apollo-prospect
Full ICP-to-leads pipeline. Describe your ideal customer in plain English and get a ranked table of enriched decision-maker leads with emails and phone numbers.
- License 许可
- MIT
- 最近更新
- 2026-11-07
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- apollo-prospect
- description
- Full ICP-to-leads pipeline. Describe your ideal customer in plain English and get a ranked table of enriched decision-maker leads with emails and phone numbers.
- argument-hint
- [describe your ideal customer]
- user-invocable
- true
03 SKILL.md 正文
<!-- Provenance: adapted from anthropics/knowledge-work-plugins (Apache-2.0, (c) Anthropic). Original skill: https://github.com/anthropics/knowledge-work-plugins/tree/main/partner-built/apollo/skills/prospect. Changes for Muse AI: Claude/Cowork product refs -> Muse AI; MCP -> connector; CLAUDE.md -> MUSE.md; ${CLAUDE_PLUGIN_ROOT} -> this skill's directory; /plugin:command refs -> skill refs. -->
Prospect
Go from an ICP description to a ranked, enriched lead list in one shot. The user describes their ideal customer via "$ARGUMENTS".
Examples
the "prospect" skill VP of Engineering at Series B+ SaaS companies in the US, 200-1000 employeesthe "prospect" skill heads of marketing at e-commerce companies in Europethe "prospect" skill CTOs at fintech startups, 50-500 employees, New Yorkthe "prospect" skill procurement managers at manufacturing companies with 1000+ employeesthe "prospect" skill SDR leaders at companies using Salesforce and Outreach
Step 1 — Parse the ICP
Extract structured filters from the natural language description in "$ARGUMENTS":
Company filters:
- Industry/vertical keywords →
q_organization_keyword_tags - Employee count ranges →
organization_num_employees_ranges - Company locations →
organization_locations - Specific domains →
q_organization_domains_list
Person filters:
- Job titles →
person_titles - Seniority levels →
person_seniorities - Person locations →
person_locations
If the ICP is vague, ask 1-2 clarifying questions before proceeding. At minimum, you need a title/role and an industry or company size.
Step 2 — Search for Companies
Use mcp__claude_ai_Apollo_MCP__apollo_mixed_companies_search with the company filters:
q_organization_keyword_tagsfor industry/verticalorganization_num_employees_rangesfor sizeorganization_locationsfor geography- Set
per_pageto 25
Step 3 — Enrich Top Companies
Use mcp__claude_ai_Apollo_MCP__apollo_organizations_bulk_enrich with the domains from the top 10 results. This reveals revenue, funding, headcount, and firmographic data to help rank companies.
Step 4 — Find Decision Makers
Use mcp__claude_ai_Apollo_MCP__apollo_mixed_people_api_search with:
person_titlesandperson_senioritiesfrom the ICPq_organization_domains_listscoped to the enriched company domainsper_pageset to 25
Step 5 — Enrich Top Leads
Credit warning: Tell the user exactly how many credits will be consumed before proceeding.
Use mcp__claude_ai_Apollo_MCP__apollo_people_bulk_match to enrich up to 10 leads per call with:
first_name,last_name,domainfor each personreveal_personal_emailsset totrue
If more than 10 leads, batch into multiple calls.
Step 6 — Present the Lead Table
Show results in a ranked table:
Leads matching: [ICP Summary]
| # | Name | Title | Company | Employees | Revenue | Phone | ICP Fit |
|---|
ICP Fit scoring:
- Strong — title, seniority, company size, and industry all match
- Good — 3 of 4 criteria match
- Partial — 2 of 4 criteria match
Summary: Found X leads across Y companies. Z credits consumed.
Step 7 — Offer Next Actions
Ask the user:
- Save all to Apollo — Bulk-create contacts via
mcp__claude_ai_Apollo_MCP__apollo_contacts_createwithrun_dedupe: truefor each lead - Load into a sequence — Ask which sequence and run the sequence-load flow for these contacts
- Deep-dive a company — Run
the "company-intel" skillon any company from the list - Refine the search — Adjust filters and re-run
- Export — Format leads as a CSV-style table for easy copy-paste
04 同仓库更多 Skills
web-scrape
Turn web pages into LLM-ready markdown via the Firecrawl API (renders JS, anti-bot handling). Use when browser_open/fetch fails on JS-heavy pages, or when you need clean markdown/structured extraction from a site. Requires FIRECRAWL_API_KEY.
design-taste-frontend
tasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curated gallery sites (One Page Love, Awwwards Sites of the Day). Deals researched directions (idea, composition, type, palette, photographs, section blueprints) from a library, enforces a strict no-slop house style with a real-browser inspector, and runs a look-and-fix loop on screenshots. Use this whenever you build, design, redesign, restyle, polish or review a landing page, marketing site, portfolio, product page, one-pager, hero or any public-facing web page, in any stack (HTML/CSS, React, Next.js, Vue, Svelte, Astro, Tailwind) — also when the user says a page looks generic, templated, "AI-made", sloppy, or asks to make it look designed, premium, award-level or less like every other site. Not for dashboards or app screens.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).