# Zernio Comment To Dm

> >-

- **Type:** Skill
- **Install:** `agentstack add skill-enriquemarq1-zernio-library-skills-zernio-comment-to-dm`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Enriquemarq1](https://agentstack.voostack.com/s/enriquemarq1)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Enriquemarq1](https://github.com/Enriquemarq1)
- **Source:** https://github.com/Enriquemarq1/zernio-library-skills/tree/main/.claude/skills/zernio-comment-to-dm

## Install

```sh
agentstack add skill-enriquemarq1-zernio-library-skills-zernio-comment-to-dm
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# zernio-comment-to-dm

Turn a comment section into captured leads. When someone comments your **keyword** on a
post, Zernio auto-DMs them — and this skill lets you set that up just by *asking Claude*,
for any post or keyword, in seconds. No dashboard clicking, no cloning workflows.

> **The skill informs; the agent acts.** This file gives Claude the Zernio API contract +
> the recipe. Claude executes with `curl` (or the user's HTTP tool). Always confirm with the
> user before creating/activating an automation (it goes live on a real audience).

## What you can ask
- "When someone comments **GUIDE** on my latest post, DM them my free template link."
- "New automation: post ``, keyword **PRICING**, DM the pricing + ask if they want a call."
- "Pause / update / delete the **GUIDE** automation."
- "Walk a short sequence: DM them the resource, then if they reply, ask for their email."

## What Claude needs (ask the user once, then remember in-session)
1. **ZERNIO_API_KEY** — `Authorization: Bearer ` (zernio.com → Settings → API keys).
2. **profileId** + **accountId** — the Zernio profile + connected IG/FB account
   (`GET /profiles`, `GET /accounts` if unknown).
3. **platformPostId** — the post the automation watches (the IG/FB post ID).
4. **keyword(s)**, the **DM message**, optional **public comment reply**.

## The recipe (Claude follows this)

### 1. Create the comment automation (the core — native, one call)
```bash
curl -s -X POST "https://zernio.com/api/v1/automations" \
  -H "Authorization: Bearer $ZERNIO_API_KEY" -H "Content-Type: application/json" \
  -d '{
    "profileId": "",
    "accountId": "",
    "platformPostId": "",
    "name": "GUIDE — free template",
    "keywords": "GUIDE",
    "dmMessage": "Hey! Here is the free template you asked for 👇 [link]. Want me to walk you through it?",
    "commentReply": "Check your DMs 📩",
    "isActive": true
  }'
```
Returns the automation id. From now on, every comment matching the keyword auto-DMs.

### 2. Reuse for a NEW post / keyword (the whole point)
Just change `platformPostId`, `keywords`, `name`, `dmMessage` and POST again. Claude can do
this from one sentence — "same thing but keyword PRICING on post , DM the pricing." No
cloning, no dashboard. Manage them: `GET /automations`, `PUT /automations/{id}` (pause via
`isActive:false`), `DELETE /automations/{id}`, logs via `GET /automations/{id}/logs?status=sent`.

### 3. The "sequence" (follow-up DMs — Claude-orchestrated)
Zernio's automation sends ONE DM per matching comment (no native multi-step sequence). For a
real sequence, the host app/agent watches the conversation and sends follow-ups:
- New replies arrive via the inbox (`GET /inbox/conversations`, `GET /inbox/messages/{conversationId}`).
- Send the next step: `POST /inbox/send` `{ "conversationId", "accountId", "message" }`.
- e.g. step 1 = the resource (the automation's dmMessage), step 2 (after they reply) = "great
  — what's the best email to send the full thing to?", step 3 = deliver + confirm.
Claude composes each step in the creator's voice; keep it short, one ask at a time.

## Guardrails
- **Confirm before going live.** Show the user the keyword + DM + reply, get a yes, then POST.
- **Never print the API key.** It lives in env/the user's secret store.
- **One keyword per automation** (keeps it intentional); create separate automations for
  separate keywords/posts.
- **Voice:** warm, direct, human, no spam. The DM should sound like the creator.

## Reference
- `reference/zernio-automations-api.md` — full endpoint contract (verified from docs.zernio.com).
- `templates/automation.json` — copy-paste body for a new comment automation.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Enriquemarq1](https://github.com/Enriquemarq1)
- **Source:** [Enriquemarq1/zernio-library-skills](https://github.com/Enriquemarq1/zernio-library-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** yes
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-enriquemarq1-zernio-library-skills-zernio-comment-to-dm
- Seller: https://agentstack.voostack.com/s/enriquemarq1
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.