aithos-rr/aithos-selection/lead-enrichment
Claude Code and agent skill by aithos-rr/aithos-selection
- community
Checking that the SKILL.md file is still in the repository.
Arricchisce liste di lead grezzi (nome, azienda) con dati completi — email verificata, ruolo, LinkedIn, segnali intent, dimensione azienda — scrivendo risultato su Google Sheet. Usa parallel-cli + Attio MCP + scraping intelligente. Da usare con lista CSV/Sheet importata da evento/conferenza, export CRM, scraping LinkedIn Sales Navigator. Skill del Webinar 2 Claude Code per il GTM.
Install
npx vskill@latest install aithos-rr/aithos-selection/lead-enrichmentSKILL.md
The same SKILL.md was published earlier as aithos-rr/aithos-selection/lead-enrichment.
Lead Enrichment
Trasforma una lista di 500 "nome + azienda" in una lista ricca con email verificata, ruolo confermato, LinkedIn, segnali intent, pronta per outreach SmartLead/HeyReach.
When to use
Attiva quando:
- Lista lead con dati parziali (es. solo nome + company)
- Export CRM con >30% campi vuoti
- Nuova lista post-evento conferenza
- Scraping LinkedIn Sales Navigator da arricchire
- Preparazione campagna outbound
Non attivare se:
- Lista <10 (→ manuale più veloce)
- Dati già completi
- Lead enterprise (>1000 employees) — richiedono workflow differente
Prerequisiti
parallel-cliinstallato (con API key in~/.zshrc)- Attio MCP configurato (per contesto aziendale)
- OAuth Google per scrivere su Sheet
- Lista input: CSV o Google Sheet con almeno colonne
Name,Company
Instructions
Fase 1 — Ingest e validate
Leggi input (CSV o Sheet URL):
Output: lista di {name, company, extra_fields} normalizzata.
Validazione:
- Rimuovi duplicati (stesso name+company)
- Valida che abbia Name + Company (altrimenti skip con warning)
Fase 2 — Enrichment batch
Per ogni lead, esegui in parallelo (Agent Teams):
Per lead, le operazioni:
- Email finder via
parallel-cli enrich --type email --name "..." --company "..." - LinkedIn via
parallel-cli search "site:linkedin.com/in <name> <company>" - Azienda via Attio MCP se già nel CRM, altrimenti
parallel-cli research <company> - Ruolo cross-check LinkedIn bio vs lista input
- Intent signals (bonus): recent funding, hiring, job changes →
parallel-cli search "<company> funding 2026 OR hiring 2026"
Compone lead arricchito:
Fase 3 — Quality scoring
Per ogni lead arricchito, assegna score:
- 🟢 Hot (score 80+): email verified high confidence, role clear, signals positivi
- 🟡 Warm (50-79): dati completi ma signals incerti
- 🔴 Cold (<50): dati parziali, skip per outreach ora
Fase 4 — Output to Sheet
Scrivi su Google Sheet (new tab o update):
| Name | Company | Email conf | Role | Company Size | Industry | Intent Signals | Score | Status | |||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Mario Rossi | Acme | mario@... | 0.92 | https://... | VP Marketing | 50-100 | SaaS | Series A Feb26 | 🟢 85 | Ready |
Fase 5 — Review batch + Attio sync
Proponi all'utente (AskUserQuestion):
- Sincronizza lead 🟢 Hot in Attio CRM? (create_record via Attio MCP)
- Skip 🔴 Cold dalla lista outreach?
- Manual review 🟡 Warm?
Fase 6 — Report
Examples
Esempio 1: 200 lead conferenza SaaStr 2026
Input: CSV con Name, Company, Role (self-reported), Email (scarabocchio) Processing: 10 agenti paralleli, ~20 min totali Output: Sheet con 200 lead, 65% email verified, 30 🟢 Hot ready per outreach
Esempio 2: CRM Attio audit
Lista: 500 contatti Attio con campo email vuoto Enrichment: per ognuno trova email verificata Sync: update record Attio con email + confidence
Gotchas
- 🔴 Email verification false positive: confidence 0.8 != 100% verified. Usa bouncer/validator separato prima di inviare (cost: 1 cent/email, saves reputation).
- 🔴 Rate limit parallel-cli: oltre 100 call/min = throttling. La skill ha built-in backoff.
- 🔴 GDPR: lead EU richiedono lawful basis. Documenta fonte scraping e basis (contract/legitimate interest).
- 🟡 LinkedIn anti-scraping: se scraping diretto, usa Apify o Sales Nav ufficiale. Evita blacklist IP.
- 🟡 Company duplicates: "Acme Corp" vs "Acme Inc" vs "ACME" → normalize prima.
- 🟢 Attio dedup: prima di sync, check if record esiste via
mcp__attio__search_records. Update vs create. - 🟢 Lista Hot → /outbound-campaign: chain natural per passare da lista arricchita a outreach.
Scripts
scripts/load_csv.py,scripts/load_sheet.py: ingestscripts/enrich_batch.py: Agent Teams parallelscripts/score.py: quality scoringscripts/write_sheet.py: output Google Sheetscripts/attio_sync.py: sync Hot leads
References
references/enrichment-fields.md: catalogo 20 campi possibili + prioritàreferences/gdpr-compliance.md: checklist EU leadreferences/parallel-cli-recipes.md: pattern call efficaci per enrichment
Crediti
Skill originale Claude Week Learnn — Webinar 2 (Code GTM). Stack: parallel-cli + Attio MCP + OAuth Google.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/lead-enrichment/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/aithos-rr/aithos-selection/lead-enrichment)