Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/glukicov/slideopsnpx agentmods add skills/glukicov/slideops/slides-to-pdfWrote 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/glukicov/slideops/slides-to-pdf)<a href="https://agentmods.dev/skills/glukicov/slideops/slides-to-pdf"><img src="https://agentmods.dev/badge/skills/glukicov/slideops/slides-to-pdf/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/glukicov/slideops/slides-to-pdf"><img src="https://agentmods.dev/badge/skills/glukicov/slideops/slides-to-pdf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 47 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00076 | $0.02469 |
| Opus 5 | $0.00038 | $0.01234 |
| Sonnet 5 | $0.00015 | $0.00494 |
| Haiku 4.5 | $0.00008 | $0.00247 |
Grade A, and why
slides-to-pdf 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 6d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slides to PDF
Converts a JS-driven, one-slide-per-screen HTML deck into a paginated PDF: one page per slide, matching the browser rendering, with a centred page number in the footer. There is no native "print to PDF" for such decks (printing captures only the visible slide), so the pipeline is: screenshot every slide at 2x with headless Chrome, wrap the screenshots in a print-paginated page, number them, print that to PDF, then verify the PDF by rendering it back to images.
Inputs to establish up front (ask only if not obvious):
- Deck path, the literal that marks one slide (default
<section class="slide"), and the deck's canvas size (default 1280x720). Read the deck's own CSS to confirm both before you start; a wrong size silently letterboxes or crops every page. - Output path: default next to the HTML, same basename,
.pdf. - Chrome-only UI to hide: for SlideOps decks this is
.hud,.progress,.hint; for other decks, identify the fixed nav/progress elements a printed page shouldn't show.
1. Find Chrome and make a staging directory
find_chrome() {
local base c
for base in "$HOME/Library/Caches/ms-playwright" "$HOME/.cache/ms-playwright"; do
[ -d "$base" ] || continue
c=$(find "$base" -maxdepth 6 -type f \
\( -name chrome -o -name Chromium -o -name "Google Chrome for Testing" \) \
2>/dev/null | grep -v headless_shell | sort -V | tail -1)
[ -n "$c" ] && { printf '%s\n' "$c"; return; }
done
for c in "/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" \
"$(command -v google-chrome || true)" "$(command -v chromium || true)"; do
[ -x "$c" ] && { printf '%s\n' "$c"; return; }
done
}
CHROME=$(find_chrome)
[ -x "$CHROME" ] || { npx --yes playwright install chromium; CHROME=$(find_chrome); }
"$CHROME" --version # sanity-check; quote "$CHROME" everywhere (macOS path has spaces)
DECK="/absolute/path/to/deck.html"
STAGE=$(mktemp -d -t slidespdf) # or a per-deck subdir of your session scratchpad
# Per-deck settings. The defaults match SlideOps decks; change all three for a foreign one.
SLIDE_MATCH='<section class="slide' # the literal that starts one slide element
W=1280; H=720 # the deck's canvas size in CSS pixels
CHROME_SANDBOX_ARGS=() # see "Sandbox" below before adding --no-sandbox
N=$(grep -c "$SLIDE_MATCH" "$DECK")
[ "$N" -gt 0 ] || { echo "No slides matched $SLIDE_MATCH; check the selector"; exit 1; }
echo "$N slides at ${W}x${H}"
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.
- 6d ago Changed · +25 lines 88258726e3a4
- 10d ago First seen · 170 lines · 76 tokens per session scan A 9e8dbce0efd8
slides-to-pdf is a skill published in the GitHub repository glukicov/slideops (49 stars, last pushed 7d ago), licensed MIT. It adds 76 tokens to every session and 2,469 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
legal-discovery
Audit e-discovery and litigation document review systems -- data collection pipelines (PST, MBOX, SharePoint, Slack), document processing (OCR via Tesseract/ABBYY, metadata extraction, deduplication), Technology Assisted Review (TAR 1.0/2.0/CAL with recall/precision tracking).
lease-abstraction
Extract a structured abstract from a commercial lease PDF — tenant/landlord identification, premises description + RSF/USF, lease term + commencement/expiration, renewal options (count, notice windows, fair-market rent reset), base rent schedule + escalations (fixed %, CPI-linked.
paddleocr-doc-parsing
A document-reading tool for turning PDFs and document images into structured Markdown or JSON. It can preserve tables, formulas, figures, seals, charts, headers, columns, and reading order.
paddleocr-text-recognition
An OCR tool for extracting exact text from images, photos, screenshots, scans, and scanned PDFs. OCR means turning text visible in an image into machine-readable text.
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.
markitdown
Convert 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.