mcpbeat

Outbound Prospecting Engine

gooseworks-ai/outbound-prospecting-engine

> find decision-maker contacts, personalize messaging, launch campaign.

907 tokens
context cost
the whole folder, loaded on every use
2
files
instructions only
0
copies elsewhere
how many repositories repackaged it
1086
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/gooseworks-ai/goose-skills --skill outbound-prospecting-engine

What comes with it

274 bytes besides the instruction
skill.meta.json

The instruction itself

14 sections, as written by the author

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

How to use it

Copy the folder

Take gooseworks-ai/outbound-prospecting-engine from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.