Generate targeted LinkedIn search queries based on problem space and outreach phase, then research and qualify contacts for problem discovery outreach. User tells the skill what problem they're exploring and what phase they're in (problem discovery, validation, or decision). Skill generates tailored search queries, then handles company research via public sources, Google-cached LinkedIn enrichment, scoring, and A/B outreach draft generation. Triggers on "find people to interview about X", "I'm exploring Y problem", "who should I talk to about Z problem", "generate search queries for [problem]", "qualify these contacts", "draft outreach for these people".
Generate persona-specific LinkedIn search queries, qualify contacts, and generate A/B-tested outreach drafts. The user tells the skill their problem space and outreach phase. The skill generates search queries tailored to who actually feels the pain (not just who owns the company). User manually browses LinkedIn using those queries and pastes contact info. The skill does everything else: company research via public sources, scoring, and draft generation.
Core principle: zero LinkedIn automation. The skill never clicks, scrolls, or interacts with LinkedIn pages. The user does all navigation. The skill only reads what is already rendered in open tabs — no different from looking at the screen.
This is the highest-quality enrichment path. The user logs into LinkedIn in the openclaw browser, manually opens profiles and posts, and the skill reads the open tabs passively.
Why this works:
Step 1 — User opens the browser and logs in:
openclaw browser start --browser-profile openclaw
Navigate to linkedin.com, log in manually (one time only — session persists in the profile).
Step 2 — User browses LinkedIn:
Step 3 — Skill reads what is open:
# List all open tabs
openclaw browser tabs --browser-profile openclaw
# Read a specific tab by its target-id
openclaw browser snapshot --target-id <id> --browser-profile openclaw
The skill scans all open tabs, identifies which are LinkedIn profiles vs. posts vs. search results, and extracts content from each.
Step 4 — Skill enriches all profiles automatically: From a LinkedIn profile page the skill can extract:
From a LinkedIn post page the skill can extract:
This replaces Google cache enrichment for any contact the user has opened in a tab. Google cache is the fallback when no tab is open for that person.
IMPORTANT: When the user invokes this skill, the first thing you do is ask them about their problem space and outreach phase, then immediately generate tailored LinkedIn search queries for them to use.
Collect from the user:
name + company pairs. Skip these throughout the process.The key insight: match search filters to who FEELS the pain, not who OWNS the company.
Before generating searches, determine:
Persona tiers by phase:
| Phase | Target Tier | Who to Search For | Why |
|---|---|---|---|
| Phase A (Problem Discovery) | Tier 1 | Individual contributors, specialists, managers who do the work daily | Deep operational knowledge, specific pain examples, frustrated enough to talk |
| Phase B (Validation) | Tier 2 | Directors, Heads of Function, Senior Managers accountable for outcomes | Understand scope + business impact, connect pain to priorities |
| Phase C (Decision) | Tier 3 | VPs, C-suite in relevant function | Buying authority, budget allocation, strategic priorities |
EXCEPTION - Founder-Led Companies (<50 employees): When the problem space naturally sits with founders/CEOs of small companies (e.g., AI agent tooling, developer tools, early-stage product challenges), search for founders REGARDLESS of phase, but filter by:
After collecting the brief, immediately generate 3-5 LinkedIn search queries tailored to the problem space and phase.
IMPORTANT: Keep queries BROAD. Over-filtering in the search query returns zero results. Use LinkedIn's UI filters instead.
Winning pattern:
For Problem Spaces in Established Companies (Pharma, Manufacturing, Enterprise):
Phase A (Problem Discovery):
"[Job Title]" [Industry]
Example: "Quality Manager" Pharma
Phase B (Validation):
"Head of [Function]" [Industry]
Example: "Head of Quality" Pharma
Phase C (Decision):
"VP [Function]" [Industry]
Example: "VP Quality" Pharma
Then use LinkedIn filters: Company size (50-1000), Location (Germany), etc.
For Founder-Led Problems (Startups, Tech, AI):
All Phases (target founders at small companies):
founder [Industry/Tech]
Example: founder AI
Example: CEO SaaS
Then use LinkedIn filters: Company size (1-50), Location, Industry
User says: "I'm exploring SOP handling in Pharma companies, Phase A (problem discovery)"
You generate:
Phase A - Tier 1 (Problem Discovery):
LinkedIn People Search (copy these one by one):
1. "Quality Manager" Pharma
2. "Regulatory Affairs" Pharma
3. "Compliance Manager" Biotech
Then apply these LinkedIn UI filters:
- Company size: 50-1,000 employees
- Location: Germany (or your target region)
- Current company (to filter out job seekers)
Google alternative (no LinkedIn login):