Lead scoring model builder
Build a data-driven lead scoring model from win/loss history — dimensions, thresholds, validation, batch scoring
- What
- Build a data-driven lead scoring model from win/loss history — dimensions, thresholds, validation, batch scoring
- Cost
- Free
- Needs
- historical win/loss data (50+ closed deals minimum, 200+ preferred); an ICP definition; a CRM export of current leads; the data must be accessible to the agent for analysis
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — a builder for data-driven lead scoring models calibrated on actual win/loss history, not generic best practices. Takes your ICP definition, historical closed deals and a CRM export, finds which attributes correlate with closed-won deals, then generates the scoring model: dimensions and point values traced to measured lift, Hot/Warm/Cool/Cold thresholds with conversion expectations, holdout validation (precision, recall, F1, AUC-ROC, confusion matrix), a CRM implementation guide, and a batch-scoring mode for current leads. Not a duplicate of coreyhaines31-revops — that listing is a general RevOps framework, while this one builds one concrete scoring model from YOUR data, with guardrails against intuition-only models (no win/loss data = set up tracking first, revisit in 90 days). By @onewave-ai, listed here with credit to its creator. Honest caveats: needs real historical win/loss data (50+ closed deals minimum, 200+ preferred) — without it the skill correctly refuses to build; works best with a clean CRM export, so expect data cleanup before analysis. Not verified. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Lead scoring model builder is a free Muse skill that builds a data-driven lead scoring model from your win/loss history, not generic best practices. It finds which attributes correlate with closed-won deals, then generates dimensions and point values, Hot/Warm/Cool/Cold thresholds, holdout validation, a CRM implementation guide, and batch scoring for current leads.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit fc5b785Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: historical win/loss data (50+ closed deals minimum, 200+ preferred); an ICP definition; a CRM export of current leads; the data must be accessible to the agent for analysis Install "Lead scoring model builder" for me. Give my agent the skill for building a data-driven lead scoring model from win/loss history — dimension construction, threshold calibration, holdout validation, and batch scoring Repository: https://raw.githubusercontent.com/onewave-ai/claude-skills/fc5b7851a6c7ba367e05797df46ad3679df355dd/lead-scoring-model/SKILL.md Pinned version: install the code at commit fc5b7851a6c7ba367e05797df46ad3679df355dd exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file for the onewave-ai-claude-skills-lead-scoring-model skill from the repository into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "onewave-ai-claude-skills-lead-scoring-model". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. gather the ICP definition, export win/loss data and the current lead list). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. Never ask me to paste secrets in chat — credentials go through the secure vault or environment variables. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- fc5b785 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.