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 agentmods add skills/code-saurabh/openskills/pptxnpx skills add CODE-SAURABH/OpenSkills --skill pptxgit clone --depth 1 https://github.com/CODE-SAURABH/OpenSkillsWhat 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 | $0.00086 | $0.02969 |
| Opus 5 | $0.00043 | $0.01484 |
| Sonnet 5 | $0.00017 | $0.00594 |
| Haiku 4.5 | $0.00009 | $0.00297 |
Grade A, and why
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 yesterday.
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 — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PowerPoint Presentation (.pptx)
A .pptx file is a ZIP archive of XML files. You can create, edit, and read them programmatically. Choose the right approach for the task:
| Task | Approach |
|---|---|
| Create a new deck | pptxgenjs (Node) or python-pptx (Python) |
| Edit an existing deck | Unzip → edit slide XML → rezip |
| Read content from a deck | markitdown deck.pptx or unzip and parse XML |
| Convert to PDF | LibreOffice headless |
Presentation Principles
- Every slide has one job. A slide that makes three points makes zero. Split ruthlessly.
- Text-only slides are forgettable. Every slide needs at least one visual element — chart, image, icon, data callout, or diagram.
- The deck must work without the speaker. Async decks (sent via email, read without a presenter) need more text and context than live-presentation decks.
- Visual hierarchy over bullet points. A large number + small label communicates faster than a sentence. A 2x2 grid communicates relationships better than a list.
- Commit to a visual direction and hold it. One font pair. One color palette. One layout style. Inconsistency signals lack of polish.
- AI slop is obvious. Cream backgrounds, accent stripes along card edges, Inter/Roboto with no rationale, blue CTA buttons, centered body text — these are trust killers. Avoid all of them.
Step 0: Before Creating
Ask the user:
- What is the deck for? (investor pitch, all-hands, client presentation, technical review, sales demo)
- Who is the audience? (technical, executive, external client, general team)
- How many slides? Or: what content needs to be covered?
- Brand constraints? (specific colors, fonts, logo to include)
- Output format? (.pptx to edit further, or PDF to send)
- Presenting live or sending async? (changes text density and speaker notes needs)
Creating with pptxgenjs (Node/TypeScript)
Setup
# pptxgenjs is often pre-installed — try require first
node -e "require('pptxgenjs')" 2>/dev/null && echo "installed" || npm install pptxgenjs
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.
- yesterday First seen · 320 lines · 86 tokens per session scan A 2da0a668ba12
pptx is a skill published in the GitHub repository CODE-SAURABH/OpenSkills (2 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 2,969 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
agent-framework-azure-ai-py
Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.
aria
Designs the data model, API contracts, and structural foundation of the system.
accint-commitments
Triage acc's open promises and close them with honest real-world verdicts via accact(runtime="outcome").
ecommerce-landing-page
Audit and optimize e-commerce landing pages for conversion. CTA placement, trust signals, page structure, copy optimization, and A/B testing strategy for product pages, collection pages, and campaign landing pages.
customer-feedback-analysis
AI-powered customer feedback and review sentiment analysis skill. Extracts pain points, feature requests, and improvement priorities from customer reviews across e-commerce platforms.
ads-linkedin
Audit LinkedIn Ads measurement, Insight Tag and conversions, professional audiences, lead generation, ABM, creative, bidding, budgets, pacing, automation, and policy. Use for LinkedIn Ads, Campaign Manager, Insight Tag, Lead Gen Forms, Thought Leader Ads, ABM campaigns, or B2B paid media.