pitch-deck — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited pitch-deck (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
<!-- Adapted from sendaifun/solana-new (create-pitch-deck), MIT © 2026 SendAI and Superteam. Telemetry removed. -->
Interview → detect audience → pick narrative → build slides with speaking notes → self-score → objection prep.
At start, read .claude/context/idea.md and .claude/context/build.md if present — pre-fill problem, wedge, traction, and stack from them; only ask what's missing.
Blunt, one at a time, skipping anything already answered by context files:
Q10 decides the slide set — full breakdown in investor-audience-guide.md:
| Audience | Emphasis | Length |
|---|---|---|
| Hackathon judges | working demo, technical novelty, why-Solana | 5–7 slides |
| VC | market size, traction slope, team, moat, ask | 10–12 |
| Grant committee | ecosystem benefit, public-good angle, milestones, budget | 8–10 |
| Accelerator | team velocity, learning rate, wedge → expansion path | 8–10 |
Slide-by-slide order per audience: pitch-structure.md.
Pick ONE backbone and state why — PAS (obvious pain, hackathons), 6-Part Investor Arc (VC), BAB (before/after/bridge), Hero's Journey (founder-story-driven), Pixar (narrative momentum). Definitions, slide mappings, and crypto examples: storytelling-frameworks.md.
For each slide: headline (a claim, not a label), 3–5 supporting points, visual suggestion, and 30–60s speaking notes. Use:
Score the draft against the audience's actual criteria (clarity, credibility, demo strength, ask specificity) and against crypto-pitch-mistakes.md — flag every mistake the deck still commits, fix, re-score. Don't present a deck you'd score below 8/10.
From Q12 + the weakest scored dimension, draft the 8–10 hardest questions this audience will ask, each with a tight 30-second answer. Hostile-question drilling beats slide polish.
Need an actual rendered deck file (.pptx)? Hand the outline to the pptx skill if available.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.