agentsclimarketplace

Lead scorer

Skill 0xjitsu/jitsu-skills/skills/lead-scorer

Persona-based AI skill ecosystem — 7 personas, 14 orchestration skills for outbound campaigns, publishing, security, macOS automation, and full-stack dev. Works with Claude Code, Claude Chat, and Agent SDK. AGPL v3 + commercial license.

Install
npx -y skills add 0xjitsu/jitsu-skills --skill lead-scorer

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

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.

The file declares its own license as AGPL-3.0-or-later. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

6.2 KB, as published. Nobody here has run it

Lead Scorer

Weighted lead scoring engine from Clay enrichment data.

When to Trigger

Activate this skill when the user:

  • Asks to score leads, rank prospects, or prioritize a contact list
  • Wants to know which contacts to reach out to first
  • Needs a quality filter before running a campaign sequence
  • Says "score", "prioritize", "rank", "qualify", or "tier"

Scoring Dimensions

Each dimension produces a score from 0 to 100. The final score is a weighted sum.

1. Company Fit (Weight: 30%)

Evaluate how well the prospect's company matches the ideal customer profile.

SignalScoreHow to Assess
Industry match0-30Exact match = 30, adjacent = 15, unrelated = 0
Company size0-25Sweet spot (50-500) = 25, too small/large = 10
Funding stage0-25Series A-B = 25, Seed = 20, Series C+ = 15, Unknown = 5
Revenue signals0-20Growing = 20, Stable = 10, Declining = 0

Data source: Clay find-and-enrich-company and ask-question-about-accounts.

2. Title Seniority (Weight: 25%)

Map the contact's role to a seniority score.

LevelScoreExample Titles
C-Level100CEO, CTO, CFO, CPO
VP80VP Engineering, VP Product, VP Sales
Director60Director of Engineering, Head of DevRel
Manager40Engineering Manager, Product Manager
IC (Senior)20Senior Engineer, Staff Engineer, Lead Dev
IC (Junior)10Software Engineer, Developer, Analyst
Unknown5Title not found or ambiguous

Data source: Clay find-and-enrich-contacts-at-company.

3. Tech Stack Overlap (Weight: 20%)

Compare the prospect's tech stack against the user's target stack.

Overlap LevelScoreDefinition
High overlap (3+)1003 or more shared technologies
Medium overlap (1-2)601-2 shared technologies
Adjacent stack30Different but compatible ecosystem
No overlap0Completely 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.

4. Social Presence (Weight: 15%)

Measure the contact's public visibility and influence.

SignalScoreThreshold
GitHub stars (repos)0-301000+ = 30, 100+ = 20, 10+ = 10, <10 = 0
Twitter/X followers0-3010k+ = 30, 1k+ = 20, 100+ = 10, <100 = 0
Newsletter subscribers0-205k+ = 20, 1k+ = 10, <1k = 5
Conference speaker0-20Recent (12mo) = 20, Ever = 10, Never = 0

Data source: Clay enrichment and ask-question-about-accounts.

5. Engagement Signals (Weight: 10%)

Track prior interactions with your brand or content.

SignalScoreDetection Method
Replied to previous email40gmail_search_messages for prior threads
Opened previous email20Tracking pixel data if available
Attended your event20Check Supabase event attendees table
Visited your site10PostHog or analytics data if available
No prior engagement0Default

Score Calculation

final_score = (company_fit * 0.30)
            + (title_seniority * 0.25)
            + (tech_overlap * 0.20)
            + (social_presence * 0.15)
            + (engagement * 0.10)

Tier Classification

TierScore RangeAction
Hot80-100Priority outreach, L3 personalization, Day 0 send
Warm50-79Standard sequence, L2 personalization
Cold20-49Low priority, L1 personalization, batch later
Skip0-19Do not contact, remove from campaign

Output Format

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.

Integration with Campaign Sequencer

When called from campaign-sequencer:

  1. Accept a list of enriched contacts (post Clay enrichment)
  2. Score each contact using the dimensions above
  3. Return the score, tier, and top signal for each contact
  4. The campaign sequencer uses tier to determine personalization depth and send priority

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.