lead-discovery
Skill191 starsChanged 5 months agoMITView on GitHub
AI-driven lead discovery for B2B export. Searches web for potential buyers matching ICP, evaluates fit, and creates CRM records for follow-up.
- Reads credentials
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- workspace/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- b2b-sdr-agentSkill
- chroma-memorySkill
- delivery-queueSkill
- graphifySkill
- quotation-generatorSkill
- sdr-humanizerSkill
- supermemorySkill
- telegram-toolkitSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 27
After discovering a target company, read their website for detailed info
- Distinctive: line 54
Read company website via Jina Reader → extract:
- Distinctive: line 75
Read company website via Jina Reader for deep understanding
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Lead Discovery — AI-Powered Prospecting
Automatically search, filter, and evaluate potential buyers based on your ICP profile.
Triggers
- Cron scheduled execution (Daily 10:00)
- Manual command from owner: "Search for leads in [market/industry]"
Search Strategy
Search Dimensions (rotate daily, pick 1-2)
- Target Market Procurement
- "{{product}} buyers [target country] 2026"
- "[target country] fleet expansion logistics company"
- "[target country] construction equipment procurement"
- Trade Shows & Procurement Signals
- "{{product}} buyers exhibition Africa Middle East 2026"
- "transport logistics tender [region]"
- Company Research (read website)
- After discovering a target company, read their website for detailed info
- Customs / Trade Data
- "[target country] {{product}} import statistics"
- "{{product}} import demand [region] 2026"
Search Execution
Jina Search (find potential buyers)
curl -s 'https://s.jina.ai/QUERY_URL_ENCODED' \
-H 'Authorization: Bearer $JINA_API_KEY' \
-H 'Accept: application/json'Jina Reader (read company website)
curl -s 'https://r.jina.ai/https://target-company.com' \
-H 'Authorization: Bearer $JINA_API_KEY' \
-H 'Accept: application/json'JINA_API_KEY in .secrets/env. Get one free at https://jina.ai/
3-Layer Enrichment Pipeline
Layer 1: Website Extraction
Read company website via Jina Reader → extract:
- Company size, employee count
- Product lines, services
- Certifications (ISO, etc.)
- Contact info (email, phone, WhatsApp)
- Office/warehouse locations
Layer 2: Purchase Signal Search
Jina Search for:
- "[company name] procurement tender"
- "[company name] fleet expansion"
- "[company name] import export"
Layer 3: Information Integration
- Combine all findings into enrichment profile
- Calculate ICP score based on USER.md criteria
- Store research notes in Supermemory with tag "customer_research"
Evaluation Flow
For each discovered prospect:
- Extract: company name, country, industry, size, contact info (email/WhatsApp/phone)
- Read company website via Jina Reader for deep understanding
- Score per USER.md ICP criteria (1-10)
- ICP >= 5: Write to CRM (source=
web_discovery, status=new) - ICP >= 7: Also mark as hot_lead, create research note
- Email found: Mark next_action=
email_outreach - WhatsApp found: Mark next_action=
whatsapp_outreach
Output Format (report to owner)
Today discovered X potential leads:
1. [Company] - [Country] - ICP [X]/10
Industry: [industry] | Size: [size]
Source: [search query]
Contact: [email/website/whatsapp]
Recommendation: [Send cold email / WhatsApp contact / More research / Enter nurture pool]
Added to CRM: X | Pending email outreach: X | Pending WhatsApp: XSearch Frequency & Quota
- Max 20 searches per day (API quota management)
- Weekly coverage: Africa 2 days, Middle East 2 days, SEA 1 day, LatAm 1 day, Other 1 day
- Duplicate companies auto-skipped (check CRM first)
Search Templates by Market
Africa (Mon/Tue)
- "{{product}} importers Nigeria Lagos"
- "logistics company Tanzania fleet"
- "construction company Kenya equipment procurement"
Middle East (Wed/Thu)
- "{{product}} dealers Saudi Arabia"
- "logistics fleet UAE Dubai"
- "construction equipment Oman transport"
Southeast Asia (Fri)
- "{{product}} importers Philippines Manila"
- "logistics company Vietnam fleet"
- "construction Indonesia heavy vehicles"
Latin America (Sat)
- "{{product}} importers Brazil"
- "logistics company Chile fleet"
- "mining transport vehicles Peru"
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

