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/isatimur/presentation-md/presentation-generatornpx skills add isatimur/presentation-md --skill presentation-generatorgit clone --depth 1 https://github.com/isatimur/presentation-mdWrote 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/isatimur/presentation-md/presentation-generator)<a href="https://agentmods.dev/skills/isatimur/presentation-md/presentation-generator"><img src="https://agentmods.dev/badge/skills/isatimur/presentation-md/presentation-generator.svg" alt="Measured on agentmods" 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 | $0.00058 | $0.11615 |
| Opus 5 | $0.00029 | $0.05808 |
| Sonnet 5 | $0.00012 | $0.02323 |
| Haiku 4.5 | $0.00006 | $0.01162 |
Grade A, and why
presentation-generator 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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- presentation-generator — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 575 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Presentation Generator
Create stunning slide decks with an AI coding agent — HTML you own, plus editable PowerPoint when the room needs Office.
Default first win (no schema lecture): ask for a deck → show three vibes → scaffold → hand the user a Studio share link.
User: "Series A pitch for our AI infra startup — bold, not corporate"
You: preview_themes (safe + bold + wildcard) → user picks
scaffold_deck(purpose, theme) → return studio_share_url (?d=)
fill copy → audit_deck → render / export PPTX if asked
Gallery + Studio (zero install): https://presentation-md.vercel.app
Progressive disclosure (load only what you need)
This SKILL.md is the workflow map. Open supporting files on demand — do not dump schema, all 75 themes, or layout encyclopedias into context before the user has a vibe.
| File | Purpose | Load when |
|---|---|---|
SKILL.md (this file) |
Workflow + first-win path | Always |
references/theme-shortlists.json |
Use-case vibe shortlists | Phase 1 (vibe) |
references/stunning-25.md |
Flagship craft ceilings | Phase 1 when brief matches |
references/theme-selection-index.json |
Compact theme metadata | Phase 1 shortlist |
references/themes.md |
One-liners for all 75 | Only if shortlists miss |
references/layout-recipes.md |
Pitch / launch / wrap slide maps | Phase 3 (craft) |
references/deck-schema.md |
Layout prop reference | Phase 3 while emitting JSON |
references/anti-slop-bans.md |
Banned AI-slop aesthetics | Before custom styling |
references/custom-html-recipes.md |
Schema-safe art escapes | Only for intentional art beats |
references/animation-patterns.md |
Motion on direct-HTML path | Direct-HTML only |
references/pptx-import.md / markdown-import.md |
Import bridges | When converting existing decks |
Phases — vibe → preview → craft → share
Phase 0 — Mode
- New deck → Phase 1
- Convert PPTX / Markdown →
import_pptx/import_markdown(see import refs), then Phase 2 - Enhance existing → open Studio / Deck JSON; remorph or retheme; skip discovery if vibe is locked
What ships with it
23 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.
- deck.schema.json 10.0 KB
- references/animation-patterns.md 1.7 KB
- references/anti-slop-bans.md 3.0 KB
- references/custom-html-recipes.md 4.9 KB
- references/deck-schema.md 6.4 KB
- references/layout-recipes.md 11 KB
- references/markdown-import.md 2.4 KB
- references/pptx-import.md 1.2 KB
- references/stunning-25.md 3.0 KB
- references/theme-selection-index.json 45 KB
- references/theme-shortlists.json 8.6 KB
- references/themes.md 8.5 KB
- scripts/check-local-assets.mjs 2.4 KB runs code
- scripts/deploy.sh 3.0 KB runs code
- scripts/export-pdf.mjs 3.4 KB runs code
- scripts/export-pdf.sh 1.6 KB runs code
- scripts/package-lock.json 1.6 KB
- scripts/package.json 244 B
- scripts/pdf-security.mjs 5.1 KB runs code
- theme.schema.json 2.5 KB
- themes/claude/theme.json 979 B
- themes/default-tech/README.md 251 B
- themes/default-tech/theme.json 815 B
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.
- 4d ago First seen · 575 lines · 58 tokens per session scan A 54d549526743
presentation-generator is a skill published in the GitHub repository isatimur/presentation-md (4 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 11,615 once invoked, about $0.0003 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
deck-product-launch
暗 hero + 亮内容, 橙→桃 accent, 特性卡 + 定价 + CTA.
playwright-recording
Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.
lyria
Generate and validate music with Google Lyria 3 through the Gemini Interactions API. Use before calling OpenMontage googlemusic, designing Lyria 3 Clip or Pro prompts, using image-to-music or custom lyrics, choosing between Lyria 3 and Lyria RealTime, diagnosing Google music-generation failures, or preparing…
comfyui
Use when working with ComfyUI workflows in OpenMontage, including comfyuiimage/comfyuivideo/comfyuimusic, custom workflowjson/workflowpath inputs, outputnode selection, missing model setup, LoRAs, low-VRAM workflow choices, and community workflow imports.
dashscope
DashScope (Alibaba Cloud Bailian / 阿里云百炼) integration — image generation (qwen-image-2.0-pro), text-to-speech (qwen3-tts-flash), and ASR with word-level timestamps (qwen3-asr-flash-filetrans). Use when generating images via Qwen-Image, narrating via Qwen-TTS, or transcribing with word-level timestamps via Qwen-ASR.
hyperframes-animation
All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4…