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

Sales Follow Up

ASecurity

RevenueOS Sales Follow-up — draft first-touch cold emails for newly discovered prospects from the business's own canon, and process inbound replies, bounces and STOP requests. Use when the user says \"draft follow-up emails\", \"write outreach for these leads\", \"check for replies\", \"who unsubscribed\", or asks RevenueOS to send a cold email — sending always requires an explicit approval step from the human.

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

Works with

climcp

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add unempyd/revenueos --skill sales-follow-up --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Sales Follow Up?

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

Security grade badge for Sales Follow Up
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/unempyd-sales-follow-up/badge)](https://www.skillsdirectory.com/skills/unempyd-sales-follow-up)

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

Download Zip
Files
SKILL.md
---
name: revenueos-sales-follow-up
description: "RevenueOS Sales Follow-up — draft first-touch cold emails for newly discovered prospects from the business's own canon, and process inbound replies, bounces and STOP requests. Use when the user says \"draft follow-up emails\", \"write outreach for these leads\", \"check for replies\", \"who unsubscribed\", or asks RevenueOS to send a cold email — sending always requires an explicit approval step from the human."
metadata:
  version: 0.1.0
  vendor: RevenueOS
---

# RevenueOS Sales Follow-up

RevenueOS Sales Follow-up drafts deterministic, personalised first-touch emails for
prospects found by RevenueOS Lead Discovery, and reads the inbox to classify replies,
bounces and unsubscribe requests. **Every send requires a human approval step — this
capability never sends on its own initiative.**

## When to use this

- New prospects exist (from RevenueOS Lead Discovery) and need a first-touch draft.
- The user wants to check for replies, bounces, or STOP requests on a sending mailbox.
- The user explicitly asks to send an approved draft.

## How to run it

CLI:

```bash
revenueos run outreach          # draft follow_up actions for undrafted prospects
revenueos run inbox             # classify replies / bounces / STOPs against sent mail
revenueos today                 # review drafts awaiting approval
revenueos approve <id>          # approve one draft
revenueos execute <id>          # send it (only after approve)
```

MCP tool:

- `revenueos_draft_followups()` — drafts first-touch emails for qualified prospects; never
  sends. Each draft becomes a `follow_up` action.
- `revenueos_approve(action_id)` then `revenueos_execute(action_id)` — the only path that
  sends an email, and only for an action already approved.
- `revenueos_today()` / `revenueos_results()` — review drafts / delivery and reply outcomes.

## Inputs

No file upload — drafts are built from the business's own canon (offer, differentiators,
pain points, tone) plus each lead's qualification `reason`. Sending needs `smtp.host` /
`sender.email` in `revenueos.yaml` and `SMTP_PASSWORD` in the environment; reading replies
needs `imap.host` and `IMAP_PASSWORD` (or `.eml` files dropped in `data/exports/inbox/`).

## What it produces

One `follow_up` action per drafted email, holding the subject and body chosen by a
deterministic hook/subject split (personalised further when an LLM credential is present).
Approving and executing a `follow_up` action sends the email (recorded immutably) and
inbox processing later updates it with `replied` / `bounced` outcomes.

## Approval rule — the safe default

**`REVENUEOS_DRY_RUN=1` is the Community default**: with it set, "sending" writes the
rendered email to `data/outputs/` instead of using real SMTP, so the whole loop can be
exercised with zero risk of contacting a real prospect. Drafts always sit as `pending`
actions; nothing sends until a human calls `revenueos approve` and then `revenueos execute`
(or the equivalent MCP tools) on that specific action. A daily send cap and a suppression
list (STOP replies, bounces) are enforced at execute time regardless of dry-run.

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.

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 →