agentleFS
prosyo-aiprosyo-ai/gtm-skill/skills/prospect-research-brief/SKILL.md

prospect-research-brief

Skill13 starsChanged 24 days agoMITView on GitHub

Use this skill when you need to research a specific person before reaching out or meeting them: \"look up this prospect\", \"what do I say to Jane\", \"find a personalised first line\". Reads the person's role, tenure, public posts, talks, career moves and company context, and produces a short brief with what they care about, what they are measured on, conversation hooks with sources, and a personalised opener for email and LinkedIn. For SDRs, AEs, founders and recruiters doing B2B outreach.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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:

    Use this for one person you are about to contact or meet.

    line 16
  2. Distinctive:

    Check they still work at the company and in the role.

    line 27
  3. Distinctive:

    When nothing specific exists, the brief says so and falls back to a role-and-trigger opener instead of inventing intimacy.

    line 60
  4. Distinctive:

    MUST confirm the person's current role before writing.

    line 65
  5. Distinctive:

    MUST attach a source to every hook.

    line 66
  6. Distinctive:

    NEVER use personal life details: family, health, location history, photos.

    line 67
  7. Distinctive:

    NEVER claim to have read or watched something you did not.

    line 68
  8. Distinctive:

    NEVER mention tracking data such as profile views or website visits in the opener.

    line 69

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Use this for one person you are about to contact or meet. It produces a brief a rep can read in 60 seconds and a first line that proves the message was written for them.

Inputs

  • Name, company and title, plus a profile link if available.
  • Your offer and the persona this person maps to.
  • Any CRM history with this person or their company.

The play

1. Confirm the person

Check they still work at the company and in the role. Roughly one in five B2B contacts changes jobs each year; a brief about the wrong job is wasted.

2. Gather in this order

  1. Their own words: posts, comments, articles, podcast or event appearances from the last 6 months.
  2. Career path: previous companies and roles, tenure in this role. A person 60 days into a role behaves differently from one 4 years in.
  3. Company context: one or two triggers from the account level that land on their desk.
  4. Shared ground: same former employer, same community, same school, a mutual customer. Use only if real and relevant.

3. Rank the hooks

Score each hook on two questions: is it specific to this person, and does it connect to the problem you solve? Keep only hooks that pass both. Read references/hook-ranking.md for the ranking grid and examples of strong and weak hooks.

4. Write the openers

One for email, one for LinkedIn. One or two sentences each, built from the strongest hook, ending in a natural bridge to the problem, not to your product.

Output format

Person: <name> - <title> at <company> - <tenure in role>
Confirmed current: yes/no (source)
Measured on: <likely metrics for the role>
What they talk about: <2-3 themes with links>
Hooks (ranked):
  1. <hook> - <source> - <why it connects>
  2. ...
Email opener: <1-2 sentences>
LinkedIn opener: <1-2 sentences, more conversational>
Avoid: <topics or claims to stay away from>

What good looks like

  • The opener could not be sent to anyone else. Swap the name and it breaks.
  • It references their thinking, not their resume. "Loved your post" is weak; "your point that SDR ramp is a data problem, not a training problem" is strong.
  • When nothing specific exists, the brief says so and falls back to a role-and-trigger opener instead of inventing intimacy.
  • The common mistake is personalising on trivia (alma mater, hometown, a sports team) that has nothing to do with the reason for the message.

Rules

  • MUST confirm the person's current role before writing.
  • MUST attach a source to every hook.
  • NEVER use personal life details: family, health, location history, photos.
  • NEVER claim to have read or watched something you did not.
  • NEVER mention tracking data such as profile views or website visits in the opener.

Example prompts

  • "Research Priya Shah, VP Revenue at Lumen. Write an email and a LinkedIn opener."
  • "I meet Tom Becker tomorrow. Give me a 60-second brief."
  • "Find a real hook for each of these 15 prospects, or tell me when there isn't one."

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.