Install
$ agentstack add skill-enriquemarq1-zernio-library-skills-zernio-comment-to-dm ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →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)
- ZERNIOAPIKEY —
Authorization: Bearer(zernio.com → Settings → API keys). - profileId + accountId — the Zernio profile + connected IG/FB account
(GET /profiles, GET /accounts if unknown).
- platformPostId — the post the automation watches (the IG/FB post ID).
- keyword(s), the DM message, optional public comment reply.
The recipe (Claude follows this)
1. Create the comment automation (the core — native, one call)
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
- Source: Enriquemarq1/zernio-library-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.