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

Dm Keyword Automation

ASecurity

Use when automating comment keyword to DM flows with UTM tracking and qualification scripts as a self-hosted ManyChat replacement. Triggers on \"keyword DM\", \"comment automation\", \"manychat replacement\", \"DM funnel\". Non-triggers: paid ads account operation (use ads-operator). Outcome: keyword map plus DM scripts plus UTM log plus qualification flow.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgoapi

Works with

cliapi

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill dm-keyword-automation --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Dm Keyword Automation?

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

Security grade badge for Dm Keyword Automation
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-dm-keyword-automation/badge)](https://www.skillsdirectory.com/skills/majinmagros-dm-keyword-automation)

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

Download Zip
Files
SKILL.md
---
name: dm-keyword-automation
description: "Use when automating comment keyword to DM flows with UTM tracking and qualification scripts as a self-hosted ManyChat replacement. Triggers on \"keyword DM\", \"comment automation\", \"manychat replacement\", \"DM funnel\". Non-triggers: paid ads account operation (use ads-operator). Outcome: keyword map plus DM scripts plus UTM log plus qualification flow."
metadata:
  origin: ECC
---

# DM Keyword Automation

Replace hosted comment-to-DM tools (ManyChat-style) with a self-hosted loop:
public comment with keyword -> auto DM -> qualification script -> tracked link.

## When To Activate

- The user wants "comment X and I will send you Y" automation.
- The user wants to replace ManyChat with owned infrastructure.
- A funnel needs per-keyword DM scripts plus UTM tracking.
- Qualification must happen inside the DM before a human takes over.

## Workflow

### 1. Map keywords to assets

- List each trigger keyword and the asset it promises.
- One keyword -> one DM script -> one destination link. No shared links.
- Record the map in a table: keyword | script file | link | owner.

### 2. Build the DM script

- Opening line delivers the promised asset, no small talk first.
- Follow with at most 3 qualification questions, one per message.
- End with a single call to action (book, buy, reply).
- Keep each message under 45 words; mobile-first line breaks.

### 3. Tag every link with UTM

- Format: `?utm_source=<platform>&utm_medium=dm&utm_campaign=<keyword>`.
- One campaign value per keyword so reply rate maps to source post.
- Log sent links per day: date | keyword | sends | replies | clicks.

### 4. Wire the trigger

- Connect the platform messaging API or an automation bridge.
- Match comments case-insensitively; strip punctuation before matching.
- Rate-limit sends per account per hour; queue overflow for next window.
- Log every send with timestamp for audit.

### 5. Pixel and conversion check

- Fire the pixel event on link click and on the goal page.
- Compare DM clicks vs goal completions weekly per keyword.
- Kill keywords with clicks but zero completions after 200 sends.

### 6. Human handoff

- Route qualified replies to a human closer with full transcript.
- Unqualified replies get a polite exit plus one fallback asset.
- Never loop questions the user already answered.

## Anti-Patterns

- One generic DM script for all keywords -> untraceable funnel.
- Shared links without UTM -> source attribution lost.
- Instant send with no rate limit -> account flag or ban.
- Pixel on click but not on goal -> vanity metrics.

## Exemplo

```text
Post: "comenta EBOOK que te mando" → keyword EBOOK → DM com asset + 3 perguntas
Link: ?utm_source=instagram&utm_medium=dm&utm_campaign=ebook (1 por keyword)
200 envios, 60 cliques, 0 conclusões → kill keyword; qualificadas → closer humano
```

## Playbook Instagram (leva YouTube rodada 8)

Para DM de Instagram (estilo ManyChat): 1 keyword por post/carrossel + CTA no criativo + mini-chat de entrega na DM. Teste com conta fria antes de escalar. Para o funil completo long→shorts→DM, orquestre com epurpose-shorts-dm-funnel.

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
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 →