Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Weighted lead scoring engine that evaluates prospects using Clay MCP enrichment data across five dimensions: company fit, title seniority, tech stack overlap, social presence, and engagement signals. Triggers when the user asks to score leads, prioritize contacts, or rank prospects. Outputs a tiered classification (Hot, Warm, Cold, Skip) with a summary table and top signal per contact for fast decision-making.
.claude/skills/0xjitsu-lead-scorer/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 98% | 69 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 310% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 125% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 42% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 5% | 0% |
Weighted lead scoring engine from Clay enrichment data.
Activate this skill when the user:
Each dimension produces a score from 0 to 100. The final score is a weighted sum.
Evaluate how well the prospect's company matches the ideal customer profile.
| Signal | Score | How to Assess | |-------------------|--------|--------------------------------------------------| | Industry match | 0-30 | Exact match = 30, adjacent = 15, unrelated = 0 | | Company size | 0-25 | Sweet spot (50-500) = 25, too small/large = 10 | | Funding stage | 0-25 | Series A-B = 25, Seed = 20, Series C+ = 15, Unknown = 5 | | Revenue signals | 0-20 | Growing = 20, Stable = 10, Declining = 0 |
Data source: Clay find-and-enrich-company and ask-question-about-accounts.
Map the contact's role to a seniority score.
| Level | Score | Example Titles | |--------------|-------|-----------------------------------------------| | C-Level | 100 | CEO, CTO, CFO, CPO | | VP | 80 | VP Engineering, VP Product, VP Sales | | Director | 60 | Director of Engineering, Head of DevRel | | Manager | 40 | Engineering Manager, Product Manager | | IC (Senior) | 20 | Senior Engineer, Staff Engineer, Lead Dev | | IC (Junior) | 10 | Software Engineer, Developer, Analyst | | Unknown | 5 | Title not found or ambiguous |
Data source: Clay find-and-enrich-contacts-at-company.
Compare the prospect's tech stack against the user's target stack.
| Overlap Level | Score | Definition | |-----------------------|-------|-----------------------------------------------| | High overlap (3+) | 100 | 3 or more shared technologies | | Medium overlap (1-2) | 60 | 1-2 shared technologies | | Adjacent stack | 30 | Different but compatible ecosystem | | No overlap | 0 | Completely different stack |
The user must define the target tech stack before scoring. Example: ["TypeScript", "Solidity", "Next.js", "Foundry"].
Data source: Clay enrichment fields for the contact and company.
Measure the contact's public visibility and influence.
| Signal | Score | Threshold | |-------------------------|-------|--------------------------------------------| | GitHub stars (repos) | 0-30 | 1000+ = 30, 100+ = 20, 10+ = 10, <10 = 0 | | Twitter/X followers | 0-30 | 10k+ = 30, 1k+ = 20, 100+ = 10, <100 = 0 | | Newsletter subscribers | 0-20 | 5k+ = 20, 1k+ = 10, <1k = 5 | | Conference speaker | 0-20 | Recent (12mo) = 20, Ever = 10, Never = 0 |
Data source: Clay enrichment and ask-question-about-accounts.
Track prior interactions with your brand or content.
| Signal | Score | Detection Method | |---------------------------|-------|---------------------------------------------| | Replied to previous email | 40 | gmail_search_messages for prior threads | | Opened previous email | 20 | Tracking pixel data if available | | Attended your event | 20 | Check Supabase event attendees table | | Visited your site | 10 | PostHog or analytics data if available | | No prior engagement | 0 | Default |
final_score = (company_fit * 0.30)
+ (title_seniority * 0.25)
+ (tech_overlap * 0.20)
+ (social_presence * 0.15)
+ (engagement * 0.10)| Tier | Score Range | Action | |--------|-------------|-------------------------------------------------| | Hot | 80-100 | Priority outreach, L3 personalization, Day 0 send | | Warm | 50-79 | Standard sequence, L2 personalization | | Cold | 20-49 | Low priority, L1 personalization, batch later | | Skip | 0-19 | Do not contact, remove from campaign |
Present results as a sorted table, highest score first:
| Name | Company | Score | Tier | Top Signal |
|---------------|----------------|-------|------|-------------------------------|
| Alex Chen | Acme Protocol | 92 | Hot | CTO + 3 stack overlaps |
| Jordan Lee | Nova Labs | 74 | Warm | Director + recent Series A |
| Sam Park | BuildCo | 45 | Cold | IC + no engagement history |
| Chris Taylor | Random Corp | 12 | Skip | No industry match, no overlap |The "Top Signal" column should contain the single strongest scoring factor for that contact, written as a human-readable phrase.
When called from campaign-sequencer:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 3,687 | 5,802 | +57% | 1 | 1 | 0% | 654 | 2,679 | +310% | 0 | 0 | — |
case-02 | fail→pass | 6,522 | 5,978 | -8% | 1 | 1 | 0% | 1,234 | 2,778 | +125% | 0 | 0 | — |
case-03 | fail→pass | 10,699 | 7,085 | -34% | 1 | 1 | 0% | 1,969 | 2,798 | +42% | 0 | 0 | — |
case-04 | fail→pass | 10,805 | 3,263 | -70% | 1 | 1 | 0% | 1,830 | 2,239 | +22% | 0 | 0 | — |
case-05 | fail→pass | 12,084 | 2,698 | -78% | 1 | 1 | 0% | 2,031 | 2,131 | +5% | 0 | 0 | — |
case-06 | fail→pass | 10,632 | 3,113 | -71% | 1 | 1 | 0% | 1,863 | 2,148 | +15% | 0 | 0 | — |
case-07 | fail→pass | 8,020 | 2,954 | -63% | 1 | 1 | 0% | 1,297 | 2,169 | +67% | 0 | 0 | — |
case-08 | fail→pass | 6,301 | 3,306 | -48% | 1 | 1 | 0% | 1,044 | 2,233 | +114% | 0 | 0 | — |
case-09 | pass→pass | 5,058 | 1,637 | -68% | 1 | 1 | 0% | 822 | 1,829 | +123% | 0 | 0 | — |
case-19 | fail→pass | 6,378 | 14,926 | +134% | 1 | 1 | 0% | 971 | 1,837 | +89% | 0 | 0 | — |
case-10 | pass→pass | 7,113 | 1,915 | -73% | 1 | 1 | 0% | 1,277 | 1,838 | +44% | 0 | 0 | — |
case-11 | fail→pass | 8,367 | 2,627 | -69% | 1 | 1 | 0% | 1,507 | 2,040 | +35% | 0 | 0 | — |
case-12 | fail→pass | 11,095 | 1,983 | -82% | 1 | 1 | 0% | 2,169 | 1,809 | -17% | 0 | 0 | — |
case-13 | fail→pass | 10,986 | 2,106 | -81% | 1 | 1 | 0% | 1,974 | 1,900 | -4% | 0 | 0 | — |
case-20 | pass→pass | 43,651 | 10,671 | -76% | 1 | 1 | 0% | 2,141 | 3,425 | +60% | 0 | 0 | — |
case-14 | fail→pass | 8,723 | 2,199 | -75% | 1 | 1 | 0% | 1,605 | 1,912 | +19% | 0 | 0 | — |
case-15 | fail→pass | 7,608 | 1,765 | -77% | 1 | 1 | 0% | 1,334 | 1,853 | +39% | 0 | 0 | — |
case-16 | fail→pass | 7,532 | 1,890 | -75% | 1 | 1 | 0% | 1,334 | 1,842 | +38% | 0 | 0 | — |
case-17 | fail→fail | 6,461 | 1,655 | -74% | 1 | 1 | 0% | 1,097 | 1,790 | +63% | 0 | 0 | — |
case-18 | fail→pass | 16,036 | 1,695 | -89% | 1 | 1 | 0% | 1,189 | 1,801 | +51% | 0 | 0 | — |
case-21 | pass→pass | 13,497 | 9,814 | -27% | 1 | 1 | 0% | 2,317 | 3,396 | +47% | 0 | 0 | — |
case-22 | pass→pass | 9,945 | 7,512 | -24% | 1 | 1 | 0% | 1,674 | 2,761 | +65% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +73 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/3/2026 | +55% |
Other measured skills in the registry, with their headline benchmark lift.