agentleFS
alebgl77alebgl77/claude-inc/skills/account-research/SKILL.md

account-research

Skill21 starsChanged 4 months agoMITView on GitHub

Researches a company or person and returns actionable sales intel — what they do, recent signals, likely pains, entry angle and talk tracks. Use when the user says "research this company", "who is this prospect", "intel on X before I reach out", or before any outreach, call or proposal targeting a specific account.

15 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Always before draft-outreach or call-prep — research is their fuel

    line 15

“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “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

Account Research — Prospector

"Know them better than their own website does."

When to use

  • "Research {company} before I contact them"
  • "Who is {name} at {company}?"
  • "Why would {company} buy {my product}?"
  • Always before draft-outreach or call-prep — research is their fuel
  • Works from public web (search + site + LinkedIn-style signals); upgrades with any CRM/enrichment MCP if connected

Workflow

  1. Frame the mission: what does the user sell, and what would make this account a good or bad fit? Write the fit hypothesis first.
  2. Company scan: what they do (in one sentence a human would say), size/stage signals, business model, who their customers are.
  3. Signal sweep: last 90 days — funding, hiring, launches, leadership changes, tech choices, public complaints. Date every signal.
  4. People map: likely buyer, likely champion, likely blocker — with role-based reasoning when names aren't public.
  5. Pain hypotheses: top 3, each tied to an observed signal (not generic industry pains).
  6. Entry angle: the single most credible reason to talk to them THIS month, plus 2 conversation openers in natural language.
  7. Disqualifiers: honest list of reasons to skip this account. Recommendation: pursue / park / drop.

Output format

## Account brief — {company}
Fit hypothesis: {1 line} · Verdict: PURSUE / PARK / DROP

**What they do**: ...
**Signals (dated)**: • {date} — {signal} → {why it matters}
**People**: buyer {role} · champion {role} · blocker {role}
**Top pains (evidence-tied)**: 1. ... 2. ... 3. ...
**Entry angle**: ...
**Openers**: "..." / "..."
**Disqualifiers**: ...

Quality bar

  • Every signal is dated and sourced (link or "observed on their site")
  • Pains reference evidence, not industry clichés
  • The entry angle would survive being read aloud to the prospect
  • A clear verdict — no fence-sitting
  • Under 1 page; a rep can absorb it in 3 minutes

Example

Ask: "Research Maison Verdier (wine e-commerce) for my SEO service." Produced: brief showing recent PrestaShop 9 migration + 2 job posts for marketing, pain hypothesis "traffic lost in migration", entry angle referencing their broken category pages, verdict PURSUE with two openers.

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.