cold-call-expert
Skill9 starsChanged 2 months agoMITView on GitHub
Génère des scripts de cold call B2B world-class pour vendre du high-ticket service (3-15k€) à des fondateurs d'agences, consultants, cabinets de conseil. Calibré sur Cold Calling Sucks (Farrokh/Cegelski 2024), Josh Braun, 30MPC, Voss, Sandler, SPIN, Sales Odyssey FR, Modjo, Enzo Colucci, Gong Labs 90 380 cold calls. Use when the user asks to "write a cold call script", "écrire un script de cold call", "script de prospection téléphonique", "cold call pour {offre}", "génère un script d'appel à froid". La feature SaaS live est exposée dans your-app.example.com → /client/sales/cold-call-script.
In this repository20 other files it gives its agents.
- campaign-proposalSkill
- client-onboarding-flowSkill
- cold-traffic-landing-pageSkill
- competitor-ads-researchSkill
- creative-briefSkill
- creative-staticsSkill
- creative-statics-v2Skill
- data-scrapingSkill
- deep-searchSkill
- devis-vercel-generatorSkill
- meta-ads-copywriterSkill
- meta-ads-creative-frameworkSkill
- meta-campaign-launcherSkill
- meta-lead-notificationsSkill
- outbound-sequence-writerSkill
- rework-campaignSkill
- sales-call-analyzerSkill
- sales-follow-up-sequenceSkill
- vsl-copywriterSkill
- vsl-end-to-end-builderSkill
The file
Files
Cold Call Script Expert
Skill méta qui consolide la recherche marché complète sur le cold call B2B services et l'expose en :
- Corpus baked →
output/cold-call-expertise.md(synthèse en 14 sections) - System prompt intégré dans la feature SaaS de l'agence
(
app/apps/web/src/lib/cold-call-script-writer/script-prompt.ts) - UI live dans l'espace client :
/client/sales/cold-call-script(à côté de la carte Sales Call Analyzer)
Status
✅ v1.0 — 2026-05-23 — En production
- Recherche corpus (5 sous-agents parallèles) →
research/01..05.md - Synthèse →
output/cold-call-expertise.md - System prompt expert → encodé dans le SaaS (
script-prompt.ts) - API + UI Next.js shippées sur main + Vercel
- Migration Supabase 033 — à appliquer manuellement (cf.
APPLY.mddu repo)
Architecture
SKILL.md ← ce fichier
├── research/
│ ├── 01-youtube-channels.md ← 15 chaînes FR + EN
│ ├── 02-books-and-courses.md ← 15 livres + formations
│ ├── 03-top-practitioners.md ← 14 practitioners + 10 podcasts
│ ├── 04-frameworks-b2b-services.md ← 15 frameworks documentés
│ └── 05-objections-gatekeeper-voicemail.md ← 22 objections + gatekeepers + VM
└── output/
└── cold-call-expertise.md ← corpus consolidé (source de vérité)Doctrine clé (extrait — voir corpus pour version complète)
- Context-first > Permission générique
- Problème > Pitch (Gong : +3x conversion avec problem language)
- Mr. Miyagi sur les objections (30MPC)
- Single CTA = book discovery 30-45 min
- 15 secondes pour gagner le droit de continuer
- Tonalité = 70% du résultat (Voss)
- 1 résultat max, daté et nommé
- Esquiver le prix en cold call
- Anti-patterns interdits ("Comment allez-vous ?", "Est-ce un bon moment ?")
- Peer-context > generic personalization
Combos par tone (utilisés par CCSW)
- direct_sec → PVC + Pattern Interrupt + Close direct
- consultatif_pro → Problem-Centric + SPIN + Close consultatif
- curiosite_doux → Permission-Based Braun + Curiosity gap + Mr. Miyagi
- referral_chaleureux → Heard the name (Farrokh) + Social proof + Close chaleureux
Re-bake périodique
Si nouvelles sources majeures sortent (ex: nouveau livre Cegelski, gros pivot Josh Braun) → rerunner le pipeline :
- Mettre à jour les prompts des 5 sous-agents
- Relancer en parallèle via Agent tool
- Régénérer
output/cold-call-expertise.md - Updater le
SYSTEM_PROMPTdansscript-prompt.ts - Bumper la version SKILL (v1.1, v1.2…)
Tags
#leadgen #cold-call #outbound #sales #b2b-services #live
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.

