create-image-fal
Generate or edit an image via any FAL image model (nano-banana edit, gpt-image, flux, ...), ROUTED THROUGH THE fal-proxy so it bills the Ads agent. image_urls…
For churned accounts, research what has changed since they left — new funding, team growth, competitor dissatisfaction, product updates that address their pain — then assess re-engagement potential and generate a personalized win-back email sequence with timing recommendations.
$ npx -y skills add gooseworks-ai/goose-skills --skill customer-win-back-sequencer --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/customer-win-back-sequencerContext preview
The summary Claude sees to decide when to auto-load this skill.
For churned accounts, research what has changed since they left — new funding, team growth, competitor dissatisfaction, product updates that address their pain — then assess re-engagement potential and generate a personalized win-back email sequence with timing recommendations.
name: customer-win-back-sequencer description: > For churned accounts, research what has changed since they left — new funding, team growth, competitor dissatisfaction, product updates that address their pain — then assess re-engagement potential and generate a personalized win-back email sequence with timing recommendations. Chains web research and LinkedIn monitoring with email sequence generation. tags: [outreach]
Not every churned customer is gone forever. This skill identifies which ones to pursue, finds the right re-engagement angle, and generates a personalized win-back sequence. Timing and relevance are everything — no generic "we miss you" emails.
**Built for:** Startups that have churned customers sitting in a spreadsheet with no plan to re-engage them. The best win-back campaigns are triggered by change — this skill monitors for those changes and strikes when the timing is right.
1. **Churn list** — CSV/sheet with: company name, domain, contact email, contact LinkedIn URL (if available), churn date, MRR at churn, churn reason (if known) 2. **Time since churn filter** — Min/max months since churn to consider (default: 3-18 months. Too recent = too soon. Too old = too stale.) 3. **Minimum value** — Only pursue accounts above $X MRR? (Focus effort on worthwhile wins)
4. **Major product updates since churn** — What's new? (Features, pricing changes, integrations, performance improvements) 5. **Churn reasons addressed** — Which past churn reasons have you actually fixed? 6. **Current offer** — Any win-back incentive? (Discount, extended trial, concierge onboarding, free migration)
7. **Sender** — Who should the emails come from? (Founder, CSM, account exec) 8. **Channel** — Email only, or email + LinkedIn? 9. **Sequence length** — How many touches? (Default: 3-4 over 3-4 weeks)
For each account in the churn list, research what's changed:
Search: "[company name]" funding OR raised OR "series" OR acquisition 2025 2026 Search: "[company name]" hiring OR "we're hiring" OR "growing team" Search: "[company name]" launch OR "new product" OR expansion OR pivot
Extract:
Search: "[contact name]" "[company name]" OR linkedin.com Search: "[company name]" "[relevant title]" new OR hired OR promoted
Determine:
If you know which competitor they switched to:
Search: "[competitor name]" complaints OR issues OR "looking for alternative" Search: "[competitor name]" site:g2.com negative reviews Search: "[company name]" "[competitor name]" OR "switched from"
Look for:
Match what's changed in your product against their churn reason:
| Churn Reason | Product Update | Win-Back Angle | |-------------|----------------|----------------| | "Too expensive" | New pricing tier / startup discount | Price-based re-engagement | | "Missing [feature]" | [Feature] shipped | Feature announcement | | "Too complex" | Simplified onboarding / UX overhaul | "We listened" narrative | | "Switched to [competitor]" | Competitive advantage developed | Competitive displacement | | "Didn't see ROI" | New ROI dashboard / case studies | Proof-based approach | | "Champion left" | N/A — find new champion | Fresh start narrative | | "Company downsized" | Company now growing again (from research) | Timing-based re-engagement |
Score each churned account's re-engagement potential:
Win-Back Score = (Change Signal × Churn Reason Addressability × Account Value) / Time Decay Change Signal (1-5): 5 = Multiple strong signals (funding + growth + competitor issues) 4 = One strong signal (funding or significant growth) 3 = Moderate signal (hiring, product launch) 2 = Minor signal (still operating, no major changes) 1 = No detectable change Churn Reason Addressability (1-3): 3 = You've directly fixed the reason they left 2 = Partially addressed or different angle available 1 = Same issues exist / unknown churn reason Account Value (multiplier): 2.0x = Was top 20% by MRR 1.5x = Mid-tier MRR 1.0x = Lower MRR Time Decay (divisor): 1.0 = Churned 3-6 months ago (sweet spot) 1.2 = Churned 6-12 months ago 1.5 = Churned 12-18 months ago 2.0 = Churned 18+ months ago
| Tier | Score | Action | |------|-------|--------| | **High Priority** | 8+ | Full personalized sequence + founder outreach | | **Medium Priority** | 4-7 | Personalized sequence | | **Low Priority** | 1-3 | Batch campaign or skip |
**Email 1: The Relevant Update (Day 0)**
Subject options: A: "[First name], [specific thing] changed since we last spoke" B: "We fixed the thing that made you leave" C: "[Company] + [Your Product] — worth a
Put your AI agent on the growth team. Research customers and competitors, analyze what is working, create the next campaign, and learn from the result.
Repo: gooseworks-ai/goose-skills
Generate or edit an image via any FAL image model (nano-banana edit, gpt-image, flux, ...), ROUTED THROUGH THE fal-proxy so it bills the Ads agent. image_urls…
Generate a single photoreal or designed image with OpenAI gpt-image via fal.ai. Supports gpt-image-1 (default, fixed sizes — the FAL fallback for Higgsfield's…
Generate an instrumental music bed via ElevenLabs Music, ROUTED THROUGH THE elevenlabs-proxy so it bills the Ads agent. Trims any sparse intro, loudnorm, fades…
Image-to-video (or text-to-video) via any FAL video model (Kling, Seedance, Veo), ROUTED THROUGH THE GooseWorks fal-proxy so the call bills the Ads agent. The…
Generate a voiceover (VO) clip via ElevenLabs text-to-speech, ROUTED THROUGH THE elevenlabs-proxy so it bills the Ads agent. Voice id + script text come from…
Scrape competitor ads from Google Ads by domain. Returns ad creatives, formats, and campaign details. Use for competitive ad research and messaging analysis.