proof-points

Proof Points

How This Works

Every stat, quote, and case study in your messaging is a promise — and every promise sales, legal, or a skeptical prospect can eventually ask you to back up. Almost no company has a clean registry of these; what they actually have is a mash of sales decks, battlecards, one-pagers, and case study PDFs, each one repeating (and slowly staling) numbers nobody's re-checked since the deck was built. This skill is both the intake and the gate: it mines claim candidates out of that mess, then makes sure nothing gets called "approved" without a source, no customer name ships without documented permission to use it, and every forbidden claim carries a stated reason — not a bare prohibition nobody can act on. It deepens your brain's existing Section 6 in place, the same Proof Points Registry message-house and positioning-messaging already read.

Step 0 — Load brain Section 6 (current registry, however thin).

Step 1 — Classify the request: Extract from source material, Add one claim directly, Verify a claim before it ships, or Audit the existing registry.

Step 2 (Extract) — Mine claim-shaped statements out of pasted decks, battlecards, case studies, or other GTM collateral; every candidate starts flagged, regardless of whether the source material cites its own source.

Step 3 (Add) — Require a source for a directly-supplied claim; unsourced claims get flagged, never silently approved.

Step 4 (Verify) — Check a claim someone wants to use against the registry: approved, forbidden, or not yet registered.

Step 5 (Audit) — Walk every existing entry for missing sources, stale dates, undocumented customer names, and unsupported superlatives.

Step 6 — Deepen brain Section 6 with the result (on user confirmation).

Step 7 — Learning Close: log the session to /context/skill-sessions.md.

---

Trigger

• When: Building a proof points registry from scratch out of existing sales decks, battlecards, case studies, or pricing pages; adding a single new metric, quote, or case study directly; checking whether a specific stat or phrase is safe to use before it ships in copy; or auditing brain Section 6 for unsourced claims, stale proof, undocumented customer names, or unsupported superlatives.
• Not for: Structuring raw, unstructured customer conversation — a call recording or interview transcript nobody's synthesized yet — into discovery insights → interview-summary, run first. That's a qualitatively different task (JTBD synthesis of what customers said) from this skill's Extract mode, which mines already-written claims out of already-somewhat-structured GTM collateral (a deck, a battlecard, a case study doc) — if Extract mode turns up a customer quote that traces back to a raw call nobody's written up, route that call through interview-summary first, then bring the resulting quote back here. Vocabulary, tone, and forbidden language (not claims) → brand-voice. Building the positioning statement or messaging hierarchy itself → positioning-messaging, run this first so it has a gated registry to cite from.
• Example prompts:
  • "Pull proof points out of this battlecard"
  • "We don't have a registry — start one from these 3 sales decks"
  • "Add a proof point: 40% faster onboarding, from our Q3 customer survey"
  • "Can I say 'industry-leading' in this deck?"
  • "Audit our proof points — anything stale or unsourced?"