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 phanghonghao/THU-Awesome-Skills --skill markitdowngit clone --depth 1 https://github.com/phanghonghao/THU-Awesome-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/phanghonghao/thu-awesome-skills/markitdown)<a href="https://agentmods.dev/skills/phanghonghao/thu-awesome-skills/markitdown"><img src="https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/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/phanghonghao/thu-awesome-skills/markitdown"><img src="https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/markitdown.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 | $0.00086 | $0.01427 |
| Opus 5.5 | $0.00034 | $0.00571 |
| Sonnet 5.5 | $0.00017 | $0.00285 |
| Haiku 4.5 | $0.00009 | $0.00143 |
Grade A, and why
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 2mo 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markitdown Skill (microsoft/markitdown)
Microsoft's markitdown converts 15+ file formats to Markdown. This skill covers formats not handled by /pdf-reader and /word2md — primarily PPTX, XLSX, EPUB, HTML, and more.
When to Use
- User mentions: "markitdown", "/markitdown", "convert to markdown"
- Need to read PPTX, XLSX, EPUB, IPYNB, ZIP — these are NOT covered by
/pdf-readeror/word2md - Need table-aware PDF extraction (markitdown detects tables,
/pdf-readerdoes not) - User says "PPTX to markdown", "Excel to markdown", "EPUB to markdown"
- Quick one-shot conversion of any document to Markdown
When NOT to Use (use other skills instead)
| Format | Better skill | Reason |
|---|---|---|
| PDF (reading) | /pdf-reader |
PyMuPDF has 3 modes, higher fidelity, dict mode for LaTeX conversion |
| DOCX (with math) | /word2md |
Correct OMML→LaTeX; markitdown has escaped-underscore bug (\_{c} instead of _{c}) |
| DOCX (with images) | /word2md |
Extracts images to files; markitdown embeds base64 data URIs |
Supported Formats
PDF, DOCX, PPTX, XLSX, HTML, EPUB, Images (via LLM caption or EXIF), IPYNB, CSV, Plain text, ZIP (processes contents), Audio/Video (transcription via Azure), Outlook MSG, RSS, Wikipedia, YouTube (transcript).
Installation
python -m pip install markitdown 2>&1 | tail -3
Usage
CLI (recommended for single files)
# Convert to stdout
PYTHONIOENCODING=utf-8 markitdown "<INPUT_FILE>" 2>/dev/null
# Convert and save to file
PYTHONIOENCODING=utf-8 markitdown "<INPUT_FILE>" -o "<OUTPUT.md>" 2>/dev/null
# Pipe from stdin
PYTHONIOENCODING=utf-8 markitdown -x pptx < "<INPUT_FILE>" 2>/dev/null
Python API (for batch or programmatic use)
PYTHONIOENCODING=utf-8 python -c "
from markitdown import MarkItDown
import sys
md = MarkItDown()
result = md.convert(sys.argv[1])
print(result.text_content)
" "<INPUT_FILE>"
Batch conversion (multiple files)
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.
- 2mo ago First seen · 142 lines · 86 tokens per session scan A 0c9c41a64810
markitdown is a skill published in the GitHub repository phanghonghao/THU-Awesome-Skills (8 stars, last pushed 3mo ago), licensed MIT. It adds 86 tokens to every session and 1,427 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.
markitdown compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| markitdownphanghonghao/THU-Awesome-Skills | Skill | 8 | 3mo ago | MIT | A | 86 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 117 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | yesterday | Apache-2.0 | A | 123 | Claude Code |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 48 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | yesterday | Apache-2.0 | A | 68 | Claude Code |
| report-to-pdfasgeirtj/system_prompts_leaks | Skill | 71k | yesterday | CC0-1.0 | A | 17 | Claude Code, Codex |
| artifact-template-minimal-letterheadasgeirtj/system_prompts_leaks | Skill | 71k | yesterday | CC0-1.0 | A | 54 | Claude Code, Codex |