Outbound Prospecting Engine
End-to-end outbound prospecting: detect intent signals, research companies, find decision-maker contacts, personalize messaging, launch campaign.
by Athina AInpx gooseworks install --all # then, in Claude Code, Cursor, or Codex: /gooseworks use the outbound-prospecting-engine skill
Outbound Prospecting Engine
Build and run a complete outbound prospecting system: signal detection → company research → contact finding → personalization → campaign launch.
When to Use
- "Set up outbound prospecting for [client]"
- "Build a lead gen engine targeting [ICP]"
- "Find and reach out to companies that need [solution]"
Prerequisites
- Client context.md with ICP, value props, positioning
- Signal keywords (what to monitor for intent)
- Approved messaging / email sequences (or generate them)
Steps
1. Define Signal Sources
Based on the client's ICP and motion, select which signals to monitor:
| Signal Source | Best For | Skill |
|---|---|---|
| Job postings | Companies with allocated budget | job-posting-intent |
| Funding announcements | Companies with fresh capital | funding-signal-monitor |
| LinkedIn posts/comments | Practitioners discussing the problem | linkedin-post-research + linkedin-commenter-extractor |
| Conference attendees | People actively engaged with the space | luma-event-attendees |
| Competitor customers | Companies already buying similar solutions | competitor-post-engagers |
2. Run Signal Detection
Execute selected signal skills with client-specific keywords. Run in parallel.
Output: Raw signal list — companies + signal context.
3. Qualify & Score
Skill: lead-qualification
Filter against ICP criteria. Score each lead:
- Multi-signal leads = highest priority
- Job posting + funding = strongest intent
- Single social mention = lowest (awareness only)
4. Find Decision-Maker Contacts
Skill: company-contact-finder
For top qualified companies, find the specific decision-makers:
- Target titles from client's ICP
- Get email addresses and LinkedIn URLs
5. Deduplicate
Skill: contact-cache
Check all leads against the contact cache. Add new leads to cache. Skip any that have been contacted before.
6. Personalize Outreach
For each lead, generate personalized email sequence using:
- The signal that surfaced them (the "why now")
- Their company context (what they do, their pain)
- The client's value proposition (how it solves their pain)
7. Launch Campaign
Skill: cold-email-outreach
Set up the outreach campaign in your chosen tool:
- Create campaign with name and schedule
- Upload lead list
- Configure 2-3 email sequence (personalized per lead or per segment)
- Allocate mailboxes
- Set sending schedule
8. Monitor & Iterate
- Track open rates, reply rates, meeting bookings
- A/B test subject lines and messaging
- Re-run signal detection weekly to add new leads
- Update contact cache with outcomes
Ongoing Cadence
- Weekly: Re-run signal detection, qualify new leads, add to campaign
- Bi-weekly: Review campaign metrics, adjust messaging
- Monthly: Review overall pipeline contribution, adjust signal sources
Human Checkpoints
- After Step 3: Review qualified lead list before finding contacts
- After Step 6: Review personalized email copy before launching campaign
- After Step 8: Review campaign performance metrics
What's included
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.