Agent Skill

B2B Lead Qualification

Score and classify B2B prospects against a defined ideal customer profile, with reasoning and a recommended next action.

Version 1.0 Updated June 2026 SKILL.md MIT 6 min read
View skill source Browse all skills

Overview

What this skill does

Qualifying a list of B2B prospects by hand is slow and inconsistent. Different reviewers weigh company size, industry, and intent differently, and one-off prompting produces a different rationale every time you run it.

This skill structures the task. It reads your ideal customer profile, extracts positive and disqualifying criteria, and evaluates every prospect against the same framework so the scores are comparable across a whole list. You receive a fit score, fit level, the reasoning, the supporting evidence, any missing information, and a recommended next action.

When to use it

Best used for

  • Qualifying exported prospect lists before outreach
  • Prioritizing accounts when you have more leads than capacity
  • Separating high-fit and low-fit companies
  • Documenting why a prospect matches an ICP

Know the limits

When not to use this skill

  • You have no defined ICP or qualification criteria yet
  • You need verified contact details rather than fit scoring
  • The dataset has no company or firmographic fields to score against

Inputs

Provide these when prompted. The skill asks for anything missing before it runs.

Required

  • An ICP definition
  • A prospect or company dataset
  • Qualification criteria

Optional

  • Exclusion criteria
  • Weighted scoring rules
  • Target locations
  • Company size range
  • Required technologies or industries

Outputs

One record per prospect with a consistent, inspectable schema.

  • fit_score

    A 0–100 score for how well the prospect matches the ICP.

  • fit_level

    A coarse band (high / medium / low) derived from the score.

  • qualification_reason

    Why the prospect scored the way it did.

  • supporting_evidence

    The data points the score relied on.

  • missing_information

    Fields that materially affect the score but were absent.

  • recommended_next_action

    The suggested follow-up for this prospect.

Example

Example

A single prospect scored against a sample ICP.

Input

ICP: Mid-market B2B SaaS, 50–500 employees, North America.

Prospect:
- Company: Lumen Robotics
- Industry: Industrial automation SaaS
- Employees: 180
- HQ: Austin, TX

Output

company_name: Lumen Robotics
fit_score: 86
fit_level: high
qualification_reason: B2B SaaS in target size band and region.
supporting_evidence: 180 employees; HQ in Austin, TX; SaaS industry.
missing_information: Decision-maker contact; current tech stack.
recommended_next_action: Enrich with a decision-maker contact, then add to outreach.

An 86 puts Lumen Robotics in the high-fit band: it matches industry, size, and region. The missing_information field flags that you still need a decision-maker contact before reaching out.

Setup

How to use the skill

General steps first, then notes for specific clients where verified.

  1. 1Download the file using the button below, or copy the Markdown.
  2. 2Place it in a directory named after the skill (e.g. skill-name/).
  3. 3Make sure the filename stays exactly SKILL.md.
  4. 4Add any references or assets included with the package.
  5. 5Load the skill into a compatible agent and provide the required inputs.
Claude Code
  1. 1Create a folder for the skill and save SKILL.md inside it.
  2. 2Place the folder where your project's skills are discovered.
  3. 3Reference the skill when you want it applied to your data.
Other compatible clients
  1. 1Confirm the client supports the open Agent Skills format.
  2. 2Load the SKILL.md file as instructed by that client.
  3. 3If skills are not auto-loaded, paste the Markdown as instructions.

Source

Full SKILL.md source

Read the rendered skill or copy the complete Markdown. The download is generated from this exact source.

Version 1.0 SKILL.md ~2 KB MIT
View on GitHub

B2B Lead Qualification

Purpose

Score and classify B2B prospects against a defined ideal customer profile, with reasoning and a recommended next action.

When to use this skill

  • Qualifying exported prospect lists before outreach
  • Prioritizing accounts when you have more leads than capacity
  • Separating high-fit and low-fit companies
  • Documenting why a prospect matches an ICP

When not to use this skill

  • You have no defined ICP or qualification criteria yet
  • You need verified contact details rather than fit scoring
  • The dataset has no company or firmographic fields to score against

Required inputs

  • An ICP definition
  • A prospect or company dataset
  • Qualification criteria

Optional inputs

  • Exclusion criteria
  • Weighted scoring rules
  • Target locations
  • Company size range
  • Required technologies or industries

Rules

  1. Use only information present in the supplied dataset or explicitly provided by the user.
  2. Do not invent missing company, contact, revenue, employee, technology, or location information.
  3. Clearly distinguish known facts from assumptions.
  4. Flag missing information that materially affects the score.
  5. Apply the same scoring framework consistently to every prospect.

Process

  1. Parse the ideal customer profile.
  2. Extract positive qualification criteria.
  3. Extract disqualifying criteria.
  4. Evaluate each prospect against both sets.
  5. Assign a score from 0 to 100.
  6. Explain the score using available evidence.
  7. Recommend the next action.

Output format

Return one record per prospect with the following fields:

  • fit_score
  • fit_level
  • qualification_reason
  • supporting_evidence
  • missing_information
  • recommendednextaction

Validation

  • Confirm every score is supported by evidence from the input.
  • Confirm missing fields are listed rather than guessed.
  • Confirm the same criteria were applied to every record.

Limitations

  • Scores reflect fit, not intent or buying readiness.
  • A high score is not a guarantee of a sale; verify before investing heavily.

Before you rely on it

Safety and limitations

  • Scores reflect fit, not intent or buying readiness.
  • A high score is not a guarantee of a sale; verify before investing heavily.
  • Review the output before acting on it.
  • Do not upload confidential datasets to an external model without authorization.
  • Outputs depend on the model and the source data and are not guaranteed to be accurate.

History

Changelog

  1. v1.0June 2026
    • Initial release.

Questions

Agent Skill FAQ

What does it do when a prospect is missing key data?
It scores on the evidence available, flags the missing fields, and lowers confidence rather than guessing — so you can enrich and re-run instead of trusting an invented score.
Can I change the scoring framework?
Yes. Edit the Rules and Process sections to weight criteria differently or add your own scoring bands.
Do I need ProfileSpider to use this skill?
No. The skill works on any compatible data. ProfileSpider is one convenient way to produce that structured input.
Does running this skill send data to ProfileSpider?
No. Downloading or copying the file does not send any data to ProfileSpider. What happens afterward depends on the AI service you load it into.
Are Agent Skills the same as prompts?
No. A skill is a structured, reusable package — task, inputs, rules, process, and output format — so the workflow runs consistently and can be shared, versioned, and edited.

Ready to Extract Structured Leads?

Start free and see how quickly you can build a clean lead list.

Install from Chrome Store

Get started for free