behavioral-modes

Detect task cues and switch between brainstorming, implementing, debugging, reviewing, teaching, and shipping modes.

8.1k|1.5k|Updated Jan 14, 2026
One-click install
npx skills add https://github.com/vudovn/antigravity-kit --skill behavioral-modes-vudovn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: behavioral-modes
Source: https://github.com/vudovn/antigravity-kit/tree/main/.agent/skills/behavioral-modes
Command: npx skills add https://github.com/vudovn/antigravity-kit --skill behavioral-modes-vudovn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill defines a library of adaptive AI operating modes to tailor responses and actions to task type. Modes include brainstorming, implementing, debugging, reviewing, teaching, shipping, and orchestrating to optimize how the AI approaches a given task.

Core Features & Use Cases

  • Mode library: Brainstorm, Implement, Debug, Review, Teach, Ship, and Orchestrate modes cover common AI tasks and decision-making styles.
  • Automatic mode switching: The system detects task cues and switches to the most suitable mode to improve efficiency and alignment.
  • Output guidance per mode: Each mode prescribes specific output formats, level of detail, and interaction patterns to fit the task.

Quick Start

Activate BRAINSTORM mode for a new feature idea, or request IMPLEMENT mode to start coding with concise output.

Frequently Asked Questions about behavioral-modes

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

FAQPage Schema
How do I control AI behavior for different tasks like debugging or brainstorming?

You can control AI behavior by applying adaptive operating modes that enforce specific output guidelines, detection logic, and switching rules tailored for tasks like debugging or brainstorming.

What are adaptive AI modes and how do they optimize workflow automation?

Adaptive AI modes are a library of operating behaviors—including Brainstorm, Implement, Debug, Review, Teach, Ship, and Orchestrate—that optimize workflow automation by prescribing specific output formats and interaction patterns per task.

Can I automatically switch AI output formats based on task cues without external dependencies?

Yes, the system detects task cues and automatically switches to the most suitable mode to enforce mode-specific output formats and interaction patterns without requiring any external dependencies.

Does multi-agent AI workflow support specific modes for code review and implementation?

Yes, multi-agent AI workflows support specific modes for code review and implementation, utilizing the Review and Implement modes to prescribe concise output formats and tailored interaction patterns for software engineering tasks.

What is the best way to guide AI output for teaching versus shipping tasks?

The best way to guide AI output is by switching between Teach mode, which adjusts interaction patterns for instructional detail, and Ship mode, which enforces guidelines optimized for final delivery and deployment.