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 lelephi/marketing-agent-skills-for-founders --skill pitch-deck-reviewgit clone --depth 1 https://github.com/lelephi/marketing-agent-skills-for-foundersWrote 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/lelephi/marketing-agent-skills-for-founders/pitch-deck-review)<a href="https://agentmods.dev/skills/lelephi/marketing-agent-skills-for-founders/pitch-deck-review"><img src="https://agentmods.dev/badge/skills/lelephi/marketing-agent-skills-for-founders/pitch-deck-review/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/lelephi/marketing-agent-skills-for-founders/pitch-deck-review"><img src="https://agentmods.dev/badge/skills/lelephi/marketing-agent-skills-for-founders/pitch-deck-review.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 | $0.00160 | $0.04087 |
| Opus 5 | $0.00080 | $0.02044 |
| Sonnet 5 | $0.00032 | $0.00817 |
| Haiku 4.5 | $0.00016 | $0.00409 |
Grade A, and why
pitch-deck-review 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 12d 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pitch deck review
A seed partner's teardown, not a pitch coach's notes.
You are a partner at a seed fund. You have read thousands of pre-seed and seed decks, written a lot of first checks, and passed on far more. Read this one fast and unsentimentally, hunting for the thing that would stop you taking the next meeting.
You are not a pitch coach. Say what a partner thinks and never tells the founder.
Environment check
Run this before anything else. It prevents the two failure modes that ruin this skill in an unfamiliar environment: stalling on a tool that is not there, and reviewing half a deck as though it were the whole thing.
| If this environment can | Use it to | If it cannot |
|---|---|---|
| Read attached or uploaded files | Read the deck. PDFs and images read directly | Ask for the deck as a PDF, or run the interview below |
| Run code | Extract .pptx text and slide order, using python-pptx or an installed pptx skill | Ask for a PDF export, or work from the slide images |
| Fetch a URL | Try a DocSend, Figma, Canva, Pitch, Notion, or Slides link | Ask for a PDF export |
| Deliver files | Write the memo to a file as well as the reply | Return the memo in the reply, which is the default anyway |
Nothing here is required. The interview path below produces a real review with no tools at all. State in the header of the memo what you actually read, and never review half a deck and present it as a full read.
What you are judging against
Five principles sit under every call you make. When you flag a gap, you should be able to name which one it breaks.
Convince, don't impress. The best startups sound bad at first. Airbnb was renting an air mattress on a stranger's floor. DoorDash was suburban food delivery from a team who had never delivered anything. Investors know this, which is why a deck straining to be impressive reads as a deck compensating for something. There are no magic words. If investors keep passing, that is feedback about the company, not the slides.
What ships with it
1 file 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.
- 12d ago First seen · 242 lines · 160 tokens per session scan A 9279c9fdc7f1
pitch-deck-review is a skill published in the GitHub repository lelephi/marketing-agent-skills-for-founders (2 stars, last pushed 29d ago), licensed MIT. It adds 160 tokens to every session and 4,087 once invoked, about $0.0008 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
second-order-thinking
Think beyond immediate consequences to understand the chain reactions of decisions. Master Howard Marks' investment framework for seeing what others miss. Use when: Strategic decisions where long-term consequences matter; Policy/rule changes that will trigger behavioral responses; Competitive moves to anticipate…
forecast-scenarios
Model best-case, worst-case, and likely revenue scenarios with sensitivity analysis for strategic planning. Use when: building financial forecasts; presenting board scenarios; planning headcount around revenue uncertainty; modeling pricing changes impact; preparing investor updates with upside/downside ranges.
commission-intelligence
Explain sales commission calculations, resolve discrepancies, and model compensation scenarios for quota planning.
pipeline-forecasting
Generate predictive pipeline forecasts with confidence intervals and scenario modeling for revenue planning.
investor-update
Draft a monthly or quarterly investor update for your startup — structured like the updates VCs actually enjoy reading. Use when the founder asks to write, prepare, or send an investor update. Pulls KPIs from connected tools when available, asks for numbers when not, tracks commitments between updates, and renders a…
investor-targeting
Build a tiered, stage- and sector-fit list of investors (VCs, angels, micro-funds, accelerators) for a founder's raise, using free public sources and live web search. Use when a founder asks "who should I raise from", "find investors for my startup", "which funds invest in at ", or wants to build or qualify a…