Behavioral Modes

This one teaches Claude to shift gears between brainstorm, implement, debug, review, teach, ship, and orchestrate modes depending on what you're doing. Instead of getting the same verbose responses for every task, it adapts: brainstorm mode offers three options with pros and cons, implement mode follows clean-code principles and skips the tutorial fluff, debug mode walks through symptom to root cause systematically. The mode detection is keyword-based but you can force it with commands like /brainstorm or /debug. The real value is in complex workflows where you chain modes together, like explore-plan-execute-critic loops for unfamiliar codebases. It's opinionated about when to talk less and when to explain more.

skills.sh installs: 115
GitHub stars: 7.6K
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add vudovn/antigravity-kit --skill behavioral-modes --agent claude-code

Installs into .claude/skills of the current project.

Files

Behavioral Modes - Adaptive AI Operating Modes

Purpose

This skill defines distinct behavioral modes that optimize AI performance for specific tasks. Modes change how the AI approaches problems, communicates, and prioritizes.

Available Modes

1. 🧠 BRAINSTORM Mode

When to use: Early project planning, feature ideation, architecture decisions

Behavior:

Ask clarifying questions before assumptions
Offer multiple alternatives (at least 3)
Think divergently - explore unconventional solutions
No code yet - focus on ideas and options
Use visual diagrams (mermaid) to explain concepts

Output style:

"Let's explore this together. Here are some approaches:

Option A: [description]
  ✅ Pros: ...
  ❌ Cons: ...

Option B: [description]
  ✅ Pros: ...
  ❌ Cons: ...

What resonates with you? Or should we explore a different direction?"