agentleFS
fjilvvifjilvvi/growthlens/skills/icp-segmentation/SKILL.md

icp-segmentation

Skill2 starsChanged 5 months agoMITView on GitHub

Define the Ideal Customer Profile and audience segments for a product from its website (and any inputs), using a jobs-to-be-done and firmographic/behavioral lens — segments, pains, desired outcomes, objections, triggers, and messaging angles per segment. Use when the user asks to "define our ICP", "who is this for", "segment the audience", "build buyer personas", or "who should we target" from a site or product description.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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 B2B, note there are two profiles: the ICP (the company) and the

    line 42
  2. Distinctive:

    Use the customer's language for pains and outcomes where the site reveals it.

    line 97
  3. Distinctive:

    Don't invent market sizes or percentages.

    line 98
  4. Distinctive:

    Keep ICP (best fit) distinct from TAM (everyone who could buy).

    line 99

≈ “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

ICP & Audience Segmentation

Turn "everyone" into a ranked set of specific, addressable segments — each with its pains, outcomes, objections, and the angle that lands.

What it does

Derives an Ideal Customer Profile and 2–4 priority segments from a product's site and context, using jobs-to-be-done plus firmographic/demographic and behavioral attributes. For each segment it captures the pain, the desired outcome, buying triggers, objections, and a tailored messaging angle — and ranks segments by fit and reachability.

When to use this skill

  • "Define our ICP from this site."
  • "Who is this product actually for? Segment the audience."
  • "Build buyer personas for <product>."
  • "Which segment should we go after first?"

Inputs needed

  • Required: the product website URL, or a clear product description.
  • Helpful: who the user thinks the customer is, their best current customers, price point (filters who can buy), and whether it's B2B or B2C.
  • If B2B, note there are two profiles: the ICP (the company) and the persona/buyer (the human). Ask which the user wants, or do both.

Method

  1. Extract the value & jobs — from the site, what core jobs/outcomes does the product deliver? List the functional, emotional, and social jobs.
  2. Identify candidate segments — who has those jobs? Use real attributes:
    • B2B: industry, company size, role, maturity, tech stack, trigger events.
    • B2C: demographics, life stage, behavior, identity, situation/context.
  3. Define the ICP — the best-fit profile: the characteristics of customers who get the most value, are easiest to reach, and convert/retain best.
  4. Profile each priority segment with:
    • Pain / problem (in their words)
    • Desired outcome (the "better life" after)
    • Buying trigger (what makes them look now)
    • Top objections / anxieties
    • Where to reach them (channels)
    • Messaging angle that resonates
  5. Score & rank — rate each segment on Fit, Value, Reachability, and Competition; recommend the beachhead segment to start with.

Output format

# ICP & Segmentation — <Product>

## TL;DR
- The ICP in one sentence, and the recommended beachhead segment.

## Jobs to be done
- Functional: · Emotional: · Social:

## Ideal Customer Profile
| Attribute | Best-fit value |
|-----------|----------------|
(B2B: industry, size, role, triggers / B2C: demographic, behavior, context)

## Priority segments
### Segment A — <name>
- Pain: · Desired outcome: · Trigger: · Objections: · Reach via: · Angle:
### Segment B — <name>
...

## Segment ranking
| Segment | Fit | Value | Reachability | Competition | Priority |
|---------|-----|-------|--------------|-------------|----------|

## Recommended beachhead & why

Quality bar

  • Segments must be addressable — you can describe how to reach them — not abstract psychographic labels.
  • Use the customer's language for pains and outcomes where the site reveals it.
  • Don't invent market sizes or percentages; rank qualitatively unless given data.
  • Keep ICP (best fit) distinct from TAM (everyone who could buy).

Common mistakes to avoid

  • Personas full of demographic trivia but no jobs, triggers, or objections.
  • One giant "target audience" instead of distinct, rankable segments.
  • Choosing a beachhead by size alone, ignoring reachability and fit.

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.