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 canvora/canvora-mcp --skill pitch-deckgit clone --depth 1 https://github.com/canvora/canvora-mcpWrote 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/canvora/canvora-mcp/pitch-deck)<a href="https://agentmods.dev/skills/canvora/canvora-mcp/pitch-deck"><img src="https://agentmods.dev/badge/skills/canvora/canvora-mcp/pitch-deck/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/canvora/canvora-mcp/pitch-deck"><img src="https://agentmods.dev/badge/skills/canvora/canvora-mcp/pitch-deck.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 | $0.00064 | $0.01429 |
| Opus 5 | $0.00032 | $0.00714 |
| Sonnet 5 | $0.00013 | $0.00286 |
| Haiku 4.5 | $0.00006 | $0.00143 |
Grade A, and why
pitch-deck 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 10d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decks and presentations
Deck formats run through Canvora's structured slide pipeline: one planning
pass builds the narrative arc and a shared design system, then every slide is
rendered against it. That is why a deck holds together where N separate images
would not. Your job is the narrative input and the format choice — the pipeline
does the rest. Setup and credits: see the canvora skill.
Pick the format by audience, not by shape
| Format | Size | Use for |
|---|---|---|
pitch_deck |
16:9 | investors, fundraising, "the story of the company" |
sales_deck |
16:9 | prospects, product value, objection handling |
presentation_slide |
16:9 1920×1080 | the general default — talks, internal, conference |
training_slide |
16:9 | teaching, onboarding, step-by-step instruction |
webinar_slide |
16:9 | live sessions, screen-share readability |
presentation_4x3 |
4:3 1024×768 | only when the user's projector/template demands it |
All six are carousel formats: 15 credits per slide. A 10-slide deck = 150. State the cost in the same message as the run — announce it, don't ask permission. When you chose the slide count (the defaults below) rather than the user, confirm that number with them; when they said "10 slides", just run it.
Every deck is 3+ outputs, so fire-and-poll instead of --wait: most harnesses
kill a shell command at 120s while the deck carries on rendering server-side.
Never re-run generate after a timeout — that starts a second, separate job.
Poll status. See the canvora skill's "Long runs" section.
Intake — three questions, maximum
- What's the source? A document (
--file-url), a link (--url), written content (--input), or just the pitch in their head (--idea)? - How many slides? If they don't know, use the audience: pitch 10, sales 8, training as many as there are steps, general 8. Cap is 10 per call.
- Whose brand?
canvora brands --json→--brand(+--logo— decks are the one place a logo on every slide is expected).
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.
- 10d ago First seen · 110 lines · 64 tokens per session scan A ea4429f9af00
pitch-deck is a skill published in the GitHub repository canvora/canvora-mcp (0 stars, last pushed 28d ago), licensed MIT. It adds 64 tokens to every session and 1,429 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
guizang-ppt-skill
A skill for creating presentation decks as single HTML files that users can move through horizontally in a browser. It provides templates with WebGL backgrounds, chapter title screens, large data displays, and image grids, in either an editorial or Swiss-style visual direction.
gpt-image-2-portrait-library
Choose, inspect, attribute, and safely adapt original-language GPT Image 2 portrait-editing prompts from a 519-record provenance-first library. Use its two-level task and scenario taxonomy for restoration, natural retouching, professional identity photos, lifestyle portraits, and identity-preserved transformations.
p5js
Use when users request: p5.js sketches, creative coding, generative art, interactive visualizations, canvas animations, browser-based visual art, data viz, shader effects, or any p5.js project.
audiocraft-audio-generation
AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
hyperframes
Render MP4/WebM videos from HTML compositions.
ascii-video
ASCII video: convert video/audio to colored ASCII MP4/GIF.