agentsclimarketplace
Sign in

Cold call

Skill manusco/resonance/.agents/skills/sales/cold-call

Generates a structured B2B cold call script using a disarming, permission-based 6-part framework. Use when asked to write a cold call script, how to open a call, how to handle phone objections, or to plan a cold calling sales outbound campaign.From its SKILL.md

Install
npx -y skills add manusco/resonance --skill cold-call

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

3.3 KB, 689 tokens by cl100k_base, as published. Nobody here has run it

/resonance-sales-cold-call: structure B2B cold call execution

Role: resonance-sales Input: Target description (seniority, role, company size, trigger event) + Sender's company offer. Output: A structured, speakable 6-part cold call script. Definition of Done: A speakable cold call script is generated containing Opener, Permission Framing, 3 Pain Hypotheses, Discovery, Mini Proof, and Meeting Ask. No AI slop or em dashes present. Passed the validator.

Prerequisites (fail fast)

  • Target persona's seniority and industry is identified (price-seniority mapped).
  • Product value proposition is climb-ladder mapped to an outcome (not just features).

Algorithm

Copy this checklist and tick items as you go.

  1. Opener: Draft a disarming, honest opener that states your name, company, and a pattern interrupt without asking "is this a good time?" or saying "how are you today?". → verify: hook is under 15 words.
  2. Permission Framing: Draft a permission request that gives the prospect explicit control and a clear exit to reduce immediate defensiveness. → verify: exit condition is stated clearly.
  3. 3 Pain Hypotheses: Formulate three specific pain hypotheses (functional, organizational, strategic) that lets the prospect self-diagnose their bottlenecks. → verify: each hypothesis is under 15 words.
  4. Discovery Questions: Design a single consequence-focused question that gets the prospect talking about the daily impact of their selected pain. → verify: only 1 main question is posed.
  5. Mini Proof: Formulate a brief, credible proof point ("companies like...") that establishes authority without generic or fabricated metrics. → verify: is under 3 sentences.
  6. Meeting Ask: Create a direct meeting ask offering a binary choice of two specific days and times for a brief 15-minute call. → verify: meeting length is capped at 15-20 minutes.

Recovery

  • Prospect hangs up immediately → log as unreachable, do not re-dial same day.
  • Prospect asks to "send an email" → redirect to value check: "happy to, but to keep it relevant, which of those three issues I mentioned is closest to what you're dealing with?"
  • Tried to customize the script 3 times without a speakable flow → stop, run the 15-second read-aloud test, simplify vocabulary, escalate.

Operating Standard

Apply the Resonance operating standard from AGENTS.md (always loaded): the builder Voice and its banned-word list (no AI slop, no em dashes), Recommendation-First decisions (models recommend, the user decides), the Completion protocol (end with DONE / DONE_WITH_CONCERNS / BLOCKED / NEEDS_CONTEXT, backed by evidence, escalate after 3 failed tries), and the Ratchet (record durable learnings in the project memory, .resonance/02_memory.md, which loads at session start).

Model note (Claude): Strong native reasoning. Do not narrate "let me think step by step" or pad with chain-of-thought; think, then act. Prefer the dedicated file and search tools over shell. State assumptions briefly, then proceed.

What ships with it: 4 files

3.8 KB alongside SKILL.md

evals/

Gives 0 of the 12 instructions most sales audience skills give in 689 tokens

Counted across 401 of the 401 authors here whose files we hold, read 2026-08-07

  • Read product marketing context before asking questionsin 21 of 401, across 11 files
  • Acknowledge competitor strengths honestlyin 18 of 401, across 7 files
  • Start every page with a summaryin 15 of 401, across 4 files
  • Use a single, low-friction call to actionin 15 of 401, across 7 files
  • Create a single source of truth for each competitorin 14 of 401, across 3 files
  • Make each follow-up email add new valuein 11 of 401, across 5 files
  • Cut any sentence that does not drive a replyin 10 of 401, across 4 files
  • Tie personalization directly to the problemin 10 of 401, across 4 files
  • Write paragraph comparisons for each dimensionin 9 of 401, across 3 files
  • Link between related competitor pagesin 9 of 401, across 3 files
  • Keep subject lines short and lowercasein 9 of 401, across 3 files
  • Define ideal customer profile from top customersin 9 of 401, across 3 files

Said here and by no other author read

  • draft a disarming opener under 15 words
  • frame a permission request with a clear exit
  • formulate three pain hypotheses under 15 words
  • design one consequence-focused discovery question
  • formulate a brief proof point without fabricated metrics
  • create a binary meeting ask for a short call

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.