agentleFS
sami2919sami2919/SignalForce/skills/champion-tracker/SKILL.md

champion-tracker

Skill9 starsChanged 3 months agoMITView on GitHub

Use when monitoring job changes of past customers, positive responders, or engaged prospects, or when a known contact moves to a new company and you need to evaluate the new opportunity

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When a job change is detected:

    line 32
  2. Distinctive:

    Do not add champions to cold sequences.

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Champion Tracker

Champion Definition

A champion is anyone who has shown genuine interest in your product:

  • Past customer or pilot participant
  • Replied positively to cold outreach (even "not now")
  • Attended a demo or discovery call
  • Engaged with content (open-source contributor, GitHub star, paper citation)

Champions carry context. When they move jobs, they bring that context with them — and arrive at a new company with fresh budget and mandate.

Champion List Setup

Maintain a dedicated "Champions" table in Clay with the following fields: Name, Current Title, Current Company, Current Domain, Original Signal, Last Interaction Date, Job Change Alert.

Three monitoring layers (run in parallel):

  1. Clay job change enrichment — enable "Job Change" column. Clay pings LinkedIn periodically and flags when company or title changes.
  2. Apollo People Alerts — go to Apollo → Lists → your champion list → enable "Job Change Alert". Sends email notification on change detection.
  3. LinkedIn Sales Navigator — add all champions to a saved lead list. Enable "Job change" alerts in the alert settings. Most reliable but requires Sales Nav license.

Review champion alerts weekly during pipeline review.

Job Change Workflow

When a job change is detected:

  1. Verify the change — confirm on LinkedIn directly. Check new company name, title, and start date.
  2. Evaluate the new company — run prospect-researcher skill on the new company. Score against ICP criteria from config/gtm-context.md.
  3. Route by ICP score:
    • ICP grade A or B: Enrich contact at new company (run contact-finder), then generate warm outreach within 48 hours. Flag in HubSpot as "Champion Re-engage".
    • ICP grade C or D: Log the move in HubSpot. Add a note with new company. Set a 90-day follow-up task — re-evaluate if their domain signals grow.
  4. Log everything in HubSpot — update contact record with new company, title, domain. Create a new deal if advancing to outreach.

Champion Outreach

Reference config/templates/email-sequences/champion-job-change.md for the full template.

Key principles for champion outreach:

  • Lead with the relationship, not the pitch. "Congrats on the move" is the opener, not "we help companies like X".
  • Reference shared history — name the specific interaction ("when we spoke about your setup at [OldCo]").
  • Be brief — 3–4 sentences max. They know who you are. No need to re-explain the product.
  • Single CTA — ask for a 15-minute catch-up, not a demo. Lower barrier.
  • Send within 48 hours of confirming the move. After 2 weeks, the "congrats on the new role" opener loses credibility.

Do not add champions to cold sequences. Always send individually from a primary inbox, not a sending domain.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.