- Home
- Skills
- Sales & Lead Gen
- lead scoring and qualification designer
Works with the AI Agents you already use
lead scoring and qualification designer
Lead scoring often relies on gut feeling or black-box models that sales teams don't trust.
$2.99
lead scoring and qualification designer
Example session with this skill installed
Design a lead scorecard for our Q3 Enterprise campaign. Fields: Industry (Fit, 20pts), Demo Request (Intent, 50pts). We have 10 test leads with won/lost outcomes and GDPR consent is documented.
- Read your context and instructions
- Compiled the lead scoring
I have processed the Q3 Enterprise campaign data and calculated the lead-priority design. The analysis includes a recommendation for a hot-lead threshold based on your historical outcomes.
Lead Scorecard — Enterprise Q3, 2023-10-27
1. Scope, sources and consent
- Consent Basis: GDPR - Legitimate Interest (E1)
- Sources: CRM Export (E1 - Internal), Marketing Intent Log (E2 - Internal)
- Proxy Screening: No protected attributes detected in 'Industry' or 'Demo Request'.
2. Field definitions and evidence
| Field | Role | Kind | Max points | Evidence | Source | Status |
|---|---|---|---|---|---|---|
| Industry | Fit | Categorical | 20 | Validated | E1 | Active |
| Demo Request | Intent | Boolean | 50 | Validated | E2 | Active |
3. Lead scorecard and segments
| Lead ID | Fit | Intent | Total | Segment | Outcome |
|---|---|---|---|---|---|
| L-9901 | 20 | 50 | 70 | Hot | Won |
| L-9902 | 20 | 0 | 20 | Nurture | Lost |
| L-9903 | 10 | 50 | 60 | Hot | Won |
| L-9904 | 0 | 0 | 0 | Nurture | Lost |
4. Threshold analysis and calibration
| Threshold | Volume | Precision | Capture |
|---|---|---|---|
| 70 | 0.10 | 1.00 | 0.25 |
| 60 | 0.30 | 0.66 | 0.50 |
| 50 | 0.40 | 0.50 | 0.50 |
Recommendation: A Hot threshold of 60 is recommended to meet the 0.60 min_precision requirement.
Calibration: Won Mean: 65, Lost Mean: 10. Separation: 55. AUC: 0.88.
Analytical estimate — validation required due to small sample size.
5. Sales handoff guide
- Hot (>=60): [DRAFT] Direct AE outreach within 4 hours. Requires human approval.
- Warm (20-59): [DRAFT] Add to personalized sequence. Requires human approval.
- Nurture (<20): [DRAFT] Automated monthly newsletter. Requires human approval.
6. Warnings, data quality and review items
- Information gap — organizational validation required: Missing values for 'Industry' in 2 records.
- Management decision required: Proposed handoff actions must be approved by the Sales VP.
Next steps
- Review the recommended hot-lead threshold (60) against AE capacity.
- Confirm the 'Industry' fit weights with the product marketing team.
- Obtain human approval for the draft outreach actions in the handoff guide.
Connects securely to your tools. The creator never sees your data.
About this skill
Lead scoring often relies on gut feeling or black-box models that sales teams don't trust. This skill delivers transparent, deterministic lead-priority designs based on your specific CRM fields, purchase intent signals, and historical outcome data.
What it does
- Designs point-based scorecards using fit and intent rules derived from your CRM field definitions and weights.
- Screens for discriminatory proxies and consent gaps, ensuring protected attributes are excluded from the scoring logic.
- Analyzes hot-lead thresholds by testing candidates against closed-won and closed-lost history to report precision and capture rates.
- Assesses model calibration by measuring mean separation between won and lost leads and providing a rank-based AUC.
- Drafts sales handoff guides that define specific actions for hot, warm, and nurture segments based on the calculated scores.
How it works
- The user provides CRM field definitions, a lead roster with outcomes, and a required consent basis.
- The skill constructs a structured request and executes a deterministic script to calculate points and metrics.
- The script evaluates multiple threshold candidates to identify the optimal "hot lead" cut-off based on historical precision.
- The skill generates a comprehensive report including the scorecard, field definitions, and calibration data.
Frameworks & tools
The skill utilizes a self-contained Python calculation engine (scripts/run.py) and standard JSON schema for data validation and lead processing.
Why this beats prompting it yourself
Generic prompts often hallucinate weights or fail to rigorously screen for protected-attribute proxies. This skill enforces a deterministic calculation trace and strictly separates validated evidence from estimates, providing the technical audit trail needed for sales-marketing alignment.
Use cases
- Auditing existing lead scoring rules against recent closed-won/closed-lost history.
- Designing a new MQL (Marketing Qualified Lead) threshold with documented precision.
- Creating a transparent scorecard for a new product launch based on estimated fit.
- Drafting a standardized sales handoff guide to reduce friction between departments.
Known limitations
This skill provides decision support only and does not fit or re-estimate weights automatically. It requires a non-empty consent basis and refuses personal-level data to maintain privacy hygiene.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Sales & Lead Gen.
Does not re-estimate weights from data. Requires a manual consent basis. Decision support only; no execution of outreach or CRM updates. Small outcome samples require external validation.
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