR (see below) |
|
| DOCX | Microsoft Word | Headings, lists, tables ([docx]) |
| PPTX | PowerPoint | Slide text, tables, notes; optional LLM image descriptions ([pptx]) |
| XLSX / XLS | Excel spreadsheets | One Markdown table per sheet ([xlsx], [xls]) |
| Images | JPEG, PNG | EXIF metadata (needs exiftool) and an LLM description when llm_client is set |
| Audio | WAV, MP3, M4A, MP4 | Metadata + speech transcription ([audio-transcription]) |
| HTML | Web pages | Clean conversion; Wikipedia and Bing result pages get dedicated handling |
| CSV / JSON / XML | Text-based data | CSV becomes a table; JSON, JSONL, and XML pass through as text; RSS/Atom feeds are parsed |
| ZIP | Archive files | Iterates contents |
| EPUB | E-books | Full text extraction |
| Outlook MSG | Email messages | Headers and body ([outlook]) |
| Jupyter | .ipynb notebooks |
Markdown and code cells |
| YouTube | Video URLs | Fetches transcripts ([youtube-transcription]) |
What ships with it
7 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.
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 Changed · -43 lines · +33 tokens per session scan B → A dc6194ba3cec
- 1mo ago First seen · 474 lines · 147 tokens per session scan B 9566482bc0e2
alterlab-markitdown is a skill published in the GitHub repository AlterLab-IEU/AlterLab-Academic-Skills (78 stars, last pushed yesterday), licensed MIT. It adds 180 tokens to every session and 4,182 once invoked, about $0.0007 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 2026-09-05.
Other skills, from other repositories
thesis-consistency-audit
A consistency audit for quantitative master’s and doctoral theses in management, finance, or strategy. It checks whether numbers, tables, analyses, and claims agree, and can inspect hidden author information in office documents.
bilingual-paper-reader
A reading tool for translating an English research-paper PDF into Chinese paragraph by paragraph, with color labels for claims, innovations, methods, limits, and quotable sentences. It uses a reusable offline HTML reader and stores highlights in the browser.
literature-matrix-builder
A tool for turning a collection of research papers in PDF format into an organised literature library and comparison spreadsheet. It can find identifiers such as DOIs, retrieve publication details, check for retractions, and prepare reference lists.
markitdown
Converts heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.
acmmm-camera-ready
Use when preparing the ACM MM (ACM Multimedia) camera-ready version of record — de-anonymizing safely, completing the ACM rights form and CCS concepts, meeting ACM sigconf requirements, releasing code/data/media artifacts and any earned reproducibility badge, registering, and planning the oral/poster presentation in…
ccs-submission
Use when auditing an ACM CCS submission for HotCRP readiness, dual-cycle abstract registration and full-paper deadlines, the 12-page ACM sigconf body, anonymization, the ethics considerations appendix, artifact-availability posture, dual-submission policy, per-cycle submission caps, desk-reject triggers, and…