magic-mouth

Automate trigger-based messaging with payload templates and suppression rules.

105|13|Updated Mar 9, 2026

Search Tags:#automation #messaging #slack #webhook #escalation #trigger

One-click install

npx skills add https://github.com/Hmbown/Wizards-of-the-Ghosts --skill magic-mouth

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: magic-mouth
Source: https://github.com/Hmbown/Wizards-of-the-Ghosts/tree/main/generated/hermes/messaging-and-coordination/magic-mouth
Command: npx skills add https://github.com/Hmbown/Wizards-of-the-Ghosts --skill magic-mouth

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Magic Mouth is trigger → message. The entire craft is specifying the trigger boundary, the message payload, and the suppression/escalation rules. It is NOT: - One-time messages: "Send a Slack message now saying X" (no trigger, no automation)

Full chatbots: "Build a conversational AI that understands context and handles open-ended questions" (requires NLU, dialogue management)
Monitoring dashboards: "Set up Grafana with real-time graphs and trend analysis" (visualization, not message routing)
Silent traps/wards: "Revert changes silently and log who tried" (defensive code manipulation, not messaging)
Encryption: "Encrypt a message so only the recipient can read it" (cryptography, not event-driven delivery)
Multimedia presentations: "Play a 20-slide deck with animations and narration" (media playback, not conditional messaging) In this grimoire, Magic Mouth is treated as a metaphorical spell with a shipping-now delivery profile. Canonical reference input: Magic Mouth (spell).

When To Use

Use this spell when the user describes an event-driven message automation: a specific trigger condition (X) should cause a specific message or notification (Y) to be sent without manual intervention.
Look for these patterns in the request:
"When [condition], send/post/notify [message/recipient]"
"Set up an autoresponder for [scenario]"
"Create an alert rule for [metric/event]"
"Design a webhook handler that posts to [channel] when [event]"
Mentions of triggers, fire conditions, suppression rules, rate limits, or escalation stages
Explicit no-fire cases ("don't fire if...", "suppress duplicates for...", "only once per...")

Prerequisites

Environment variables available to Hermes: SLACK_TOKEN.
Primary credential or token: SLACK_TOKEN.
Binaries on PATH: curl.

Setup

Confirm the required environment variables are available inside the active Hermes runtime, not just in a shell profile.
Verify the required binaries resolve on PATH before you rely on them in a procedure.
Choose a non-production or low-risk target first if the skill can page, unlock, alert, or touch a live integration.

Procedure

Restate the target, the success condition, and any no-touch boundaries before taking action.
Extract the trigger: Identify the exact condition that fires the message (metric threshold, event type, time window, keyword match). Note any compound conditions or timing delays ("wait 5 minutes before firing").
Specify the payload: List every variable in the message (who, what, where, severity, links). Write the response template with placeholders.
Define boundaries: Document no-fire cases, rate limits, suppression windows, and escalation stages. Explicitly state what happens on repeated triggers.
Return the spec: Produce a trigger-response specification with test cases covering: nominal fire, no-fire, repeated-trigger suppression, and escalation progression. If Slack or a messaging API is available, include the concrete API call or workflow configuration.
Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.

Deliverables

A trigger-response specification or message template.
Example payloads covering nominal and edge-case inputs.
Notes on rate limits, suppression, escalation, and logging.

Pitfalls / Guardrails

Keep the metaphor anchored to a real mechanism instead of drifting into lore.
Do not automate messages requiring human judgment, empathy, or legal review
Protect against loops, spam, and easily-spoofed trigger conditions
Always include a suppression mechanism for repeated triggers
Do not rely on a live integration until credentials, target scope, and rollback expectations are verified.

Verification

Check that the result includes every deliverable promised above.
Check that confirmed facts, assumptions, and inferences are visibly separated.
Check that the metaphor still maps cleanly to a real operational mechanism.
Check the required environment variables and binaries in the active Hermes runtime before trusting the procedure on a live target.

Example Invocation

/magic-mouth turn this trigger into a reliable automated response and show me the exact fire conditions

Quick Start

Configure a trigger-to-message workflow by specifying the event, the payload, and escalation rules.

Frequently Asked Questions about magic-mouth

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I set up event-driven Slack notifications for automated triggers?▼

Event-driven Slack notifications are set up by binding a specific trigger condition to an outgoing message payload. This automation requires defining the exact fire condition, payload template, and suppression rules to route alerts without manual intervention.

What is a trigger-to-message specification for webhook automation?▼

A trigger-to-message specification maps an event condition to a notification payload template. It includes exact fire conditions, required credentials like SLACK_TOKEN, rate limits, suppression windows, and escalation paths for reliable webhook automation.

How do I prevent duplicate automated messages when a trigger fires repeatedly?▼

To prevent duplicate automated messages, you must define suppression rules and rate limits within your trigger boundary. The specification requires explicit no-fire cases and suppression windows to control what happens on repeated triggers.

Do I need a SLACK_TOKEN to automate trigger-based messaging?▼

Yes, a SLACK_TOKEN environment variable is required to automate trigger-based messaging. You must confirm this credential is available in the active runtime and verify curl is on your PATH before executing the workflow.

Can I build a conversational AI chatbot using trigger-based messaging?▼

No, trigger-based messaging is not for building conversational AI chatbots. It handles event-driven notification workflows with clear boundaries and escalation paths, whereas chatbots require natural language understanding and dialogue management.

How do I configure escalation paths for automated alert rules?▼

Escalation paths for automated alert rules are configured by defining boundary conditions and escalation stages in the message specification. You must document what happens on repeated triggers and include test cases covering escalation progression.