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 JeffGuo7/s-loop --skill make-pptxgit clone --depth 1 https://github.com/JeffGuo7/s-loopWrote 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/jeffguo7/s-loop/make-pptx)<a href="https://agentmods.dev/skills/jeffguo7/s-loop/make-pptx"><img src="https://agentmods.dev/badge/skills/jeffguo7/s-loop/make-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/jeffguo7/s-loop/make-pptx"><img src="https://agentmods.dev/badge/skills/jeffguo7/s-loop/make-pptx.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 | $0.00095 | $0.01393 |
| Opus 5 | $0.00048 | $0.00696 |
| Sonnet 5 | $0.00019 | $0.00279 |
| Haiku 4.5 | $0.00010 | $0.00139 |
Grade A, and why
make-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 today.
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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Making PowerPoint decks
You have two tools for this job: create_pptx (generates the file by running
your pptxgenjs script) and inspect_pptx (machine-checks the result). Follow
the workflow below exactly — it is what separates a polished deck from a messy
one.
Workflow
- Plan silently: decide the slide count, one core message per slide, and a palette (one primary color, one neutral, one accent; roughly 60% / 30% / 10% usage). 5-12 slides is right for most requests unless the user asks otherwise.
- Write ONE script that builds the entire deck, call
create_pptxwith it. Do not call the tool once per slide. - Call
inspect_pptxon the output. Fix every reported issue (overflow, overlap, validation errors) by editing your script and re-runningcreate_pptxto the same path. Re-inspect after fixing. A deck with reported issues must not be delivered. - Reply with a file link so the user can open it:
[File: name.pptx](relative/path.pptx)plus a 2-3 sentence summary of the deck structure.
Script contract
The tool runs your script as an ES module with a ready-to-use presentation
instance exposed as the global pptx. Build the deck on it — do not
redeclare pptx, and do not call writeFile (the tool writes the file to
outputPath after your script returns):
pptx.layout = 'LAYOUT_16x9' // always first; 16:9 canvas = 10 x 5.625 inches
const title = pptx.addSlide()
title.addText('Quarterly Review', { x: 0.6, y: 2.2, w: 8.8, h: 1.2, fontSize: 32, bold: true })
// ... more slides ...
// done — the harness saves the file automatically
Never emit base64 file content in the script output.
Design baseline (non-negotiable)
- Canvas: 10 x 5.625 inches (16:9). Every element gets explicit
x, y, w, h. There is NO auto-layout — compute positions yourself. - Typography: titles >= 20pt bold, body >= 14pt, captions >= 11pt. One
font family per deck; for Chinese content use
fontFace: 'Microsoft YaHei'(微软雅黑), for English 'Segoe UI' or 'Arial'. Line spacing 1.2-1.5 on body text (lineSpacingMultiple). - Margins: keep >= 0.5in padding on every side. Nothing touches the edge.
- Consistency: reuse the same title position, accent bar, and footer
positions on every content slide. Define a helper function in your script
(e.g.
function contentSlide(kicker, title) {...}) instead of repeating coordinates. - Density: max ~6 bullets per slide, max ~15 words per bullet. If content overflows, split into two slides — do not shrink text below 14pt.
- Visual variety: alternate layouts (title slide / bullets + side panel / two columns / chart + takeaway / section divider / closing). Not every slide should look the same, but all should share the grid and palette.
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.
- today First seen · 99 lines · 95 tokens per session scan A d579b1734850
make-pptx is a skill published in the GitHub repository JeffGuo7/s-loop (10 stars, last pushed yesterday), licensed MIT. It adds 95 tokens to every session and 1,393 once invoked, about $0.0005 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 2026-09-12.
Other skills, from other repositories
ha-data-analytics
A local-first data-analysis and reporting skill for CSV and spreadsheet files. It produces decision-ready analyses and shareable offline reports while separating facts, calculations, interpretations, and recommendations.
office-xlsx
Use when the user asks to create, inspect, verify, analyze, format, or deliver Excel .xlsx workbooks, Google Sheets-targeted spreadsheet artifacts, trackers, budgets, models, tables, dashboards, formulas, CSV/TSV-to-XLSX conversions, or spreadsheet-ready data packs.
agent-office
A guide for creating, editing, rewriting, converting, processing, or delivering Word documents, spreadsheets, presentations, and PDF files.
doc-processor
Reads, parses, and generates documents in various formats like Markdown, PDF, docx, CSV, or HTML. Uses bash commands to invoke document conversion tools like pandoc or python scripts.
data-analysis
Use this skill when the user uploads Excel (.xlsx/.xls) or CSV files and wants to perform data analysis, generate statistics, create summaries, pivot tables, SQL queries, or any form of structured data exploration. Supports multi-sheet Excel workbooks, aggregation, filtering, joins, and exporting results to…
officecli-financial-model
Use this skill when the user wants to build a financial model — 3-statement model, DCF valuation, LBO, SaaS unit economics, sensitivity / scenario analysis, debt schedule, or fundraising projections — in Excel. Trigger on: 'financial model', '3-statement model', 'P&L + BS + CF', 'DCF', 'WACC', 'NPV', 'terminal value'…