Outbound prospecting engine
End-to-end outbound prospecting: detect intent signals, research companies, find decision-maker contacts, personalize messaging, launch campaign.
How to use it
- Hit Copy SKILL.md — or use the Claude Code line below to get every file.
- Claude: ⋯ → Download .md, then Customize → Skills → Add → Upload skill.
ChatGPT: make a Project and paste it into Instructions.
Neither? Paste it at the top of a new chat — it works for that chat. - Describe your job in plain words. The AI follows the skill from there.
npx degit gooseworks-ai/goose-skills/skills/outreach/playbooks/outbound-prospecting-engine#main ~/.claude/skills/outbound-prospecting-engineFor one project only, change the path to .claude/skills/outbound-prospecting-engine. This skill also uses context.md — copying SKILL.md alone won't be enough. See the folder on GitHub.
Not working?
- Check which app you pasted it into — the steps above name the right one.
- Some skills need the paid tier of Claude or ChatGPT.
Paste into Claude, ChatGPT or Cursor.
Show the full text104 lines
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
| 1 | |
| 2 | type playbook |
| 3 | name outbound-prospecting-engine |
| 4 | description > |
| 5 | End-to-end outbound prospecting: detect intent signals, research companies, |
| 6 | find decision-maker contacts, personalize messaging, launch campaign. |
| 7 | |
| 8 | |
| 9 | # Outbound Prospecting Engine |
| 10 | |
| 11 | Build and run a complete outbound prospecting system: signal detection → company research → contact finding → personalization → campaign launch. |
| 12 | |
| 13 | ## When to Use |
| 14 | |
| 15 | "Set up outbound prospecting for [client]" |
| 16 | "Build a lead gen engine targeting [ICP]" |
| 17 | "Find and reach out to companies that need [solution]" |
| 18 | |
| 19 | ## Prerequisites |
| 20 | |
| 21 | Client context.md with ICP, value props, positioning |
| 22 | Signal keywords (what to monitor for intent) |
| 23 | Approved messaging / email sequences (or generate them) |
| 24 | |
| 25 | ## Steps |
| 26 | |
| 27 | ### 1. Define Signal Sources |
| 28 | |
| 29 | Based on the client's ICP and motion, select which signals to monitor: |
| 30 | |
| 31 | | Signal Source | Best For | Skill | |
| 32 | |--------------|---------|-------| |
| 33 | | Job postings | Companies with allocated budget | job-posting-intent | |
| 34 | | Funding announcements | Companies with fresh capital | funding-signal-monitor | |
| 35 | | LinkedIn posts/comments | Practitioners discussing the problem | linkedin-post-research + linkedin-commenter-extractor | |
| 36 | | Conference attendees | People actively engaged with the space | luma-event-attendees | |
| 37 | | Competitor customers | Companies already buying similar solutions | competitor-post-engagers | |
| 38 | |
| 39 | ### 2. Run Signal Detection |
| 40 | |
| 41 | Execute selected signal skills with client-specific keywords. Run in parallel. |
| 42 | |
| 43 | **Output**: Raw signal list — companies + signal context. |
| 44 | |
| 45 | ### 3. Qualify & Score |
| 46 | |
| 47 | **Skill**: lead-qualification |
| 48 | |
| 49 | Filter against ICP criteria. Score each lead: |
| 50 | Multi-signal leads = highest priority |
| 51 | Job posting + funding = strongest intent |
| 52 | Single social mention = lowest (awareness only) |
| 53 | |
| 54 | ### 4. Find Decision-Maker Contacts |
| 55 | |
| 56 | **Skill**: company-contact-finder |
| 57 | |
| 58 | For top qualified companies, find the specific decision-makers: |
| 59 | Target titles from client's ICP |
| 60 | Get email addresses and LinkedIn URLs |
| 61 | |
| 62 | ### 5. Deduplicate |
| 63 | |
| 64 | **Skill**: contact-cache |
| 65 | |
| 66 | Check all leads against the contact cache. Add new leads to cache. Skip any that have been contacted before. |
| 67 | |
| 68 | ### 6. Personalize Outreach |
| 69 | |
| 70 | For each lead, generate personalized email sequence using: |
| 71 | The signal that surfaced them (the "why now") |
| 72 | Their company context (what they do, their pain) |
| 73 | The client's value proposition (how it solves their pain) |
| 74 | |
| 75 | ### 7. Launch Campaign |
| 76 | |
| 77 | **Skill**: cold-email-outreach |
| 78 | |
| 79 | Set up the outreach campaign in your chosen tool: |
| 80 | Create campaign with name and schedule |
| 81 | Upload lead list |
| 82 | Configure 2-3 email sequence (personalized per lead or per segment) |
| 83 | Allocate mailboxes |
| 84 | Set sending schedule |
| 85 | |
| 86 | ### 8. Monitor & Iterate |
| 87 | |
| 88 | Track open rates, reply rates, meeting bookings |
| 89 | A/B test subject lines and messaging |
| 90 | Re-run signal detection weekly to add new leads |
| 91 | Update contact cache with outcomes |
| 92 | |
| 93 | ## Ongoing Cadence |
| 94 | |
| 95 | **Weekly**: Re-run signal detection, qualify new leads, add to campaign |
| 96 | **Bi-weekly**: Review campaign metrics, adjust messaging |
| 97 | **Monthly**: Review overall pipeline contribution, adjust signal sources |
| 98 | |
| 99 | ## Human Checkpoints |
| 100 | |
| 101 | **After Step 3**: Review qualified lead list before finding contacts |
| 102 | **After Step 6**: Review personalized email copy before launching campaign |
| 103 | **After Step 8**: Review campaign performance metrics |
| 104 |