Guide · Agent skill
How to use the Ideal Customer Profile agent skill
Updated · written with AI from the project's own documentation and checked against our catalogue data
The ideal-customer-profile skill is an agent skill that takes your customer research and turns it into a structured Ideal Customer Profile (ICP). It covers who your best customers are, how they buy, what jobs they are trying to get done and which pain points matter most. This guide explains what an agent skill is, how to install this one, how to ask for an ICP in plain language and what to check in the output.
Ideal Customer Profilephuryn/pm-skills · MIT Download the skill Quick start
- 1Download the ZIP. Get the ideal-customer-profile ZIP from this page under the MIT licence.
- 2Unzip into a skills folder. Place the skill folder in ~/.claude/skills/ for personal use, or in .claude/skills/ inside a project.
- 3Or upload in the Claude apps. Go to Settings → Capabilities → Skills and upload the ZIP.
- 4Gather your research. Collect PMF survey responses, interview notes, win/loss data or usage analytics.
- 5Ask for an ICP. Make a natural request such as defining your ICP from the attached survey data.
- 6Review the output. Check that the firmographic, behavioral, JTBD and disqualification sections are present and grounded in your data.
- 7Revisit regularly. Update the ICP as you gather more customer data.
What an agent skill is and what this one does
An agent skill is a folder containing a SKILL.md file with instructions that an AI agent can load when a task matches the skill's description. This skill is one of those instruction sets. Once it is installed, the agent knows how to structure customer research into an ICP.
The skill is a text-based analysis method, not a software tool. It does not connect to your CRM or survey platform. You provide the research data, and the agent produces the profile.
- Demographics: company size (employees, revenue), industry, geography, job title and department
- Behaviors: how customers discover, evaluate and adopt solutions, and how they make decisions
- Jobs to be done: primary, secondary, emotional and social jobs, and the success metrics for each
- Needs and pain points: the problems that matter most, current workarounds and barriers to solving them
- Go-to-market implications, plus disqualification criteria for who is not a good fit
Install the ideal-customer-profile skill
Download the ZIP for this skill from this page. You can install it in one of two ways.
Option 1 is a personal install for Claude Code: unzip the file into ~/.claude/skills/ so the skill folder sits there. Option 2 is a project install: unzip it into the .claude/skills/ folder inside your project.
Option 3 is to upload the ZIP in the Claude apps under Settings → Capabilities → Skills.
- Personal install: ~/.claude/skills/
- Project install: .claude/skills/ inside your project folder
- Claude apps: Settings → Capabilities → Skills, then upload the ZIP
Trigger the skill with natural requests
You do not need a special command. The skill's description says to use it when defining an ICP, analyzing PMF survey data or understanding who your best customers are, so phrasing your request around those tasks is usually enough.
The source also describes passing input with $ARGUMENTS. Input can include research data such as surveys, interviews and transcripts, customer success metrics, product usage analytics, sales activity and win/loss data, an existing customer database and competitive intelligence.
- Define our ICP from these product-market fit survey responses: [paste or attach data]
- Who are our best customers? Here is our win/loss data from last quarter: [data]
- Analyze these interview transcripts and describe the jobs our customers are trying to get done
- Based on our usage analytics, which customer segments show the lowest churn and highest expansion?
What the output contains
The source lists the sections the output should include. Check that the result covers them, and treat any missing section as a gap to ask about.
The output includes a firmographic profile, a behavioral profile, a complete JTBD mapping, the top 5-7 pain points, quantified impact metrics where data allows, the decision-making process, a typical customer journey, go-to-market implications, disqualification criteria and a high-value segment within the ICP.
- Firmographic and behavioral profile
- Jobs to be done mapping (functional, emotional, social)
- Top 5-7 pain points and specific needs
- Decision-making process and key stakeholders
- Go-to-market implications and messaging
- Disqualification criteria (who is NOT a good fit)
- High-value segment within the ICP
Tips for better results
The quality of the profile depends on the research you give it. The skill is aimed at company-level targeting, and the source notes that without customer data the output would be guesswork, so start with real customer evidence.
The source recommends combining quantitative and qualitative data, interviewing 10+ high-value customers for pattern identification and defining both an ideal ICP and acceptable secondary segments.
- Use quantitative and qualitative data together
- Interview 10+ high-value customers for pattern identification
- Look for non-obvious demographic patterns, since outliers can be high-value
- Define acceptable secondary segments alongside the ideal ICP
- Revisit the ICP quarterly as you gather more data
- Share the ICP across marketing, sales and product
- The ICP should drive focus, not exclude all others
Safety notes: scripts and network access
This skill runs no scripts and uses no network access, according to its listing. It only includes a SKILL.md file. It requires nothing beyond the research data you choose to provide.
Because the skill works on the data you supply, review what you paste in. Do not share personal data you are not permitted to use.
- Runs scripts: no
- Uses network: no
- Files: SKILL.md only
- Not for making decisions about individuals, such as screening people by demographics, because of fairness and privacy concerns
What people use it for
- Defining who a product is for after collecting product-market fit survey results
- Helping a sales team decide where to focus outreach and how to prioritize leads
- Turning interview notes into a clear description of target customers for a founder or PM
- Identifying which customer segments show high expansion or low churn in usage analytics
- Writing go-to-market messaging and listing who is not a good fit
Frequently asked questions
How do I install the ideal customer profile skill?
Download the ZIP from this page and unzip it into ~/.claude/skills/ for personal use, or into .claude/skills/ inside a project. You can also upload the ZIP in the Claude apps under Settings → Capabilities → Skills.
Is the ideal customer profile skill free?
The skill is published under the MIT licence, as stated on this page. Check the licence file in the source repository for the full terms.
What does the skill need to run?
The listing states that it requires nothing in particular. It runs no scripts and uses no network access. The main input is your own customer research, such as survey responses or interview notes.
Can I use it without any customer data?
The skill is not meant for teams with no customer data yet. Its output depends on research input and would otherwise be guesswork, so start with customer interviews first.
Does the skill connect to my CRM or survey tool?
No. It is a text-based analysis method. You provide the data, such as exported survey responses or win/loss records, and the agent analyses it.
How is this different from a manual ICP template?
The skill follows a structured framework covering demographics, behaviors, jobs to be done and needs, and adds go-to-market implications and disqualification criteria. The quality still depends on the data you supply and your review of the result.
New agent skills, repos and AI tools — every week
The best new skills and open-source projects, the fastest-growing repos, and one free prompt. Five minutes to read. Unsubscribe anytime.
Our verdict
Use this skill if you have customer research, such as PMF survey results, interview notes or win/loss data, and want a structured ICP that covers who buys, what jobs they need done and who is not a fit. Pick something else if you have no customer data yet, in which case start with customer interviews, or if you need to make decisions about individual people, which this company-level skill is not designed for.
Download the skill