agentleFS
oncesylviaoncesylvia/fundraising-skills/skills/pitch-narrative/SKILL.md

pitch-narrative

Skill4 starsChanged 5 months agoMITView on GitHub

Sharpen a founder's fundraising story before they reach out — the one-liner, the elevator pitch, and the round narrative (problem, why now, wedge, traction, why you, the raise). Use when a founder says "help me with my pitch", "what's my one-liner", "tighten my elevator pitch", "what's my fundraising story", or before building a target list or outreach. This is the foundation the other skills draw on — do this first if the story is fuzzy.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read shared/references/outreach-ethics.md — truthful traction applies to the narrative too.

    line 14
  2. Distinctive:

    Interview, then sharpen: Ask the founder to explain it casually first, then mirror back the strongest version and cut the jargon.

    line 47
  3. Very specific:

    If the founder is in the China market or asks for Chinese, use references/zh-talk-tracks.md and first read …

    line 71

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Pitch narrative

A fuzzy story makes every other step harder — targeting, emails, intros, and calls all reuse the same few sentences. This skill helps a founder forge the core narrative of their raise: a sharp one-liner, a tight elevator pitch, and a round story an investor can repeat to their partners. Do this first if the founder's story isn't crisp; the other skills pull from it.

Read shared/references/outreach-ethics.md — truthful traction applies to the narrative too. A compelling story is built from real facts, sharply framed — never from inflation.

What we're producing

  1. The one-liner (one sentence) — what you do, for whom, the wedge. Plain language, no buzzwords, understandable by a smart outsider. This is the subject-line and intro-blurb seed.

    "We help <customer> <do the job> without <the pain>."

  2. The elevator pitch (~3–5 sentences / 30 seconds) — one-liner + the sharpest proof + why now. The version for a hallway or the top of a call.
  3. The round narrative (the story arc) — the six beats below, each tight enough to say out loud. This is what feeds the deck, the email, and the call.

The six beats (see references/narrative-frameworks.md)

  1. Problem — a real, specific pain for a specific customer. Concrete > grand.
  2. Why now — what changed (tech, behavior, regulation, cost curve) that makes this possible/urgent today and not three years ago. Investors fund timing.
  3. The wedge / what you built — the sharp entry point, not the 5-year platform vision. What you do first, and why it's a knife not a spoon.
  4. Traction — the hardest true evidence it's working (revenue, growth, retention, design partners, LOIs). Lead with rate of change.
  5. Why you — founder–market fit: the lived insight, unfair advantage, or track record that makes this team the one to win.
  6. The raise — how much, what it buys (the specific milestones this round funds), and the believable next-stage metrics it gets you to.

Method

  • Interview, then sharpen. Ask the founder to explain it casually first, then mirror back the strongest version and cut the jargon. Founders often bury the best line in paragraph three.
  • Pressure-test each beat. For the wedge: "why start there?" For why-now: "why couldn't this exist in 2019?" For why-you: "what do you know that others don't?" Weak answers are where the pitch leaks.
  • Make it repeatable. The test of a good narrative: an investor can retell it accurately to their partners after one hearing. Optimize for forwardability.
  • Tailor by audience, keep the spine. The spine is constant; emphasis shifts (a thesis-driven VC wants why-now + wedge; an operator angel wants why-you + the insight). Note the shifts; don't rewrite the truth per listener.

Output

  • The one-liner (offer 2–3 phrasings to pick from).
  • The elevator pitch (30-second version).
  • The six-beat round narrative, each beat 1–2 sentences.
  • A short list of the weak spots you probed and how to strengthen them (e.g., "why-now is soft — what specifically changed?").
  • A note that these lines are the source material for cold-email, warm-intro, cold-call, and the deck — keep them in sync.

Bilingual / China market (中文)

If the founder is in the China market or asks for Chinese, use references/zh-talk-tracks.md and first read shared/references/china-market-playbook.md. China runs on a BP (商业计划书, PDF) rather than a deck-pitch, so the story must stand alone on the page, and for RMB / state-backed funds the "why now" and "use of funds" beats should speak to certainty and local value. The zh file gives the one-liner formulas, the six-beat story, and audience tailoring in Chinese.

Refuse / push back when

  • The founder wants buzzword-dense "investor-speak" — push for plain language; clarity reads as confidence, jargon reads as hiding.
  • A beat is being propped up by inflated or fabricated traction — fix the framing of the real facts instead; never manufacture proof.
  • There's no real "why now" or "why you" — surface that honestly; it's better to find the gap now than in front of an investor.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.