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

Debrief

ASecurity

Post-conversation processor. Takes meeting notes (name, company, context) and creates CRM records, drafts follow-up email, logs everything. Use after any meeting, call, coffee, or event encounter. Triggers on "met someone", "just had a call", "debrief", "meeting notes".

7 stars
0 votes
0 copies
0 views
Added 9/20/2026
ai-agentsexpressdatabase

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add unempyd/revenueos --skill debrief --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Debrief?

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

Security grade badge for Debrief
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/unempyd-debrief/badge)](https://www.skillsdirectory.com/skills/unempyd-debrief)

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

Download Zip
Files
SKILL.md
---
name: debrief
description: Post-conversation processor. Takes meeting notes (name, company, context) and creates CRM records, drafts follow-up email, logs everything. Use after any meeting, call, coffee, or event encounter. Triggers on "met someone", "just had a call", "debrief", "meeting notes".
---

# Debrief -- ACTIVATED

You are processing a conversation the user just had. Turn it into a qualified pipeline entry with follow-up.

---

## Process

### 1. Extract Info from Input

Parse whatever is shared. Minimum: who, what company, where they met.
Ask for missing critical info (don't guess):
- Name
- Company (if not provided, research from name)
- What was discussed / their situation

### 2. Enrich

- Search your contact database for existing records
- If not found: web search for company + person

### 3. Qualify

Score ICP fit:
- **Primary ICP** -- B2B service business, $500K-$5M revenue, 5-50 employees
- **Secondary ICP** -- Adjacent fit (right size but different industry, or right industry but different size)
- **Not a fit** -- Disqualification criteria met

Recommend pipeline tier based on company size and expressed needs.

### 4. Create CRM Records

Create or update:
- **Contact:** name, email (if available), company, title, source, notes
- **Company:** name, domain, industry, size estimate
- **Deal:** stage, estimated value, source, conversation notes
- Link all three records

### 5. Draft Follow-Up

Generate:
- **Email** -- personalized to their specific pain/interest. Reference something specific they said.
- **LinkedIn connection request** -- shorter, warmer variant
- Include one clear next step

### 6. Log

Record to your logging system:
```
### [Debrief]
- Met [Name] ([Company]) at [Place]
- ICP fit: [fit level] -- [reason]
- CRM: contact + company + deal created
- Follow-up: drafted, pending review
- Next step: [what was agreed]
```

---

## Output Format

Present:

```
DEBRIEF COMPLETE

CONTACT: [Name] -- [Title] -- [Company]
ICP FIT: [level] [one-line reason]
TIER: [tier]

CRM: Contact created | Company created | Deal created ($[X]/mo est.)

FOLLOW-UP EMAIL:
Subject: [subject]

[email body]

LINKEDIN MESSAGE:
[shorter message]

NEXT STEP: [what was discussed or recommended]
```

---

## Rules

- Never send anything automatically -- always show the sender first
- If email address isn't available, flag it and draft LinkedIn-only follow-up
- If it's clearly not a fit, still create the contact (tagged "not ICP") but skip deal
- For high-value opportunities, flag prominently
- Always be specific in follow-ups -- reference what they actually said

Attribution

unempydunempyd
View sourceMore from unempyd →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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.

3351 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 →