← Back to Skills Marketplace
romainrabreau

LinkedIn Prospector

by romainrabreau · GitHub ↗ · v1.2.0 · MIT-0
cross-platform ✓ Security Clean
332
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install linkedin-prospector
Description
Score LinkedIn prospects by signal strength (0-3). Detect high-intent leads: new job, funding, recent post, active hiring. Free skill - full outreach methodo...
README (SKILL.md)

LinkedIn Prospector

Score LinkedIn prospects by signal strength before reaching out.

This skill helps your OpenClaw agent evaluate whether a prospect is worth contacting right now - based on observable signals, not guessing.

What this skill does

Your agent reads a prospect list and assigns each person a score:

Score 3 - Contact now:

  • New job in last 90 days AND your offer is relevant to their role
  • Company raised funding in last 6 months
  • Published a post in last 7 days that relates to your offer
  • Actively hiring for roles that indicate a problem you can solve

Score 2 - Optional:

  • Weaker versions of the above (older signals, indirect relevance)

Score 0-1 - Skip:

  • No detectable signal
  • Skipping score 0-1 prospects is the main reason high-performing outreach works

How to use

Load this skill into your OpenClaw agent:

SKILL signal-lead-finder.md

Then give your agent a prospect list (CSV or plain text with first name, LinkedIn URL, company, title).

Ask:

"Review this prospect list. Apply signal-lead-finder.md. 
Score each person 0-3. Sort by score descending. 
Show me the top 10 with their specific signals."

Your agent will then draft outreach messages only for score-3 prospects (if you use outreach-sequence.md from the full pack).

What this skill does NOT do

This is a scoring and decision framework, not a browser automation tool. Your agent reads context (prospect info you provide) and applies the scoring rules. It does not log into LinkedIn or send messages automatically - any message sending uses your agent's normal capabilities and requires your review.

Scoring rules

The agent applies this logic:

Signal check:
- New job (\x3C90 days): +2 if role matches your ICP
- Funding (\x3C6 months): +2 if company stage matches  
- Recent post (\x3C7 days): +1 if topic overlaps with your offer
- Active hiring: +1 if roles indicate the problem you solve

Score 3: multiple strong signals, contact now
Score 2: single weak signal, optional
Score 0-1: no signal, skip

Why signal scoring matters

Outreach without signal scoring gets 3-5% reply rate (industry average). Outreach with signal scoring gets 25-35%+ reply rate.

The difference is not the message quality. It is whether the person has a reason to care right now.

Full methodology pack

This is the free signal-scoring skill. The full pack includes:

  1. signal-lead-finder.md (this file)
  2. outreach-sequence.md - message structure and follow-up timing rules
  3. message-quality-check.md - quality scoring (0-5) before sending
  4. setup-course.md - ICP definition, list building, campaign setup
  5. winning-examples.md - 10 annotated message examples with scores
  6. sales-fundamentals.md - the 70/30 rule and forbidden words

Full pack: https://openclaw-courses-fawn.vercel.app - €14.99, delivered by email.


Built by Romain Rabreau, founder of Recon0x. Contact: [email protected]

Usage Guidance
This skill is an offline scoring framework that operates on prospect lists you provide and does not itself access LinkedIn or external services. Before using: avoid pasting sensitive personal data (SSNs, private credentials, medical info), review any outreach text the agent generates before sending, and confirm compliance with LinkedIn and privacy rules if you use the results for outreach. If you plan to buy the paid pack, verify the vendor/site independently before sharing payment details.
Capability Analysis
Type: OpenClaw Skill Name: linkedin-prospector Version: 1.2.0 The skill bundle contains only metadata and Markdown instructions (SKILL.md) designed to guide an AI agent in scoring LinkedIn prospects based on business signals like recent funding or job changes. There is no executable code, no evidence of data exfiltration, and no malicious prompt injection; the external link (openclaw-courses-fawn.vercel.app) appears to be a legitimate promotional link for a paid methodology pack.
Capability Assessment
Purpose & Capability
Name/description (scoring LinkedIn prospects) match the SKILL.md content. The skill is a decision framework that operates on prospect lists you supply and does not request unrelated credentials or tools.
Instruction Scope
SKILL.md instructs the agent to read a user-provided prospect list (CSV/plain text) and apply explicit scoring rules. It does not instruct web scraping, reading system files, accessing environment variables, or transmitting data to third-party endpoints. It does note that sending messages would use the agent's normal messaging capabilities (user review required).
Install Mechanism
No install spec and no code files present (instruction-only). Nothing will be written to disk or downloaded as part of the skill itself.
Credentials
The skill declares no required env vars, credentials, or config paths. That matches its described purpose of locally scoring user-supplied prospect lists.
Persistence & Privilege
Skill is not marked always:true and requests no elevated privileges or persistent system changes. It can be invoked autonomously per platform defaults, which is normal for skills.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install linkedin-prospector
  3. After installation, invoke the skill by name or use /linkedin-prospector
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.2.0
v1.2.0: Clarified scope - this is a scoring/decision framework, not browser automation. Removed ambiguous language about automated sending. Added explicit note that the skill does not log into LinkedIn directly. Uses agent's normal capabilities with user review.
v1.1.0
Signal-based lead scoring (0-3), automated 3-touch sequence (day 0/3/7), message quality enforcement (70/30 rule, forbidden words, 150-char limit). 35%+ reply rate on real campaigns.
Metadata
Slug linkedin-prospector
Version 1.2.0
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 2
Frequently Asked Questions

What is LinkedIn Prospector?

Score LinkedIn prospects by signal strength (0-3). Detect high-intent leads: new job, funding, recent post, active hiring. Free skill - full outreach methodo... It is an AI Agent Skill for Claude Code / OpenClaw, with 332 downloads so far.

How do I install LinkedIn Prospector?

Run "/install linkedin-prospector" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is LinkedIn Prospector free?

Yes, LinkedIn Prospector is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does LinkedIn Prospector support?

LinkedIn Prospector is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created LinkedIn Prospector?

It is built and maintained by romainrabreau (@romainrabreau); the current version is v1.2.0.

💬 Comments