Works with the AI Agents you already use
ideal customer profile builder
Gut-feel marketing and manual spreadsheet analysis fail to capture the true drivers of your sales success.
$2.99
ideal customer profile builder
Example session with this skill installed
Analyze the provided CSV of 200 closed-won and 50 closed-lost records from our CRM. Map the attributes to our product capabilities and define the fit tiers based on win rate lift.
- Read your context and instructions
- Compiled the ideal customer profile
I have processed the 250 records provided. 15 records were excluded due to missing consent flags or outcomes outside the analysis scope.
Ideal Customer Profile — Acme Corp, 2024-05-20
1. Scope, sources, consent and assumptions
- Sources: CRM Export (E1).
- Access Scope: Sales performance analysis for Q1-Q2.
Exclusions: Personally identifiable information and sensitive attributes (age, gender) were excluded from analysis.
2. Population and exclusions
- Total Records: 250
- Analyzed: 235 (180 Wins, 55 Losses)
- Baseline Success Rate: 76.6%
- Exclusions: 15 (10 Consent missing, 5 Future dated)
3. Fit factors and evidence
| Rank | Attribute | Value | n | Successes | Success rate | Lift | Wilson lower | Evidence score | Level |
|---|---|---|---|---|---|---|---|---|---|
| 1 | Industry | Fintech | 45 | 42 | 93.3% | 1.22 | 0.81 | 0.88 | High |
| 2 | Employee_Count | 500-1000 | 30 | 27 | 90.0% | 1.17 | 0.74 | 0.82 | High |
| 3 | Region | North America | 110 | 90 | 81.8% | 1.07 | 0.73 | 0.75 | Medium |
4. ICP definition and fit criteria
Analytical estimate — validation required (In-sample only)
- Definition: Industry is Fintech AND Employee_Count is 500-1000.
- Performance: Precision 92%, Recall 38%, Coverage 20%, Lift 1.20.
5. Selection bias and data-quality flags
- Severity: Low: Results rely heavily on Source E1; multi-source validation recommended.
- Warning: Small sample size for 'Industry: Healthcare' (n=4) resulted in suppression.
6. Capability alignment and sales-note signals
- Fintech: Linked to High-Frequency Transaction API.
- Employee_Count 500-1000: Information gap — organizational validation required.
7. Proposed actions and items for human review
- Draft Action: Increase LinkedIn ad spend for Fintech segment. (Blocker: Budget approval).
- Draft Action: Update CRM fit fields for new leads. (Blocker: Ops sync).
Management decision required: Adopting this ICP and associated budget changes requires professional judgment.
Next steps
- Review the Fintech/API alignment with the Product team.
- Confirm if the 500-1000 employee range aligns with our current seat-based pricing model.
- Provide the missing consent flags for the 10 excluded records to increase statistical power.
Connects securely to your tools. The creator never sees your data.
About this skill
Gut-feel marketing and manual spreadsheet analysis fail to capture the true drivers of your sales success. This skill replaces guesswork with a deterministic analysis of your historical deal data to identify the specific firmographic and behavioral traits that actually predict won outcomes.
What it does
- Attribute lift calculation identifies which customer traits provide the highest statistical lift in win rates compared to your baseline.
- Wilson evidence scoring applies statistical confidence intervals to ensure your ICP is based on significant data, not outliers.
- Fit tiering categorizes potential customers into tiered segments based on historical performance and evidence strength.
- Bias detection flags selection bias, small sample sizes, and data quality issues that could undermine your targeting strategy.
- Capability mapping links identified fit criteria directly to your product capabilities and sales-note signals.
How it works
- Prepare a
request.jsonfile containing your pseudonymous customer records, outcomes, and access scope. - Execute the included Python analysis script to process the data using standardized statistical formulas.
- Review the generated profile, including precision and recall metrics for the proposed ICP definition.
- Evaluate the draft actions and capability alignment for human approval and strategic implementation.
Frameworks & tools
The skill relies on a self-contained Python analysis engine that handles all counts, rates, and intervals. It uses JSON schemas for data validation and produces structured Markdown reports for decision support.
Why this beats prompting it yourself
Standard LLMs hallucinate statistical correlations and struggle with precise confidence intervals like Wilson lower bounds. This skill uses a deterministic script to ensure every number is calculated accurately, while the agent focuses on explaining the evidence and flagging risks like selection bias.
Use cases
- Analyzing won and lost records to find predictive traits for a new product launch.
- Validating an existing "gut-feel" ICP against actual historical deal data.
- Identifying information gaps where customer traits lack linked product capabilities.
- Generating evidence-based fit criteria for sales and marketing alignment.
Known limitations
Does not support customer persona synthesis from qualitative interviews or lead scoring for individual prospects. Requires structured historical records with clear won/lost outcomes and explicit consent fields to process data.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
Requires structured JSON input with consent flags. Does not perform qualitative persona research or lead scoring. Minimum group sizes apply to prevent reconstruction of individual records.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 days ago