account-research-brief

Installation
SKILL.md

Run this before a first meeting or an ABM push. It produces a one-page brief where every claim is tagged as evidence-backed or inference, so the AE knows what they can say out loud.

The play

  1. Resolve the company to a stable identifier first. Match on the company's own URL slug rather than its display name. Name search returns near-matches and you will research the wrong entity, which is worse than researching nothing.

  2. Pull firmographics. Size, industry, headquarters, founding year, description, specialities. This is the skeleton the rest hangs on.

  3. Read composition, not just headcount. How the employee base splits by function and seniority says more than a total. A company that is 60% engineering sells differently than one that is 60% sales.

  4. Extract positioning pillars. Cluster the company's own description, tagline, and specialities into three to six themes: product areas, target buyer, stated differentiators. Name each pillar and cite the exact source phrase. These are the words the buyer already uses about themselves.

  5. Build a SWOT where every line is tagged. Mark each point evidence (traceable to something retrieved) or inference (your read). An untagged SWOT is opinion wearing a suit, and an AE who repeats an inference as fact in a meeting loses the room.

  6. Ask before you spend on people. Confirm two things with the requester: which titles matter, and how many employee records to pull. Skipping this is how a routine brief turns into a surprise bill.

  7. Read hiring as a live signal. Recent joiners, by function, are the most current evidence you have of where budget is moving. A team that added four engineers and no marketers last quarter is telling you something.

  8. Deliver both shapes. Structured data for the next automation step, and a short human brief for the AE. They have different readers and different lifespans.

Installs
2
GitHub Stars
165
First Seen
Sep 16, 2026
account-research-brief — swan-gtm/gtm-skills