agentleFS
mypip-iomypip-io/skills/research-one-person/SKILL.md

research-one-person

Skill1 starsChanged 26 days agoMITView on GitHub

Researches one potential customer from what they've shared publicly, so a founder can find something genuine to say and know whether to write at all. Produces a short brief to act on in a few minutes. Use when a founder wants to research someone before messaging them, personalise a first message properly, prepare for a conversation, or asks \"what should I say to this person\".

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Start where you found them: Read the post or comment that caught your attention, and the conversation around it.

    line 21
  2. Distinctive:

    Don't quote their words back at them.

    line 46
  3. Distinctive:

    If there's nothing genuine to say, wait.

    line 47

≈ “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

Research one person

Find what a name and a job title could never tell you.

Most "personalised" messages are a template with a first name and a company dropped in, and people can tell within a line. Everyone leaves a trail online, and founders, creators and decision-makers most of all: posts, talks, articles, newsletters, interviews. Most of them want their work to be found. Reading it properly is how you find something real to say.

The reaction you're after is "yes, that's exactly the problem I have". The reaction to avoid is "how do you know that?"

What you need

  1. What you sell, in one line.
  2. Who the person is, and where you came across them.

Steps

  1. Start where you found them. Read the post or comment that caught your attention, and the conversation around it.
  2. Read their recent public work. What are they building, writing or talking about? What do they seem to care about? What have they already tried?
  3. Look for the real reason to write. Something they're working through where you have something genuine to offer. If you can't find one, the honest answer is not to write yet.
  4. Check fit. Are they likely to buy, or do they sell something similar? Is the problem current, or something they solved long ago?
  5. Decide what not to mention. Anything personal, anything from somewhere they wouldn't expect you to have looked, anything that makes them wonder how you know it. Knowing it can still help you understand them. Saying it rarely helps.

Output

Who: <one line>
Where you found them: <link and what they said, in your own words>
What they're working through: <a sentence or two>
The real reason to write: <one sentence, or "none yet">
What to open with: <something they'd be glad you noticed>
Leave out: <what you know but shouldn't mention>
Fit: <likely buyer / not a buyer / unsure, and why>

Rules

  • Respect is the point. Research is to understand them, not to show off what you found.
  • Don't quote their words back at them. Show you understood them in your own words.
  • If there's nothing genuine to say, wait.

With MyPip (coming)

MyPip researches the best people it finds for you every day and gives you the reason they're ready and the way in. When the MyPip MCP is live, this skill will be able to open those briefs directly.

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.