Skip to content

AI agent skills for startup validation, competitive intelligence, and planning

feat: add pitch-deck-outline deliverable to startup-pitch

Ferdinando Bonsegna19880e30853f
diff --git a/AGENTS.md b/AGENTS.md
index 9af40a4..2e3f128 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -66,7 +66,7 @@ startup-skill/ # Plugin namespace (startup:*)
│ ├── frameworks.md
│ └── honesty-protocol.md
├── startup-pitch/ # Skill: startup:startup-pitch
-│ ├── SKILL.md # Main skill file (~418 lines, 2 waves)
+│ ├── SKILL.md # Main skill file (~424 lines, 2 waves)
│ └── references/
│ ├── research-principles.md
│ ├── research-scaling.md
@@ -174,6 +174,7 @@ All skills run a **V1: Verification** agent after synthesis. It audits deliverab
- `pitch-1min.md` — Elevator pitch (formal + casual)
- `pitch-email.md` — Investor cold email + follow-up
- `pitch-appendix.md` — Q&A preparation, objection handling
+- `pitch-deck-outline.md` — Slide-by-slide deck structure with headlines, visuals, speaker notes
- `pitch-scorecard.md` — Pitch quality scoring rubric
- `raw/` — Raw research data from each wave
diff --git a/CLAUDE.md b/CLAUDE.md
index 1d85c65..c5b655d 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -66,7 +66,7 @@ startup-skill/ # Plugin namespace (startup:*)
│ ├── frameworks.md
│ └── honesty-protocol.md
├── startup-pitch/ # Skill: startup:startup-pitch
-│ ├── SKILL.md # Main skill file (~418 lines, 2 waves)
+│ ├── SKILL.md # Main skill file (~424 lines, 2 waves)
│ └── references/
│ ├── research-principles.md
│ ├── research-scaling.md
@@ -163,6 +163,7 @@ Each wave must complete before the next starts. Agents use WebSearch for real da
- `pitch-1min.md` — Elevator pitch (formal + casual)
- `pitch-email.md` — Investor cold email + follow-up
- `pitch-appendix.md` — Q&A preparation, objection handling
+- `pitch-deck-outline.md` — Slide-by-slide deck structure with headlines, visuals, speaker notes
- `pitch-scorecard.md` — Pitch quality scoring rubric
- `raw/` — Raw research data from each wave
diff --git a/README.md b/README.md
index d08ff0d..c8c32f7 100644
--- a/README.md
+++ b/README.md
@@ -23,7 +23,7 @@ Works with [Claude Code](https://claude.ai/claude-code) and any agent that suppo
| [startup-design](startup-design/) | Complete startup strategy: market research, customer discovery, competitive analysis, brand, product definition, financial projections, and validation experiments. 8 phases plus pre-flight check and customer interview gate, 30+ structured deliverables. |
| [startup-competitors](startup-competitors/) | Battle cards for every competitor, pricing landscape, feature matrix, and strategic report. Built from real reviews, forums, and web data. |
| [startup-positioning](startup-positioning/) | Market positioning using April Dunford's framework. Positioning doc, competitive alternatives map, market category analysis, and messaging implications. |
-| [startup-pitch](startup-pitch/) | Investor-ready pitch in multiple formats: 10-min, 5-min, 2-min, 1-min elevator, and email. Includes scoring rubric, Q&A prep, and investor roleplay practice. |
+| [startup-pitch](startup-pitch/) | Investor-ready pitch in multiple formats: 10-min, 5-min, 2-min, 1-min elevator, email, and a slide-by-slide deck outline. Includes scoring rubric, Q&A prep, and investor roleplay practice. |
## Usage
diff --git a/startup-pitch/SKILL.md b/startup-pitch/SKILL.md
index 3be3477..cedd5a6 100644
--- a/startup-pitch/SKILL.md
+++ b/startup-pitch/SKILL.md
@@ -272,6 +272,12 @@ Generate all requested formats. If the user didn't specify, generate all of them
- Known weaknesses with honest answers and mitigation plans
- Financial and competitive backup (if available from prior sessions)
+**`{project-name}/pitch-deck-outline.md`** — Slide-by-slide deck structure (10-12 slides):
+- Derived from `pitch-full.md`: same narrative order, translated into slides — don't invent new content here
+- For each slide: a **headline** that states the takeaway ("A $47B market growing 23% annually", never a label like "Market Size"), 3-5 body bullets under 30 words total, a visual suggestion (chart, diagram, screenshot), and speaker notes drawn from the corresponding narrative section
+- One idea per slide; the headlines alone, read in sequence, must pitch the company
+- The final slide carries the ask
+
### Raw Data
Each agent saves its raw output to `{project-name}/raw/`. Agents must NOT write directly to deliverable paths — raw and synthesized output are separate.
@@ -413,6 +419,6 @@ Read only what you need for the current phase.
| `research-wave-1-audience-narrative.md` | When running Wave 1 | ~164 | Agent templates for investor + narrative research |
| `research-wave-2-competitive-framing.md` | When running Wave 2 | ~159 | Agent templates for competitive framing + why now |
| `pitch-frameworks.md` | During Phase 3 | ~261 | Complete pitch framework with integration matrix |
-| `research-synthesis.md` | After waves complete | ~423 | Synthesis protocol and output templates |
+| `research-synthesis.md` | After waves complete | ~467 | Synthesis protocol and output templates |
| `research-scaling.md` | After intake, before Phase 2 | ~96 | Complexity scoring, tier definitions, wave configurations |
| `verification-agent.md` | After pitch construction | ~129 | Verification protocol, universal + skill-specific checks |
diff --git a/startup-pitch/references/research-synthesis.md b/startup-pitch/references/research-synthesis.md
index 61770d6..9d336a4 100644
--- a/startup-pitch/references/research-synthesis.md
+++ b/startup-pitch/references/research-synthesis.md
@@ -1,6 +1,6 @@
# Pitch Research Synthesis Protocol
-**Contents:** Before Writing · Cross-Source Connections to Look For · Confidence Rating · Pitch Construction Process · Output File Templates (pitch-full, pitch-5min, pitch-2min, pitch-1min, pitch-email, pitch-appendix, pitch-scorecard) · Post-Synthesis Verification
+**Contents:** Before Writing · Cross-Source Connections to Look For · Confidence Rating · Pitch Construction Process · Output File Templates (pitch-full, pitch-5min, pitch-2min, pitch-1min, pitch-email, pitch-appendix, pitch-deck-outline, pitch-scorecard) · Post-Synthesis Verification
## Before Writing
@@ -373,6 +373,48 @@ After writing all pitch deliverables (before the scorecard/review phase), run th
---
+### pitch-deck-outline.md
+
+Translate the full narrative into slides — compression and visualization, not new writing. Follow the pitch order already established; a typical investor deck runs 10-12 slides (Title, Problem, Solution, Market, Product, Business Model, Traction, Go-to-Market, Team, Financials, The Ask).
+
+```markdown
+# Pitch Deck Outline: {product}
+*Skill: startup-pitch | Generated: {date}*
+
+**Source narrative:** pitch-full.md — same order, translated to slides.
+
+## Slide 1 — Title
+**Headline:** {Company name + one-line description in customer language}
+**Visual:** Logo, tagline
+**Speaker notes:** {The 2-sentence opener}
+
+## Slide {N} — {Element}
+**Headline:** {One takeaway sentence — never a label}
+**Body:**
+- {3-5 bullets, under 30 words total}
+**Visual:** {Chart / diagram / screenshot suggestion}
+**Speaker notes:** {What to say, from the corresponding pitch-full.md section}
+
+{...repeat for all slides...}
+
+## Deck Quality Checklist
+- [ ] Every headline tells the takeaway (headlines alone, in sequence, pitch the company)
+- [ ] One idea per slide
+- [ ] Under 30 words per slide body
+- [ ] A visual suggested for every slide
+- [ ] Speaker notes on every slide
+- [ ] The final slide carries a clear ask
+
+## Red Flags
+- {...}
+
+## Yellow Flags
+- {...}
+
+## Sources
+- {source} [Tier N]
+```
+
### pitch-scorecard.md
```markdown