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 pamelafox/presentation-skills --skill thumbnail-of-pptxgit clone --depth 1 https://github.com/pamelafox/presentation-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/pamelafox/presentation-skills/thumbnail-of-pptx)<a href="https://agentmods.dev/skills/pamelafox/presentation-skills/thumbnail-of-pptx"><img src="https://agentmods.dev/badge/skills/pamelafox/presentation-skills/thumbnail-of-pptx/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/pamelafox/presentation-skills/thumbnail-of-pptx"><img src="https://agentmods.dev/badge/skills/pamelafox/presentation-skills/thumbnail-of-pptx.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00111 | $0.00682 |
| Opus 5 | $0.00056 | $0.00341 |
| Sonnet 5 | $0.00022 | $0.00136 |
| Haiku 4.5 | $0.00011 | $0.00068 |
Grade A, and why
thumbnail-of-pptx 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 12d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thumbnail of a PPTX slide
Run the thumbnail_of_pptx.py script to capture a slide thumbnail from a OneDrive/Office presentation link:
uv run .agents/skills/thumbnail-of-pptx/thumbnail_of_pptx.py <url> <output_path>
Arguments
url(required): A OneDrive sharing link, or anaka.msshort link that redirects to one (e.g.https://aka.ms/my-talk-slides). The link must open the Office Online / PowerPoint web viewer.output_path(required): Path to write the PNG thumbnail (e.g.thumbnail.png). Parent directories are created if needed.--slide N(optional): 1-based slide number to capture. Defaults to1, the title slide.--scale N(optional): Device scale factor for a crisper image. Defaults to2.--wait MS(optional): Milliseconds to wait for the slide to render before screenshotting. Defaults to9000. Increase for large decks or slow networks.
Outputs
A single PNG image of the requested slide, cropped to the slide canvas (roughly 16:9, no PowerPoint viewer UI).
Prerequisites
Playwright browsers must be installed:
uv run playwright install chromium
How it works
- Launches headless Chromium and navigates to the URL (following
aka.msredirects to the real OneDrive viewer). - Waits for the network to go idle, then waits a fixed delay for the Office Online viewer to stream in and paint the slide.
- Locates the viewer iframe (named
wacIframe, with a fallback that finds any frame containing a<canvas>). - Optionally advances to slide
Nby focusing the canvas and pressing the right-arrow key. - Element-screenshots the slide
<canvas>so the output contains only the slide, not the surrounding viewer chrome.
Notes
- This is complementary to fetch-slides: use
fetch-slideswhen you need the full deck as a PDF (requires LibreOffice for PPTX), and this skill when you just want a lightweight thumbnail image of one slide and the file may not be downloadable. - Because it relies on the public web viewer, the sharing link must be viewable by anyone with the link.
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.
- 12d ago First seen · 71 lines · 111 tokens per session scan A 093d8ab4984a
thumbnail-of-pptx is a skill published in the GitHub repository pamelafox/presentation-skills (117 stars, last pushed 9d ago), licensed MIT. It adds 111 tokens to every session and 682 once invoked, about $0.0006 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
km-content-extraction
Content extraction routing for KM - local documents (HWP/HWPX/PDF/DOCX/XLSX), web, and vault sources. Use when input is a local file or when km-workflow reaches Phase 2 with a non-URL input.
svg-press
Teaches agents how to hand-craft self-contained SVG diagrams that render correctly in browsers, tags, and Playwright PDF/PNG. Covers containment math, viewBox sizing, arrow construction, text hierarchy, KDCube brand color tokens, semantic zone fills, badges, the PNG inspection loop, writepng parameters, multi-diagram…
export-presentation
Export HTML slide presentations to PDF or PNG screenshots.
openclaw-rpa
Record browser, Excel, Word & API actions once — replay without the LLM: faster, cheaper, no hallucinations. github.com/laziobird/openclaw-rpa . Supports computer-use automation: web clicks/fill/extract, local Excel (.xlsx via openpyxl), Word (.docx via python-docx), HTTP API calls (httpx GET/POST), and auto-login…
single-page-pdf-export
A browser-based export tool that turns a local HTML page or web page into one tall PDF page. The PDF has no browser print headers or footers.
file-download
Download files from websites, save PDFs, and read downloaded content. Trigger when the user asks to: download a file, save a PDF, export a document, fetch a file from a URL, grab a report, download and read a PDF, or save page content as a file.