- Home
- Skills
- Sales & Lead Gen
- AI Outreach Assistant: Lead Scoring
Works with the AI Agents you already use
AI Outreach Assistant: Lead Scoring
Score B2B sales leads 1-10 and draft short, personalized cold email or LinkedIn messages for the ones worth contacting, with an audit trace for every decision.
$9
AI Outreach Assistant: Lead Scoring
Example session with this skill installed
Score these leads and draft LinkedIn outreach for the good ones. We sell an AI developer-vetting platform for engineering teams.
name,company,role,industry,linkedin_about,pain_point
Rahul Mehta,Acme Tech,CTO,SaaS,Building cloud-native SaaS products,Scaling engineering teams efficiently
Ananya Singh,FinEdge,Head of Engineering,FinTech,Leading fintech platform development,Hiring vetted developers quickly
Priya Nair,BrightMart,Store Operations Manager,Retail,Runs day-to-day operations for 3 stores,Reducing staff turnover
- Read your context and instructions
- Compiled the ai outreach assistant
- Generated the data export
Summary
Scored 3 leads against a threshold of 7. 2 qualified for outreach, 1 skipped. Results saved to output_messages.csv.
| Name | Company | Score | Priority | Outreach |
|---|---|---|---|---|
| Ananya Singh | FinEdge | 8 | High | Drafted |
| Rahul Mehta | Acme Tech | 8 | High | Drafted |
| Priya Nair | BrightMart | 3 | Low | Skipped |
Decision traces
Ananya Singh: Score 8/10 (High) because engineering leader at a FinTech with an urgent hiring pain that developer vetting directly addresses. Outreach generated.
Rahul Mehta: Score 8/10 (High) because a CTO scaling a SaaS engineering team has buying authority and a direct need. Outreach generated.
Priya Nair: Score 3/10 (Low) because retail store operations has little need for developer hiring. Skipped because score below threshold (7).
Messages
Ananya Singh
Hi Ananya, leading platform development at FinEdge must mean hiring is rarely off your plate, and in FinTech every new engineer has to clear a high bar for security and reliability. Many engineering heads we speak with lose weeks screening candidates who look strong on paper but stall in technical rounds. We help teams like yours shortlist pre-vetted developers in days, so your senior engineers spend time building rather than interviewing. Would a short call next week to compare notes on your current hiring process be useful?
Rahul Mehta
Hi Rahul, building cloud-native products at Acme Tech while scaling the team behind them is a hard balance, especially when every hire needs to be productive in a modern SaaS stack from week one. Many CTOs we talk to find that interviewing quietly eats their best engineers' time. We help SaaS teams add pre-vetted developers quickly, so growth does not slow delivery. Would you be open to a quick chat about how you are approaching hiring this quarter?
Next steps
- Review and personalize the two drafts before sending.
- Lower the threshold (for example to 6) if you want messages for borderline leads.
output_messages.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
Hand your agent a list of B2B leads and get back a ranked list plus ready-to-send outreach for the ones worth your time.
What it does
- Scores every lead 1-10 on seniority and buying authority, how well their pain point fits what you sell, industry and company fit, and likely benefit.
- Skips weak leads below a threshold (7 by default, you can change it), so you never waste a message.
- Drafts one personalized message per qualified lead: one paragraph, under 120 words, at least two real details about the prospect, and a soft question as the call to action. No hype, no emojis, no invented facts.
- Explains every decision with a one-line trace, such as "Score 8/10 (High) because... Outreach generated."
- Saves
output_messages.csvwith your original columns plus score, priority, reason, trace and message.
Input
A CSV or pasted table with name, company, role, industry, linkedin_about, pain_point. Missing details? The agent asks you, or, if you approve the per-call price, fills them in with Agensi lead-data tools.
Why it works
The rubric and message rules come from a working open-source lead-scoring pipeline. In this skill they run inside your agent, so there is no local model, API key or setup.
Good for
Founders doing their own outbound, SDRs clearing a lead list before a sequence, and agencies prepping prospect lists for clients.
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.
Requires structured input with name and company. Does not support subject lines or multi-paragraph emails. Paid enrichment requires user confirmation of costs.
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 3 days ago
Requires
Nothing to install.
Permissions
Read Files: reads the leads CSV the user points to. Write Files: saves output_messages.csv with scores, traces and drafted messages. No network access unless the user approves optional Agensi lead-data tools.