About icp-validation
icp-validation is a skill for assessing a company against a defined ideal customer profile (ICP). It scores segment, size, active signals, and target-role fit, then returns a verdict with reasoning.
Key features
- 01Scores four ICP dimensions
- 02Checks company website signals
- 03Uses LinkedIn data via MCP
- 04Returns a fit verdict with reasoning
Use cases
- 01Prioritizing companies for outreach
- 02Evaluating a prospect against an ICP
MCP support
The skill checks LinkedIn through MCP for headcount, hiring, open roles, and leadership information. If that data is unavailable, it flags the limitation and uses public signals.
Install
Copy the command and run it in a terminal.
$
npx skills add https:/ / github.com/ victor-shulga/ outbound-engine-skills --skill icp-validationAfter installing, type/icp-validationin Claude Code to confirm it loaded.
Details
From the project READMEICP Validation
Validate a company against defined ICP criteria and return a scored fit verdict.
What you need
- Company name or website URL
- ICP definition (provide inline or reference your ICP file)
Process
- Pull the company's website and scan for: team size indicators, tech stack signals, product type, industry, and growth stage
- Check LinkedIn via MCP for: headcount, recent hires, open roles, and leadership profile
- Score fit against each ICP dimension (1-3 per dimension):
- Segment fit: does the company match the target segment?
- Size fit: does headcount/revenue match the ICP range?
- Signal fit: is there an active reason they'd respond now?
- Role fit: is the target persona present and reachable?
- Return a one-line verdict + reasoning
Output format
Company: [Name]
Fit score: [X/12]
Verdict: [Strong fit / Marginal fit / Not a fit]
Segment: [score] — [one line reason]
Size: [score] — [one line reason]
Signal: [score] — [one line reason]
Role: [score] — [one line reason]
Why a buyer, not a competitor: [one line — what they sell and to whom, and why that makes them a buyer of your offer]
Recommended action: [Tier 1 / Tier 2 / Skip]
Skip reason: [ring 1 business model / ring 2 competitor / ring 3 size or geo / ring 4 already ours] — [one line]
Notes
- If ICP isn't defined, ask for it before proceeding
- If LinkedIn data is unavailable via MCP, flag it and use public signals only
- "Marginal fit" means worth a Tier 2 sequence, not skip
Comments
Markdown supported