Skip to content
Agentmart
Submit a tool

ideal-customer-profile

Build an evidence-aware Ideal Customer Profile from customer outcomes, retention, value, time-to-value, churn, win-loss, usage, PMF survey, qualitative…

Skill by ThorStarlord

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/thorstarlord-ideal-customer-profile

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Build an evidence-aware Ideal Customer Profile from customer outcomes, retention, value, time-to-value, churn, win-loss, usage, PMF survey, qualitative research, buying context, and business evidence across profile characteristics, behaviors, Jobs to Be Done, pains, ideal-of-ideal indicators, disqualifiers, and GTM implications. Use for a customer_understanding responsibility and produce ideal_customer_profile. Without sufficient evidence, produce an explicit hypothesis rather than inventing LTV, CAC, churn, willingness-to-pay, buying cycle, revenue, titles, company size, or fit.

Use cases: research

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/ideal-customer-profile

What's inside

Skill name
ideal-customer-profile
Description
Build an evidence-aware Ideal Customer Profile from customer outcomes, retention, value, time-to-value, churn, win-loss, usage, PMF survey, qualitative research, buying context, and business evidence across profile characteristics, behaviors, Jobs to Be Done, pains, ideal-of-ideal indicators, disqualifiers, and GTM implications. Use for a customer_understanding responsibility and produce ideal_customer_profile. Without sufficient evidence, produce an explicit hypothesis rather than inventing LTV, CAC, churn, willingness-to-pay, buying cycle, revenue, titles, company size, or fit.
License
MIT
Instructions
27 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • contract.md · references/

SKILL.md (first lines)

# Ideal customer profile

Satisfy a `customer_understanding` responsibility by producing `ideal_customer_profile`.

## Inputs

Require a product/service, market or segment scope, evidence/currentness window, and an inventory of available customer evidence. Valuable evidence includes retention/cohort, usage, churn, win-loss, revenue/LTV, CAC, time-to-value, PMF survey, interviews, NPS/CSAT, support, and buying-process evidence.

## Procedure

1. Read [references/contract.md](references/contract.md).
2. Bind the segment and evidence window before interpreting customer fit.
3. Inventory available evidence and separate direct observations from derived values, agent inference, hypotheses, and unresolved claims.
4. Identify high-value patterns only from supplied evidence; otherwise retain them as hypotheses.
5. Describe company/person/decision profile, behaviors, Jobs to Be Done, needs/pains, ideal-of-ideal indicators, and disqualifiers at the evidence strength actually supported.
6. Distinguish buyer, champion, and user roles only when evidence warrants them; do not invent titles, committees, budgets, or purchase processes.
7. Treat LTV, churn, CAC, time-to-value, NPS, revenue, deal size, willingness-to-pay, purchase cycle, and product-usage statistics as observed only with durable evidence.
8. Preserve material contradictions and segment ambiguity as unresolved questions rather than forcing a single ideal profile.
9. Derive GTM implications as proposed recommendations, not externally validated channel, message, qualification, or sales-policy truth.
10. Stop when remaining uncertainty would not change the bounded decision, or when required evidence is unavailable/outside authority.
11. Return `ideal_customer_profile` and control.

## Boundary

`ICP hypothesis != validated segment`, `high-value pattern != causal explanation`, `disqualifier recommendation != sales policy`, `GTM implication != external execution authority`, and `artifact valid != customer fit established`.

From ThorStarlord/sensemaking-skills, MIT.

More from ThorStarlord/sensemaking-skills

Signals

Stars
0
Forks
0
Open issues
7
Last commit (this folder)
Sep 10, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from ThorStarlord

Cite this page

ideal-customer-profile skill. Agent Mart. https://agentmart.dev/skills/thorstarlord-ideal-customer-profile (last updated 2026-10-24)