champion-move-outreach
End-to-end champion/buyer/user job change signal composite. Takes a set of known people (past buyers, champions, power users), detects when they move to a new company, researches the new company for ICP fit, and drafts personalized outreach leveraging the existing relationship. Tool-agnostic — works with any people source, detection method, and outreach platform.
npx skills add gooseworks-ai/goose-skills --skill champion-move-outreach --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Tracks known buyers, champions, and power users for job changes. When someone who already knows your product moves to a new company, that signal is used to research the new company for ICP fit and draft personalized outreach that leverages the existing relationship.
How it works
- Step 0: Configuration (One-Time Setup): Collect preferences on people_source, tracked_categories, ICP fields, signal detection config, outreach tool, and your_company context. Store in a JSON config path.
- Step 1: Detect Job Changes: For each tracked person, use the configured detection_tool to verify if they moved from last_known_company. Output movers with new_company, new_title, start_date, and other move details; also record no_change and unable_to_verify cases. Human checkpoint summarizes tracked/moved/unchanged and prompts for proceeding with research.
- Step 2: Research New Company & Qualify Against ICP: For each mover, perform web research to describe the company and assess ICP fit against target_industries, target_company_size, target_geographies, disqualifiers, and minimum_deal_size. Assess authority, department fit, influence trajectory, and seniority. Determine outreach approach based on old category and new title. Output qualified_movers with comprehensive nested data: person, move, new_company_research, qualification, priority_tier, and disqualified_movers for those failing criteria. Tier definitions dictate urgency.
- Step 3: Find New Contact Details: For qualified movers, use contact_tool to locate new work emails or fall back to LinkedIn. Output contactable_movers with new_email and confidence, or email_not_found with LinkedIn fallback. Human checkpoint summarizes emails vs LinkedIn-only contacts.
- Step 4: Draft Personalized Outreach: Draft outreach that leverages the existing relationship rather than cold messaging (details beyond this excerpt are not provided in the supplied content). The process is designed to tailor messages to the mover’s new role and company context.
When to use it
Use when you have a set of known relationships (past buyers, champions, power users) and you want to monitor for job changes, then qualify those changes against ICP and prepare personalized outreach. It supports multiple tools for detection and outreach and is described as tool-agnostic.
What it can touch
- Detection tools: LinkedIn profile monitoring, Apollo job change data, Web search (tool-agnostic).
- Research and qualification: web search access, ICP fields, company data, and outreach planning data structures.
- Contact discovery: contact_tool (Apollo, Clearbit Prospector, Web search, LinkedIn).
Caveats
- Requires configuration data to function (input sources, ICP criteria, and outreach settings).
- Outcomes depend on successful data gathering from detection and contact tools; there are explicit output structures and human checkpoints to approve before drafting outreach.
- The workflow references several explicit data schemas (e.g., movers, qualified_movers) and requires consistent data formats as described in the steps.
# Champion Move Outreach Tracks known buyers, champions, and power users for job changes. When someone who already knows your product moves to a new company, that's the highest-conversion outbound signal in B2B — they already trust you, they're in a new role trying to make an impact, and they have firsthand experience with what your product delivers. **Why this is the #1 signal:** Every other signal (funding, hiring, leadership change) targets strangers. This targets people who already know, like, and trust your product. Conversion rates on champion-move outreach are 3-5x higher than cold outreach because: - They don't need to be educated on what you do - They have a positive experience to anchor on - They want quick wins at the new company (bringing in a tool they trust IS a quick win) - They can internally champion the deal because they have firsthand results to cite ## When to Auto-Load Load this composite when: - User says "track my champions", "check for job changes", "who moved from our customer accounts", "champion tracking" - User has a list of past buyers/users and wants to know if anyone changed jobs - An upstream workflow (TAM Pulse) triggers a champion change check ---
- When to Auto-Load
- Step 0: Configuration (One-Time Setup)
- People to Track
- ICP Definition (for qualifying the new company)
- Signal Detection Config
- Outreach Config
- Your Company Context
- Step 1: Detect Job Changes
- Input Contract
- Process
- Output Contract
- Human Checkpoint
- Step 2: Research New Company & Qualify Against ICP
- Tier Assignment
What does the champion-move-outreach skill do?
End-to-end champion/buyer/user job change signal composite. Takes a set of known people (past buyers, champions, power users), detects when they move to a new company, researches the new company for ICP fit, and drafts personalized outreach leveraging the existing relationship. Tool-agnostic — works with any people source, detection method, and outreach platform.
How do I install it?
Run `npx skills add gooseworks-ai/goose-skills --skill champion-move-outreach --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From gooseworks-ai/goose-skills, a repository with 1,091 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.
