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…
End-to-end leadership change signal composite. Takes any set of companies, detects recent leadership changes (new VP+, C-suite hires and promotions), evaluates relevance to your product, and drafts personalized outreach. Uses Apollo People Search (free) for fast detection +
$ npx -y skills add gooseworks-ai/goose-skills --skill leadership-change-outreach --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/leadership-change-outreachContext preview
The summary Claude sees to decide when to auto-load this skill.
End-to-end leadership change signal composite. Takes any set of companies, detects recent leadership changes (new VP+, C-suite hires and promotions), evaluates relevance to your product, and drafts personalized outreach. Uses Apollo People Search (free) for fast detection +
name: leadership-change-outreach
version: 2.0.0
description: >
End-to-end leadership change signal composite. Takes any set of companies,
detects recent leadership changes (new VP+, C-suite hires and promotions),
evaluates relevance to your product, and drafts personalized outreach.
Uses Apollo People Search (free) for fast detection + Apollo Enrichment (1 credit/person)
for employment history, start dates, LinkedIn URLs, and verified emails.
tags: [outreach]
graph:
provides:
- companies-with-leadership-changes # Companies with relevant new leaders
- new-leader-profiles # Details on the new leaders (enriched)
- personalized-email-sequences # Outreach drafts to new leaders
requires:
- company-list # Any list of companies (with domains)
- your-company-context # What you sell, what leaders care about
connects_to:
- skill: cold-email-outreach
when: "User wants to launch the campaign via their outreach tool"
passes: new-leader-profiles, personalized-email-sequences
- skill: linkedin-outreach
when: "User wants LinkedIn outreach instead of or alongside email"
passes: new-leader-profiles
capabilities: [apollo-lead-finder, email-drafting]Detects new leadership hires at target companies and evaluates whether the new leader is relevant to your product — as a direct buyer, a champion, or someone whose mandate aligns with what you sell. If relevant, enriches their profile and drafts personalized outreach that speaks to their new-role priorities.
**Why leadership changes work:** New leaders re-evaluate everything in their first 90 days. They inherit a vendor stack they didn't choose, a team they didn't build, and KPIs they need to hit fast. They're the most receptive buyers in any organization because:
Load this composite when:
This composite uses a two-phase Apollo pipeline that replaces slower web search approaches:
1. **Apollo Free Search** — `search_people` with `q_organization_domains` + `person_titles` filters. Returns person IDs, obfuscated names, and titles. No credits consumed. Scans 100+ people across dozens of companies in ~30 seconds. 2. **Local Post-Filter** — Strict title matching to remove noise from Apollo's fuzzy matching (regional titles, sub-function heads, non-GTM roles). Typically reduces results by 50-60%. 3. **Apollo Enrichment by ID** — `people/match` with the person `id` from free search. Returns full employment history with `start_date`/`end_date` for every role, LinkedIn URL, verified email, and full name. Costs 1 credit per person. 4. **Change Detection** — Filter enriched results by `start_date` on the `current: true` employment entry within the lookback window.
**Why this beats web search:** Web search relies on press releases and announcements — most leadership changes below C-suite are never publicly announced. Apollo pulls from LinkedIn profile data directly, catching changes that web search misses. Speed: ~90 seconds total vs 5+ minutes for web search.
**Cost:** 1 Apollo credit per person enriched. With a tight post-filter (VP+ GTM titles only), a scan of 10-15 companies typically costs 30-50 credits.
**Important:** Apollo tracks start dates at month granularity (e.g., `2026-02-01`), not exact day. Set lookback windows accordingly — use full months rather than exact day counts.
---
On first run for a client/user, collect and store these preferences. Skip on subsequent runs.
| Question | Purpose | Stored As | |----------|---------|-----------| | What does your product do? (1-2 sentences) | Match against leader mandates | `company_description` | | What leader titles are **direct buyers** of your product? | Highest priority — they can sign the check | `buyer_leader_titles` | | What leader titles could **champion** your product? | They'd advocate internally or be an entry point | `champion_leader_titles` | | What leader titles have **mandates your product supports**? | Their goals align with your product's value | `aligned_leader_titles` | | What departments are relevant? | Filter out irrelevant leadership changes | `relevant_departments` |
**Example for a sales AI product:**
buyer_leader_titles: ["VP Sales", "CRO", "Chief Revenue Officer", "SVP Sales"] champion_leader_titles: ["Director of Sales Ops", "Head of Revenue Operations", "VP Business Development"] aligned_leader_titles: ["COO", "CEO", "VP Operations"] relevant_departments: ["Sales", "Revenue", "Operations", "Business Development"]
| Question | Options | Stored As | |----------|---------|-----------| | How far back should we look? | 30 / 60 / 90 days (default: 90) | `lookback_days` | | Minimum seniority for detection? | VP+ (default) / Head+ / Director+ | `min_seniority` |
The free search uses `person_titles` to filter. Define these based on the client's buyer/champion/aligned titles. Default VP+ GTM titles:
titles = [
# C-Suite
'CRO', 'Chief Revenue Officer',
'CMO', 'Chief Marketing Officer',
'CCO', 'Chief Commercial Officer',
# VP-level (Sales, Marketing, Growth, Revenue, RevOps, Demand Gen, BD, Partnerships, CS, Commercial, GTM)
'VP of Sales', 'VP Sales', 'Vice President of Sales', 'Vice President Sales',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.