agentleFS
volodymyrkhodonovychvolodymyrkhodonovych/claude-sales-skills/skills/account-research-brief/SKILL.md

account-research-brief

Skill1 starsChanged 10 days agoMITView on GitHub

Builds a sourced research brief on a target B2B company and contact before outreach, with recent triggers, likely priorities and a suggested first-touch angle. Use whenever the user wants to research, look into or prepare to approach a prospect company or person, asks "who is X at Y", or wants a reason to reach out, even if they never say "research".

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. prosyo-ai/gtm-skill★ 13same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository7 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If these are still placeholders, ask once.

    line 18
  2. Distinctive:

    Ask only for what is missing:

    line 21
  3. Distinctive:

    Search the web for the company: what it does, size or stage if public, products, customers, recent news.

    line 26
  4. Distinctive:

    Search for the contact: current role, tenure, public statements, talks or posts about relevant topics.

    line 27
  5. Distinctive:

    Look for recent, checkable triggers: funding, launches, hires, job posts, contracts, regulation, events.

    line 28
  6. Distinctive:

    Write the brief in the format below and flag what is unverified.

    line 30
  7. Distinctive:

    Don't force a trigger: If nothing real and recent exists, say so.

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Account research brief

Good outreach starts with a real reason to write. This brief finds that reason in public sources and keeps facts apart from guesses, so the email that follows can be specific without being invented.

Setup (fill in once)

  • WHAT_WE_DO: {{one plain sentence on what you sell}}
  • IDEAL_CUSTOMER: {{a few lines: industries, company size, roles you sell to}}

If these are still placeholders, ask once. Without them the fit assessment is guesswork.

Inputs

Ask only for what is missing:

  • Target company, and the contact's name and role if known
  • Why this account is of interest, if the user has a reason

Steps

  1. Search the web for the company: what it does, size or stage if public, products, customers, recent news. Record the source and date of each finding.
  2. Search for the contact: current role, tenure, public statements, talks or posts about relevant topics. Use professional sources only.
  3. Look for recent, checkable triggers: funding, launches, hires, job posts, contracts, regulation, events. Prefer the last few months, since older news makes a weak opener.
  4. Compare with WHAT_WE_DO and IDEAL_CUSTOMER and note the fit honestly, including where it is weak.
  5. Write the brief in the format below and flag what is unverified.

Format

  • Company snapshot: 3–4 bullets with sources.
  • Contact: role, tenure, one relevant public fact. Write "not found" if there is nothing.
  • Recent triggers: dated, each with a source link. Write "none found" if there are none rather than stretching.
  • Likely priorities: 2–3, each marked as inferred from which finding.
  • Fit: strong, partial or weak, with the reason in one sentence.
  • Suggested angle: one line a first-touch email could build on. Hand this to the cold-outreach-email skill if the user wants the email.
  • Open questions: what the user should verify before sending.

Rules, and why

  • Every claim carries a source and date. The brief is only useful if the user can check it before acting on it.
  • Mark inference as inference. A guessed priority stated as fact turns into a wrong first line in an email.
  • Public, professional information only. Skip family, home address and personal social accounts. They add nothing to a business reason to write and can make outreach feel invasive.
  • Don't force a trigger. If nothing real and recent exists, say so; a relevance-based email is better than a fake hook.
  • Stop and ask if the target is a private individual rather than a business contact.

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.