agentleFS
njpattennjpatten/claude-skills/pre-call-prep/SKILL.md

pre-call-prep

Skill0 starsChanged 2 months agoMITView on GitHub

Researches prospects and generates tailored context, questions, and call strategies for upcoming discovery and sales calls. Triggers on 'I have a call with', 'prep me for', 'research this prospect', 'help me prepare for my call', or 'what should I ask'.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. legioncodeinc/littlebird-skills★ 8same name
    2. stephenrogan/csm-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository6 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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
  1. Distinctive:

    Never walk into a call cold again.

    line 8
  2. Distinctive:

    Use web search to find:

    line 30
  3. Distinctive:

    If you don't know the industry, provide a 2-minute crash course:

    line 56
  4. Distinctive:

    If all you have is a name and gmail:

    line 170
  5. Distinctive:

    Search LinkedIn for the name

    line 172
  6. Distinctive:

    Search name + any context (city, industry keywords, how they found you)

    line 173
  7. Distinctive:

    If found, proceed normally

    line 174
  8. Distinctive:

    If not found, output a pre-qualification email template to send before the call

    line 175

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Pre-Call Prep

Never walk into a call cold again. This skill researches the prospect, builds context, and generates questions so your brain has time to think BEFORE the call — not during it.

The Problem This Solves

You can't improvise smart questions in real-time while also trying to understand a new industry, person, and company from scratch. This skill front-loads that thinking.

Inputs Needed

Provide whatever you have:

  • Name
  • Company/organization
  • Email domain
  • LinkedIn URL
  • Industry/vertical
  • Any booking form answers or context on how they found you

Minimum viable: Name + anything else (company, email domain, LinkedIn, etc.)

Workflow

Step 1: Research the Person

Use web search to find:

  • LinkedIn profile → role, tenure, background
  • Company website → what they do, size, industry
  • Recent news → funding, growth, challenges
  • Their content → posts, articles, interviews (reveals how they think)

Output a brief:

## Who You're Talking To

**Name:** [Name]
**Role:** [Title] at [Company]
**Company:** [What they do in 1 sentence]
**Size:** [Employees/revenue if findable]
**Industry:** [Vertical]
**Background:** [Relevant career history]
**How they found you:** [Source]

## Context Clues
- [Anything notable from research]
- [Recent news, posts, or signals]
- [Why they might be reaching out now]

Step 2: Research Their Industry (If Unfamiliar)

If you don't know the industry, provide a 2-minute crash course:

  • What does this industry actually do?
  • What are the top 3 pain points for companies like this?
  • What does AI automation typically solve in this space?
  • What jargon should you know?
  • Who are the key players/competitors?

Keep it short. Just enough to not sound ignorant.

Step 3: Hypothesize Their Problem

Based on research, guess why they're reaching out:

  • What pain are they likely experiencing?
  • What have companies like this tried before?
  • What's the typical budget range for solutions?
  • What's the likely decision-making process?

Frame as hypotheses to validate, not assumptions to act on.

Step 4: Generate 5 Questions

Provide 5 specific questions tailored to THIS prospect, not generic.

## Your 5 Questions

1. [Opening question to get them talking about their problem]

2. [Pain quantification question specific to their industry]

3. [Question about what they've tried / why now]

4. [Budget/timeline/decision process question]

5. [Consequence question — what happens if they don't solve this]

Make them copy-paste ready. Print or pull up on a second screen before the call.

Step 5: Call Reminders

Always end with:

## Call Reminders

**Talk ratio target:** <35% you
**Your pivot phrase:** "Let me pause — I want to make sure I understand your situation. Tell me more about [X]."
**Goal:** Quantify their pain in dollars or hours. No number = no proper pricing later.
**End with:** Specific next step with a date, not "let's stay in touch."

Output Format

# Pre-Call Prep: [Name] @ [Company]

**Call Date:** [If known]
**How They Found You:** [Source]

---

## Who You're Talking To

**Name:** 
**Role:** 
**Company:** 
**Industry:** 
**Background:** 

## Context Clues
- [Notable items from research]

---

## Industry Crash Course (if needed)

[2-3 paragraphs max on the industry, pain points, jargon]

---

## Hypotheses to Validate

1. They're probably struggling with [X]
2. They've likely tried [Y] before
3. Budget is probably in the [$X-$Y] range
4. Decision maker is probably [role]

---

## Your 5 Questions

1. 

2. 

3. 

4. 

5. 

---

## Call Reminders

**Talk ratio target:** <35% you
**Your pivot phrase:** "Let me pause — I want to make sure I understand your situation. Tell me more about [X]."
**Goal:** Quantify their pain in dollars or hours.
**End with:** Specific next step with a date.

When There's Almost No Info

If all you have is a name and gmail:

  1. Search LinkedIn for the name
  2. Search name + any context (city, industry keywords, how they found you)
  3. If found, proceed normally
  4. If not found, output a pre-qualification email template to send before the call
## ⚠️ Low-Info Prospect

I couldn't find enough to prep properly.

**Recommendation:** Send this before the call:

---

Subject: Quick context before our call

Hey [Name],

Looking forward to chatting on [date]. So I can make our time valuable, could you share:

1. What's your company/organization and what do you do?
2. What problem are you hoping to solve?
3. What's your timeline?

Just a few sentences is fine.

Talk soon,
[Your name]

---

**If they don't respond:** Treat as low-priority. Casual 15-min call max, not full discovery.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.