signal

Log, review, and generate content angles from enterprise AI signals.

Updated Feb 22, 2026
One-click install
npx skills add https://github.com/mentilead/growthOS --skill signal-mentilead
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: signal
Source: https://github.com/mentilead/growthOS/tree/main/skills/signal-monitor
Command: npx skills add https://github.com/mentilead/growthOS --skill signal-mentilead

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and scripts (resource) components.

What problem does it solve?

This Skill helps practitioners stay informed about the rapidly evolving enterprise AI landscape by systematically logging, classifying, and analyzing external signals, ensuring their personal experiments remain aligned with or informed by broader industry trends.

Core Features & Use Cases

  • Signal Logging: Quickly capture and classify signals from various sources (reports, announcements, conversations) with minimal friction.
  • Signal Review: Analyze logged signals over the past 60 days, grouped by classification (confirmation, contradiction, unknown), highlighting unused signals.
  • Content Angle Generation: Generate content ideas by bridging enterprise signals with personal experiment findings, identifying potential contradictions or confirmations.
  • Use Case: A developer working on an AI-powered customer service tool can log an industry report about a new LLM capability. The skill can then help them analyze if this new capability confirms their current approach, contradicts it, or presents a new opportunity for content creation.

Quick Start

Log a new signal by describing the signal, its source, and whether it confirms or contradicts your experiment.

Frequently Asked Questions about signal

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

FAQPage Schema
How do I track enterprise AI signals and connect them to my experiment findings?

To track enterprise AI signals, you log signals from sources like reports and announcements, classify them as confirmations or contradictions, and generate content angles bridging them with your personal experiment thesis.

What is the best way to generate content ideas from market intelligence and trend analysis?

Generating content ideas from market intelligence involves logging external industry trend signals, grouping them by confirmation or contradiction status, and identifying content opportunities that align with your ongoing experiment findings.

How do I systematically log and classify AI industry signals for content strategy?

You log AI industry signals by describing the signal, noting its source, and classifying it as a confirmation, contradiction, or unknown to maintain context for your content strategy and experiment thesis.

Can I review logged market intelligence signals to find unused content opportunities?

Yes, you can review logged market intelligence signals over a 60-day period, grouped by their classification status, which highlights unused signals and identifies potential content opportunities for your strategy.

Do I need prior experiment context to use AI signal tracking for content angle generation?

Yes, AI signal tracking requires reading status and memory files to maintain context and your experiment thesis, which is essential for accurately framing generated content angles against external industry trends.

Why does AI signal classification focus on confirmations and contradictions?

AI signal classification focuses on confirmations and contradictions to systematically bridge external enterprise trends with personal experiment findings, directly identifying whether new capabilities validate or challenge your current approach.