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 AgentlyLabs/founder-skills --skill pitch-deckgit clone --depth 1 https://github.com/AgentlyLabs/founder-skillsWrote 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/agentlylabs/founder-skills/pitch-deck)<a href="https://agentmods.dev/skills/agentlylabs/founder-skills/pitch-deck"><img src="https://agentmods.dev/badge/skills/agentlylabs/founder-skills/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/agentlylabs/founder-skills/pitch-deck"><img src="https://agentmods.dev/badge/skills/agentlylabs/founder-skills/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 | $0.00234 | $0.02303 |
| Opus 5 | $0.00117 | $0.01151 |
| Sonnet 5 | $0.00047 | $0.00461 |
| Haiku 4.5 | $0.00023 | $0.00230 |
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 11d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investor-Grade Pitch Decks
What this skill actually does
It builds decks as HTML rendered to PDF at 16:9, using a dark editorial design system and a discipline about narrative that matters more than the visuals.
Building slides as code is not a gimmick here. It buys three things Keynote cannot: a design system enforced by CSS variables so nothing drifts slide to slide, product artifacts drawn in real markup instead of screenshotted or faked in a vector tool, and version control on the narrative. The output is a normal PDF that opens anywhere.
The one rule that determines whether the deck works
Never open a design tool before the narrative is settled. A beautifully typeset deck carrying a muddled argument is worse than an ugly one carrying a sharp argument, because the polish invites the reader to look closely at reasoning that cannot survive it.
So the workflow is strictly: interrogate → outline → write headlines → then build. Read
references/narrative.md before writing a single slide. If the user hands you content and
asks only to "make it look good," still run the narrative check first and say plainly what
the argument is missing — then build what they asked for.
Step 1 — Interrogate before designing
You need real answers to these. Ask directly; do not invent them, and do not proceed on assumptions for the first four.
- Stage and ask. Pre-seed, seed, Series A? Raising how much, for what runway? This sets what evidence is expected — a pre-seed deck can sell a thesis, a Series A deck cannot.
- The wedge. Who is the first user, precisely, and what do they do the morning after they sign up?
- Why now. What changed in the last 18 months that makes this possible and did not before? A deck with no credible "why now" reads as a company that could have been started at any point and therefore probably will not win.
- The evidence. Actual numbers: users, revenue, retention, pipeline, waitlist. Whatever is real, however small.
- The uncomfortable question. What will the sharpest person in the room push on? Decks that pre-empt their strongest objection outperform decks that hide it.
- Brand. Ask for the company website URL — that is the fastest path to a deck that
looks like it came from the same company as the product. See Step 1b. If there is no
site yet, the defaults in
references/design-system.mdare production-ready as-is.
What ships with it
8 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.
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.
- 11d ago First seen · 170 lines · 234 tokens per session scan A 6071222dc4f3
pitch-deck is a skill published in the GitHub repository AgentlyLabs/founder-skills (2 stars, last pushed 14d ago), licensed MIT. It adds 234 tokens to every session and 2,303 once invoked, about $0.0012 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.