- Home
- Skills
- Sales & Lead Gen
- lead research
Works with the AI Agents you already use
lead research
Builds prospect lists where every fact has a source link, reports shortfalls instead of inventing companies, and never guesses email addresses.
$9
lead research
Example session with this skill installed
Find 5 companies that install solar photovoltaic systems and publish a business address in their official Impressum within Berlin, Germany.
Company size can be any size. No specific offer or product is provided, so do not score fit against an assumed offer.
Return each company's
- Legal/display name
- Solar installation focus
- Address published in its Impressum
- Employee-count status
- Official website
- Supporting source URLs
- Confidence label
Use only facts supported by cited sources. Mark company-reported headcounts as self-reported. Keep unverified counts as "Not publicly verified." Do not treat multiple pages on one company website as independent sources. Do not claim official registry verification unless you checked the registry record.
- Read your context and instructions
- Compiled the lead research
| No. | Company Name | Solar Services | Berlin Address | Employee Count | Website | Confidence |
|---|---|---|---|---|---|---|
| 1 | Solaro PV Berlin GmbH | Solar PV, battery storage, renewable energy systems | Weinbergsweg 10, 10119 Berlin | 25+ (self-reported) | https://solaro-pv.de | Medium |
| 2 | Solarnetz GmbH | PV planning and installation | Volkmarstr. 18, 12099 Berlin | Not publicly verified | https://solarnetz-berlin.de | Medium |
| 3 | Profisolar Bau GmbH | PV, storage, heat pumps, commercial and industrial solar | Turmstraße 8, 10559 Berlin | Not publicly verified | https://www.profisolarbau.com | Medium |
| 4 | Celer GmbH Haus- und Solartechnik | PV consulting, planning and installation | Marzahner Str. 24 A, 13053 Berlin | Not publicly verified | https://www.celer-gmbh.de | Medium |
| 5 | Henning Fitschen (Fitschen Solar) | PV engineering, planning, installation and service | Johannes-Werner-Straße 23, 12487 Berlin | Not publicly verified | https://www.fitschensolar.de | Medium |
Evidence Limitations
- Sources: Official company websites, Impressum and About pages.
- Employee counts are self-reported or marked Not publicly verified.
- Commercial-register records were not independently verified.
- This is a sample of 5 companies, not a complete Berlin market census.
Connects securely to your tools. The creator never sees your data.
About this skill
Finding reliable B2B prospects is slow, and most automated tools return outdated or fabricated data that burns your domain reputation. This skill transforms your agent into a disciplined business research analyst that builds verified prospect lists with mandatory source attribution for every fact.
What it does
- ICP Validation confirms industry, location, company size, and offer fit before starting the search to prevent irrelevant results.
- Source-Backed Research enforces a strict rule where every non-null field must have a verifiable source link.
- Evidence Verification checks company websites to confirm they are active businesses rather than defunct or directory-only entries.
- Data Collection captures legal names, verified industry tags, office locations, and published business contact info.
- Shortfall Reporting identifies exactly why a target count wasn't met instead of padding the list with guesses or "hallucinated" companies.
How it works
- Define the target profile including niche, geography, and exclusions.
- Search using specific patterns that surface trade associations and primary company domains.
- Verify candidates against the Ideal Customer Profile (ICP) using live site data.
- Export results in a structured Markdown table and a machine-readable JSON object following a strict lead-record schema.
Frameworks & tools
This skill is framework-agnostic and runs in any agent environment supporting SKILL.md, such as Claude Code or Cursor. It utilizes the agent's built-in web search and browsing capabilities to navigate public business registries and company websites.
Why this beats prompting it yourself
Standard prompts often cause LLMs to "guess" email formats or invent companies to satisfy a requested count. This skill implements a strict logic gate that forbids fabrication, mandates source links, and requires manual confirmation of business activity before a lead is recorded.
Use cases
- Build a targeted prospect list from a specific ICP for outbound sales.
- Identify competitors or partners within a specific regional industry.
- Verify the status and size of a list of companies before CRM import.
- Find trade association members for niche market research.
Known limitations
Does not support lead scoring or outbound email writing. Research is limited to publicly available data on company websites and authorized business registries.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Sales & Lead Gen.
Requires an agent with web browsing or search capabilities. Cannot bypass login walls or 403 errors. Does not provide personal mobile numbers or private contact data.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 4 days ago
Requires an AI agent with web search or browsing capabilities. Research uses publicly available business information. Results include source references and may have gaps when information cannot be verified. Demo data is illustrative.