- Home
- Skills
- Data & Databases
- Lead Scorer: Rank and Export Hot Leads
Works with the AI Agents you already use
Lead Scorer: Rank and Export Hot Leads
Score, dedupe and rank sales leads 1 to 10 (hot, warm, cold) and export a ranked CSV.
Free
Lead Scorer: Rank and Export Hot Leads
Example session with this skill installed
I have a CSV with 8 new leads. Normalize the list, score them, and tell me who the hot prospects are.
- Read your context and instructions
- Compiled the lead scorer
- Generated the data export
I processed 8 leads. After normalization, 1 duplicate and 1 invalid email were removed, and 6 valid leads were scored (3 hot).
Lead Scoring Results
| Name | Company | Score | Category | Reasoning | |
|---|---|---|---|---|---|
| Elena Park | elena.park@globex.com | Globex | 9 | hot | Corporate email at an established company. |
| Ana Souza | ana.souza@acmelogistics.com | Acme Logistics | 8 | hot | Corporate email matches the company name; B2B sector fits. |
| Carla Dias | carla.dias@northwind.io | Northwind | 8 | hot | Corporate domain matches the company name. |
| Felipe Alves | felipe@lojadoalves.com.br | Loja do Alves | 6 | warm | Corporate domain matches, but small retail business. |
| Diego Rocha | diego@yahoo.com | Rocha Consultoria | 4 | warm | Company given, but free email address. |
| Bruno Lima | bruno@gmail.com | 2 | cold | Free email and no company provided. |
The full ranked list was saved to leads_scored.csv.
Next steps
- Follow up with the 3 hot leads first.
- Ask for a company name from Bruno Lima before outreach.
leads_scored.csv
CSV · data export
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Manual lead qualification is a bottleneck that delays sales response times. This skill cleans a raw list of leads, scores each one from 1 to 10 with a transparent rubric, and returns a ranked CSV so you know who to contact first.
What it does
- Data normalization removes duplicate entries, drops invalid emails, and extracts company domains.
- Lead scoring assigns a 1 to 10 value based on a documented rubric, with a one-sentence reason for each score.
- Pipeline categorization labels leads as hot (7-10), warm (4-6) or cold (1-3).
- CSV export saves a deduplicated list ranked from the highest score to the lowest.
How it works
- Input. Provide a list of leads (name, email, company) in CSV or JSON.
- Normalization. A script removes duplicates and invalid emails.
- Scoring. Your agent applies the rubric to every lead and writes a short reason for each score.
- Export. The results are saved as a ranked CSV, and your agent shows you the top leads first.
Frameworks & tools
Python 3 (standard library only). The script works only with local files. Nothing is uploaded or sent anywhere.
Why use it instead of a plain prompt
A fixed rubric makes scores consistent from one run to the next, and a script handles duplicates and the CSV so your agent does not do it by hand. The skill is also instructed not to invent facts about companies.
Use cases
- List cleanup. Batch process new leads from a website form or an email list.
- Outreach prioritization. Find which prospects from a large event list deserve a first follow-up.
- Event follow-up. Rank the contacts you collected at a conference.
Known limitations
Scores for leads with no company or with a free email address are low by default. The rubric is a general default, so tell your agent your ideal customer profile for better results.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Data & Databases.
Low scores for leads with missing company data. Requires SUPABASE_URL, SUPABASE_KEY, or HUBSPOT_TOKEN environment variables for optional integrations.
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
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 5 days ago
- Free with an Agensi account
- Software
Python 3
- Optional
- Supabase project (own keys)HubSpot private app token
HubSpot and Supabase are optional. The core scoring and CSV export need no accounts.
Permissions
Needs Python 3. Works with any agent that can run Python scripts.