Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Follow Up Closing 20 Videos

ASecurity

Writes sales follow-ups and closing next steps using the rules repeated most often across the 20 most-watched videos on the topic, weighting each rule by how many of those videos say it, and flags any expert disagreements to A/B test. Use when the user says "write my follow-up", "the prospect went quiet", "how do I close this deal", "what do I send after the sales call", "help me book the next meeting", or "they said they need to think about it".

6 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgoaws

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add ToolMonsters/gtm-skills-from-youtube --skill follow-up-closing-20-videos --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Follow Up Closing 20 Videos?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Follow Up Closing 20 Videos
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/toolmonsters-follow-up-closing-20-videos/badge)](https://www.skillsdirectory.com/skills/toolmonsters-follow-up-closing-20-videos)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: follow-up-closing-20-videos
description: Writes sales follow-ups and closing next steps using the rules repeated most often across the 20 most-watched videos on the topic, weighting each rule by how many of those videos say it, and flags any expert disagreements to A/B test. Use when the user says "write my follow-up", "the prospect went quiet", "how do I close this deal", "what do I send after the sales call", "help me book the next meeting", or "they said they need to think about it".
author: Yonathan Cohen (Tool Monsters)
version: 1.0.0
updated: 2026-09-14
license: MIT
---

# /follow-up-closing

This skill comes from the transcripts of the 20 most-watched videos on following up after sales calls and closing deals, published in the last 6 months (since 2026-03-14). Together they have 55,981 views and 96,926 words. From them, 407 pieces of advice were extracted, and 379 were kept because their verbatim quote was found in a transcript. Those pieces of advice fall into 211 distinct themes. The number next to each rule is how many of the 20 videos say it. Sources are in sources.md.

The most repeated rule reached 7 of 20. Treat the weights as odds, not laws.

## Inputs
1. The call notes or transcript, including the exact pain points and current approach the prospect described.
2. Where the deal stands: date of last contact, how many follow-ups have been sent, and whether a next meeting is already booked.
3. The stakeholders you know by name and role, and who has not been involved yet.
4. What you are offering, including price and terms, and what you want this message or call to achieve.

Do not invent pain points, quotes, names, roles, budgets, prices, or deadlines the user has not provided.

## The rules, by weight
### Strong (7 of 20)
- **Avoid generic, repetitive follow-ups; personalize every message.** (7/20) Drop "just circling back" and "just checking in." Refer to the exact pain points the prospect shared on the call.

### Solid (4 of 20)
- **Diagnose pain and current approach before pitching.** (4/20) Ask: "How are you handling things today without those capabilities?"
- **Uncover and challenge the real objection behind stalls.** (4/20) Ask: "Is this because you don't have the budget, or because you don't see the value in what we do?"
- **Book the next meeting live on the call.** (4/20) Book a meeting from a meeting. In the last third of the call, ask: "How does next Tuesday look at this exact same time?"

### Mentioned (3 of 20)
Use pattern-interrupt messages to re-engage prospects · Send a takeaway text asking if they are still open or if you should close the file · Always ask for the sale or next step on every call · Multi-thread with multiple stakeholders early · Send follow-ups and proposals within minutes of meetings (5 to 10 minutes, not 2 to 3 days) · Keep following up persistently, even after rejection

## Where the experts disagree: do not pick, test
The data showed no disagreements among the 20 videos, so no A/B test is assigned by default.

## Steps
1. Read the call notes. List the prospect's pain points and current approach in their own words. If either is missing, recommend asking the diagnosis question on the next call before pitching again.
2. Decide the situation: right after a call, a stall or objection, or a prospect who has gone quiet.
3. Right after a call: draft the follow-up or proposal to send within 5 to 10 minutes. Reference the specific pains, confirm the next meeting if one was booked, and propose a specific day and time if one was not.
4. Stall or objection: write one question that separates the real objection (for example, budget versus value) and include a clear ask for the next step.
5. Gone quiet: count the follow-ups already sent. If the prospect has not replied, write a personalized follow-up or a pattern-interrupt message. When it fits, offer a takeaway text asking if they are still open or if you should close the file.
6. Check the stakeholder list. If only one contact is involved, suggest bringing in another named role, using only names and roles the user has provided.
7. Review every draft against the Strong rule. Remove any generic line that could be sent to any prospect.
8. Finish by listing each rule applied with its weight (for example, "Personalize every message, 7/20"). Then state which choice is being A/B tested. If the user did not name one, say that no disagreement was found in the data, so no test is running.

## Never
- Never claim close rates, reply rates, or other results the user has not measured.
- Never invent facts about the prospect or customer, including pains, quotes, stakeholders, budget, or timing.
- Never send a follow-up that only says "just checking in" or "just circling back" with no reference to the prospect's situation.

Attribution

ToolMonstersToolMonsters
View sourceMore from ToolMonsters →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →