lead-list-research-with-claude-code

Build and refine B2B lead lists with an AI agent in the loop. Use when sourcing accounts, defining an ICP, scoring prospect fit, finding personas, enriching contacts, or turning a messy market into a qualified outbound list.

Jump to install

Repository: Wolverine971/buildos-platform
Last source activity: June 11, 2026 at 14:35
Detected SKILL.md language: English
Stars: 2
Forks: 0

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/Wolverine971/buildos-platform --skill lead-list-research-with-claude-code

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

SKILL.md

Source instructions · Read-only preview

Back to search Back to installation

Lead List Research With Claude Code

Use this skill to help an agent build a qualified lead list through iterative research, scoring, exclusions, and contact sourcing. The goal is not to automate judgment away. The goal is to coordinate research agents, tools, and human review until the list reflects a real market opinion.

When to Use

Build an account list from a target market or lookalike customer

Turn closed-won customers into an ICP search pattern

Score companies for fit and explain why they qualify

Find buyer personas or titles for qualified accounts

Debug noisy lists with agencies, resellers, enterprise accounts, or wrong-fit categories

Create a repeatable outbound campaign source list

Do not use this skill when the user only needs a simple contact lookup, a generic scraping job, or a list with no qualification criteria.

Inputs

Offer or product being sold

Target market hypothesis

Closed-won examples or ideal customer URLs if available

Firmographic limits such as geography, employee count, stage, industry, or budget

Exclusion patterns from prior bad lists

Contact persona assumptions

Source tools available, such as search, CRM export, enrichment CLI, or spreadsheet

Core Workflow

Start from the market thesis. Restate what the user believes is true about the target market and why those accounts may buy.

Find candidate accounts. Use lookalikes, category search, domain search, directories, maps, or CRM patterns. Keep the first pull broad enough to expose noise.

Inspect the first batch. Classify strong fit, marginal fit, and bad fit. Report the failure patterns, not just the final rows.

Anneal the ICP. Tighten inclusion and exclusion rules one variable at a time: employee count, category, business model, product type, geography, funding, website language, or technical signals.

Create a scoring prompt. Score each account from 1 to 10 with fit reasoning. Define the threshold for qualified accounts before scaling.

Spot-check before scaling. Test the scoring prompt on a small sample. Ask the user to confirm borderline judgments.

Source contacts by persona tier. Identify likely titles by inspecting real companies. Use role tiers instead of seniority alone.

Make enrichments durable. Save progress as rows are found so partial failures do not erase the run.

Review the finished list. Summarize total accounts, qualified accounts, contacts found, reasons for qualification, and remaining noise risks.