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.

インストールへ移動

リポジトリ: Wolverine971/buildos-platform
ソースの最終更新活動: 2026年6月11日 14:35
検出された SKILL.md の言語: 英語
スター: 2
フォーク: 0

インストール方法

デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。

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

コマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。

ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。

ソースファイルを確認

インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。

SKILL.md

ソースの指示 · 読み取り専用プレビュー

検索に戻るインストールに戻る

supabase

Query and manage the BuildOS Supabase database. Use for debugging data issues, checking users, LLM usage, queue jobs, schema questions, or admin database operations with safety checks.

2026-08-28

animate-expo

Build animations in React Native and Expo, making the decisions in the order that determines whether they feel right — should it animate, which thread it runs on, which properties, spring or timing, how the gesture hands off, how it degrades. Writes the implementation with Reanimated, Gesture Handler, Expo Router and expo-haptics. Use when animating anything in an Expo app, adding gestures, sheets, screen transitions, press feedback or haptics, or fixing motion that stutters on device. For web animation use `animate`.

2026-08-27

animate

Build an animation from scratch, making the decisions in the order that determines whether it feels right — should it animate at all, what purpose, which tool, which properties, which curve and duration, how it interrupts, how it exits. Writes the implementation. Use when asked to animate something, add motion, make a component feel alive, or build a transition. For critiquing existing motion use review-animations; for auditing a whole codebase use improve-animations.

2026-08-27

このリポジトリのすべてを見る

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.