Cold Outreach
Trova i prospect giusti, li studia e redige contatti personalizzati.
Trova i prospect giusti, li studia uno a uno per trovare un aggancio di personalizzazione autentico e redige messaggi che invieresti davvero — niente parte senza la tua approvazione.

Installala in 3 passaggi
Nessuna registrazione. Nessuno strumento da riga di comando. Scegli la tua AI, copia una riga e incollala.
Preferisci fare da te? Acquista la skill ($4.99), scarica lo ZIP dalla conferma d'acquisto, decomprimilo nella cartella mostrata sopra e riavvia la sessione della tua AI — stesso risultato. L'hai già acquistata? Il tuo assistente AI può scaricarla per te.
Prove dal mondo reale
Persone vere hanno svolto proprio questo lavoro con agenti IA.
Research and draft cold outreach with Claude Code
Leggi il caso →Caso d'usoRun marketing prospecting and SEO research
Leggi il caso →Caso d'usoRun business development and sourcing bots on email and Teams
Leggi il caso →Cosa contiene
Un file SKILL.md (la guida operativa) + un modello di partenza. Un'anteprima:
Cold Outreach
When to use
- You're doing business development and need personalized cold emails without writing each one from scratch
- You want to target businesses with weak web presence for your service
- You're running LinkedIn outreach and need research-backed messages, not mail-merge templates
- You've spotted buying signals (hiring sprees, funding rounds, new launches) and want to act on them fast
- Your marketing team needs a prospect list plus fresh SEO research in the same pass
Workflow
- Define the target (input: your business → output: ICP + buying signals)
Write the ideal customer profile: company size, industry, geography, the titles you want to reach. Add the buying signals you'll watch for — hiring sprees, funding rounds, product launches, outdated websites. A vague ICP produces a vague list; this step decides everything downstream. - Build the list (input: ICP + signals → output: prospect list)
Search for matching companies across your sources: web search, LinkedIn, local business data, or niche communities. For each prospect record the company, the right contact, their role, and a source link. Keep the list small enough to research properly — 50 researched prospects beat 5,000 names. - Research each prospect (input: prospect list → output: personalization notes)
Dig into what each prospect is actually doing: their business, recent news, what's broken or missing (no website, outdated site, bad reviews). The goal is one genuine hook per prospect — something specific you noticed about them, not a compliment that could apply to anyone. - Draft the outreach (input: personalization notes → output: message drafts)
Write one message per prospect: short (around 100 words for email), the hook up front, one clear tie to what you offer, one specific ask. Every claim in the draft carries a source link so you can verify it. Drafts sit in your outbox — nothing sends itself. - You approve everything (input: drafts → output: approved sends)
Read every message before it goes out. Fix the tone, cut anything that sounds templated, and verify the personalization is real. Only then do the messages move into your sending tool, one approved batch at a time. - Follow up on replies (input: replies → output: follow-up drafts)
When people reply, draft follow-ups on a schedule: answer their question, attach the material they asked for, suggest the next step. You still take over warm conversations personally — the skill handles the draft, you handle the relationship.
Output spec
Anteprima del modello
Cold Outreach — ICP Brief, Prospect Sheet & Approval Queue
No message goes out without your approval. Ever.
ICP brief
Target: {company size / industry / geography} Titles to reach: {e.g. founder, marketing manager} Buying signals: {e.g. hiring spree, funding round, outdated website, bad reviews} Offer angle: {one line — what you do for them}
Prospect research sheet
Message draft — {company} / {contact}
Channel: {email / LinkedIn} Subject: {subject line}
> {draft — ≤100 words, hook up front, one offer tie-in, one specific ask}
Sources cited: {urls backing each claim}
[ ] Approve & send [ ] Edit first [ ] Skip
Follow-up queue
Il pacchetto della skill (SKILL.md + modello) è scritto in inglese.
Potrebbe piacerti anche
Grok Bot Routine Rescue
Find which scheduled routine is eating your weekly pool — and kill it
Flussi di lavoro
Inbox Triage
La tua casella, già letta: urgenti segnalati, risposte in bozza, tu devi solo premere invio
Flussi di lavoro
Bill Fighter
Contesta addebiti ingiusti e reclami respinti con lettere supportate dalle prove