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 vasilyu1983/AI-Agents-public --skill document-pptxgit clone --depth 1 https://github.com/vasilyu1983/AI-Agents-publicWrote 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/vasilyu1983/ai-agents-public/document-pptx)<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/document-pptx"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/document-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/vasilyu1983/ai-agents-public/document-pptx"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/document-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 | $0.00035 | $0.01959 |
| Opus 5 | $0.00017 | $0.00979 |
| Sonnet 5 | $0.00007 | $0.00392 |
| Haiku 4.5 | $0.00003 | $0.00196 |
Grade A, and why
document-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 9d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document PPTX
Use this skill to create, edit, inspect, troubleshoot, or automate PowerPoint presentations programmatically.
Keep the skill focused on tool choice, template safety, notes and chart workflows, and repairability. Use the helper scripts and references instead of carrying long inline library manuals in SKILL.md.
Quick Reference
| Need | Default Tool | When to Use |
|---|---|---|
| fresh editable deck in Python workflow | python-pptx |
generation, extraction, notes, standard charts |
| fresh editable deck in JS/TS or browser flow | PptxGenJS |
Node/browser export, HTML-heavy workflows |
| designer-owned branded template | PPTX-Automizer or template-safe library flow |
replace named template elements |
| inspect masters, layouts, placeholders, and notes | scripts/pptx_inventory.py |
before editing branded templates |
| extract or back up notes | scripts/pptx_extract_notes.py |
speaker-note export |
| inspect damaged deck or OOXML parts | scripts/pptx_ooxml_inspect.py |
repair dialogs, broken rels, missing targets |
Decision Rules
- start from the audience and the decision the deck must support
- use one takeaway per slide
- prefer a branded template when brand fidelity matters
- resolve template layouts by name, not guessed index
- keep chart data traceable to one source of truth
- accessibility is part of authoring, not a final afterthought
- if animations, broken content, or unreadable-content repair are in scope, treat that as specialist troubleshooting work
Template-First vs From-Scratch Judgment
Deciding whether to open a branded .pptx template or build from a blank Presentation() is the single highest-leverage call in this skill — get it wrong and every downstream slide inherits the mistake.
- Use the branded template when: the deck goes to an external audience, brand/legal review is in the approval path, the org already has a maintained
.pptx/.potx, or the request mentions "our deck," "our template," or a company name. - Build from scratch when: it's an internal working draft, no template exists yet, the ask is exploratory ("mock up a few options"), or the content is data/report-shaped and speed matters more than pixel-perfect branding.
- Red flag: never guess at brand colors, fonts, or layout names when a template is available — inventory it first (
scripts/pptx_inventory.py). A plausible-looking hex code that isn't the actual brand color is worse than asking. - Escalate to PPTX-Automizer only when a designer already owns the
.pptx/.potxand the job is narrow, named-element replacement (chart data, a metric, a photo) — not general content authoring. Automizer is not a general slide-generation library; it merges into an existing structure. - If the user has no template and no strong brand requirement, do not manufacture one — a clean, legible, unbranded deck beats an invented "corporate" look with unverified colors.
What ships with it
18 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.
- agents/openai.yaml 324 B
- assets/pitch-deck.md 9.9 KB
- assets/quarterly-review.md 13 KB
- assets/slide-narrative-template.md 1.9 KB
- data/sources.json 8.9 KB
- learnings.consolidated.md 589 B
- learnings.md 353 B
- references/extraction-stack.md 1.1 KB
- references/pptx-accessibility-compliance.md 6.1 KB
- references/pptx-animations-transitions.md 11 KB
- references/pptx-charts.md 8.9 KB
- references/pptx-layouts.md 6.7 KB
- references/pptx-speaker-notes-delivery.md 9.9 KB
- references/pptx-template-branding.md 15 KB
- references/pptx-troubleshooting-repair.md 5.9 KB
- scripts/pptx_extract_notes.py 2.9 KB runs code
- scripts/pptx_inventory.py 4.7 KB runs code
- scripts/pptx_ooxml_inspect.py 5.8 KB runs code
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.
- 9d ago First seen · 160 lines · 35 tokens per session scan A 6c1799bbafcd
document-pptx is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (87 stars, last pushed 10d ago), licensed MIT. It adds 35 tokens to every session and 1,959 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
upload-artifact
Upload a file as a ClosedLoop document (PRD, implementation plan, feature, or template). Reads file content and uploads via MCP without consuming conversation context. Also supports creating new versions of existing documents. Triggers on: "upload artifact", "upload PRD", "upload implementation plan", "upload…
extract-plan-md
Sync plan.md with plan.json content. MUST be used after ANY edit to plan.json to keep plan.md in sync. Triggers: After editing plan.json with Edit tool (REQUIRED - always sync after edits) User asks to "sync plan.md", "update plan.md", "extract the md from a plan" Converting plan.json to markdown or viewing plan as…
frontmatter-guard
Injects the canonical vault frontmatter schema snippet into agent prompts before any vault-write task, preventing malformed YAML frontmatter in Obsidian notes. Context: wave-executor is about to dispatch a vault-mirror agent that writes learning notes under /Projects/vault/40-learnings/. user: "dispatch vault-write…
vault-mirror
Use when you need to populate the Meta-Vault with machine-generated notes derived from session-orchestrator JSONL records. Converts entries from .orchestrator/metrics/sessions.jsonl and .orchestrator/metrics/learnings.jsonl into vault-conformant Markdown under 50-sessions/ and 40-learnings/. Called automatically at…
vault-sync
Use when you need to validate the Meta-Vault's Markdown frontmatter and wiki-link integrity before closing a session or after vault edits. Runs as a hard gate at session-end Phase 1 — blocks close if any .md file fails the Zod frontmatter schema or has dangling [[wiki-links]]. Supports three modes: hard (blocks on…
docx
Create, read and edit Microsoft Word .docx documents — reports, letters, contracts, formatted multi-section documents with headings, tables, images, headers/footers and styles. Also covers reading an existing .docx to extract or modify its content, filling a .docx template, converting to PDF, and the raw OOXML route…