Champion Tracker
Track product champions for job changes and qualify their new companies against ICP. Takes a CSV of known champions (with LinkedIn URLs), creates a baseline snapshot via Apify enrichment, then detects when champions move to new companies. Scores new companies on a 0-4 ICP fit scale. Outputs a downloadable CSV of movers with qualification verdicts.
by Athina AInpx gooseworks install --all # then, in Claude Code, Cursor, or Codex: /gooseworks use the champion-tracker skill
Champion Tracker
Detect when product champions change jobs and qualify their new companies against ICP.
When to Use
- You have a list of known product users/champions (from reviews, LinkedIn posts, CRM exports)
- You want to detect when they change companies (high-intent re-sell signal)
- You want each job change scored against ICP before reaching out
Two Phases
Phase A: Discover Champions (agent-driven, one-time)
Build the initial champion list from public sources. This is done by the agent, not the script.
- Scrape reviews — Use
review-site-scraperskill to pull G2/Trustpilot reviews. Extract reviewer names + companies. - Search LinkedIn posts — Use the
linkedin-post-researchskill (Apify-based) to find people who posted about the product. - Resolve LinkedIn URLs — Use Fiber
/v1/kitchen-sink/person(name + company → profile URL) or ContactOut via Orthogonal. - Compile CSV — Merge all sources into
champions.csvwith required columns.
Phase B: Track Job Changes (script-driven, repeatable)
Use champion_tracker.py for ongoing tracking.
Script Usage
Prerequisites
APIFY_API_TOKENin.env(for LinkedIn profile enrichment)- Champion CSV with columns:
name,linkedin_url(required);original_company,original_title,email,source,notes(optional)
Commands
Initialize baseline (first run):
# Dry run — see cost estimate
python3 skills/champion-tracker/scripts/champion_tracker.py init -i champions.csv --dry-run
# Create baseline
python3 skills/champion-tracker/scripts/champion_tracker.py init -i champions.csvCheck for job changes (subsequent runs):
# Dry run
python3 skills/champion-tracker/scripts/champion_tracker.py check --dry-run
# Detect changes and output CSV
python3 skills/champion-tracker/scripts/champion_tracker.py check -o changes.csvView status:
python3 skills/champion-tracker/scripts/champion_tracker.py statusOutput CSV Columns
| Column | Description |
|---|---|
| champion_name | Full name |
| linkedin_url | LinkedIn profile URL |
| previous_company | Company at baseline |
| previous_title | Title at baseline |
| new_company | Current company (changed) |
| new_title | Current title |
| change_detected_date | Date this check was run |
| position_start_date | When they started the new role |
| days_since_change | Days since new position started |
| icp_score | 0-4 ICP qualification score |
| icp_verdict | Strong Fit / Good Fit / Possible Fit / Weak Fit |
| icp_notes | Scoring breakdown |
| Email if available | |
| notes | Original notes from champion CSV |
ICP Scoring (0-4)
| Signal | Points | What it checks |
|---|---|---|
| B2B signal | 1.0 | Title contains sales/SDR/revenue/growth keywords |
| Outbound motion | 1.0 | Sales leadership title (VP Sales, Head of Growth, etc.) |
| Company size | 1.0 / 0.5 | SMB/mid-market = 1.0; unknown = 0.5 benefit-of-doubt |
| Seniority | 1.0 | VP, Director, Head of, C-level, Founder |
Verdicts: Strong Fit (>=3) / Good Fit (>=2) / Possible Fit (>=1.5) / Weak Fit (<1.5)
Cost
- ~$3 per 1,000 LinkedIn profiles enriched
- 50-80 champions ≈ $0.15-0.25 per run
--dry-runalways shows cost before any API calls
File Structure
skills/champion-tracker/
SKILL.md # This file
scripts/
champion_tracker.py # Main CLI script
input/
champions_template.csv # Template for manual additions
snapshots/ # Created at runtime
baseline.json # Latest full snapshot
archive/ # Timestamped copies
output/ # Created at runtime
changes-YYYY-MM-DD.csv # Generated outputDependencies
- Reuses
LinkedInEnricherfromskills/lead-qualification/scripts/enrich_leads.py - Falls back to inline implementation if import fails
- Requires:
requests(Python package),APIFY_API_TOKEN(env var)
What's included
APIFY_API_TOKEN in .env (for LinkedIn profile enrichment)name, linkedin_url (required); original_company, original_title, email, source, notes (optional)Render Model Comparison Grid
Render a 'model comparison grid' video from a config — a fal-style "same prompt, N contenders" showcase — a dark real-DOM stage where per beat a monospace prompt fades in centered, docks to a small top strip, then a labeled 2-4 panel grid (static images OR muted video clips, mixable per cell) staggers in and holds for comparison, plus a minimal end card — frame-stepped via Playwright (video cells are frame-seeked deterministically) and encoded with FFmpeg. Deterministic assembly, FREE (cell media comes from create-image-fal / create-video-fal, music from create-music-elevenlabs), text stays pixel-crisp. Use for the model-comparison-grid format.
Render Offer Ad
Render a punchy ~12s vertical (9:16) music-only direct-response OFFER ad as a 4-beat kinetic-typography film — HEADLINE slam → real PRODUCT drop → CLAIM/proof → CTA pill — from one config of copy slots, a real product photo, a brand palette, fonts, bpm, and beat split. DETERMINISTIC + FREE (a bundled Remotion project; springs + interpolate, no AI-gen for visuals). Backgrounds are engine gradient divs off the palette, props are inline SVG, the ONLY composited bitmap is the REAL product photo (objectFit:contain, never stretched), and ALL headline/claim/CTA/URL/wordmark text is typeset in the engine — never AI-rendered (the format's credibility guard). A driver binds the config to Remotion input props, renders the 9:16 master, and derives a 1:1 center-crop with ffmpeg. Two gating checks run before render (claim verbs must match the product's physical format; the claim beat needs an edge-entry mechanism prop). Use for the motion-graphics-offer-ad format.
Render Myth Vs Fact
Assemble a myth-vs-fact kinetic-typography explainer video ad (≈29.5s, 9:16) from N myth/fact pairs + hook / turn / punch copy + palette + a brand end-card PNG + a VO track — a hook, 3 red-strike MYTH cards that flip to teal-check FACT cards (per-line strikethrough that crosses EVERY wrapped line), a "what actually works" turn, an optional proof reveal, a punch line, and a static end card. DETERMINISTIC assembly with ZERO AI-gen visuals — HTML hyperframes rendered frame-exact via Playwright (`window.renderAt(t)`, animation a pure function of beat-local time), Whisper beat-snap to VO word onsets, concat at a uniform fps, karaoke `.ass` captions burned last (suppressed on the proof + end-card beats), and a VO + optional music mix (music −20 dB, `amix normalize=0`, tail fade). FREE (Python + Playwright + ffmpeg); the recipe supplies the copy / palette / end-card / VO and gates the paid VO / music / Whisper calls to their own capabilities. Use for the myth-vs-fact format.