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 AssafTzurEl/assaf-agent-skills --skill pptx-to-slide-mdgit clone --depth 1 https://github.com/AssafTzurEl/assaf-agent-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/assaftzurel/assaf-agent-skills/pptx-to-slide-md)<a href="https://agentmods.dev/skills/assaftzurel/assaf-agent-skills/pptx-to-slide-md"><img src="https://agentmods.dev/badge/skills/assaftzurel/assaf-agent-skills/pptx-to-slide-md/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/assaftzurel/assaf-agent-skills/pptx-to-slide-md"><img src="https://agentmods.dev/badge/skills/assaftzurel/assaf-agent-skills/pptx-to-slide-md.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 | $0.00141 | $0.01929 |
| Opus 5 | $0.00071 | $0.00964 |
| Sonnet 5 | $0.00028 | $0.00386 |
| Haiku 4.5 | $0.00014 | $0.00193 |
Grade A, and why
pptx-to-slide-md 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PPTX → slide-Markdown
Convert an existing .pptx back into the plain-text format the user writes
slides in, so a finished deck becomes editable source again.
Target format
One block per slide. --- separates slides; === separates slide content from
speaker notes. Presenter instructions (images, animations, demos) live in
[brackets] inside the content area. If the deck has sections, each section
begins with a [Section N: Section Name] label before the first slide in that
section.
[Section 1: Introduction]
[Slide 1]
# Slide Title
Slide content in markdown: bullets, numbered lists, tables, **bold**, *italic*, ~~strikethrough~~, [links](url).
[image: assets/slide3_img1.png — "alt text"]
[animation — 2 click steps:
click 1: entrance of "First point"
click 2: entrance of "Second point"]
===
**Speaker Notes:**
Notes in markdown.
---
[Slide 2]
# Next Slide Title
...
===
**Speaker Notes:**
*(none)*
Each slide is preceded by a [Slide N] label (N is the slide's position in the
deck, so a subset extraction keeps the original numbers). --- separates slides
and === separates content from notes, as before.
Blank lines between elements ensure Markdown viewers render each block as a separate paragraph rather than collapsing consecutive lines into soft-wrapped text.
The user also uses [^] inside speaker notes to mark a click. See the note on
animations below for why extraction puts animation detail in the content area
rather than fabricating [^] positions in the notes.
How to run it
The work is done by scripts/extract.py (Python 3; needs python-pptx and
lxml). lxml normally arrives as a dependency of python-pptx, but the script
imports it directly (from lxml import etree), so it is declared in its own right
in requirements.txt.
pip install python-pptx lxml --break-system-packages # if not already present
python scripts/extract.py <input.pptx> -o <output.md>
Options:
-o, --output— output path (default:<input-stem>.mdin the cwd).--slides— subset to extract, e.g.--slides 3-20or--slides 1,4,7-9(1-based; default: all). Numbers in[Slide N]stay absolute.--images-dir DIR— where to write extracted images (default:<output-stem>_images/next to the output file).--no-images— don't write image files; still emit[image: filename]inline.
What ships with it
2 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.
- 12d ago First seen · 178 lines · 141 tokens per session scan A 7654faa04f93
pptx-to-slide-md is a skill published in the GitHub repository AssafTzurEl/assaf-agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 141 tokens to every session and 1,929 once invoked, about $0.0007 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
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.