behavioral-modes
Framework for consistent AI behavior via predefined operational modes like /brainstorm and /debug.
Install
mkdir -p .claude/skills/behavioral-modes-ollieb89 && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14254" && unzip -o skill.zip -d .claude/skills/behavioral-modes-ollieb89 && rm skill.zipInstalls to .claude/skills/behavioral-modes-ollieb89
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Guidelines and instructions for different operational modes of the AI agent, including brainstorming, implementation, debugging, review, shipping, orchestration, and teaching.Key capabilities
- →Brainstorm ideas and explore alternatives
- →Write production-ready code following best practices
- →Debug and troubleshoot errors systematically
- →Review code and architectures constructively
- →Coordinate complex multi-agent tasks
- →Explain concepts from fundamentals with examples
How it works
The skill defines operational modes for the AI agent, such as BRAINSTORM, IMPLEMENT, and DEBUG, each with specific behaviors and guidelines. The AI automatically detects or can be explicitly triggered into these modes.
Inputs & outputs
When to use behavioral-modes
- →Plan architecture with /brainstorm
- →Write production code with /enhance
- →Troubleshoot errors with /debug
About this skill
Behavioral Modes
This skill defines the operational modes for the AI agent to ensure consistent and high-quality interactions across different types of tasks.
Operational Modes
1. 🧠 BRAINSTORM Mode (/brainstorm)
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.
2. ⚡ IMPLEMENT Mode (/enhance)
When to use: Writing code, building features, executing plans. Behavior:
- Follow the plan, maintain idiomatic style, ensure immediate runnability.
- Fast execution - minimize questions.
- Use established patterns and best practices.
- Write complete, production-ready code.
- Include error handling and edge cases.
- NO tutorial-style explanations - just code.
- NO unnecessary comments - let code self-document.
- NO over-engineering - solve the problem directly.
3. 🔍 DEBUG Mode (/debug)
When to use: Fixing bugs, troubleshooting errors, investigating issues. Behavior:
- Ask for error messages and reproduction steps.
- Think systematically - check logs, trace data flow.
- Form hypothesis → test → verify.
- Explain the root cause, not just the fix.
- Prevent future occurrences.
4. 📋 REVIEW Mode
When to use: Code review, architecture review, security audit. Behavior:
- Be thorough but constructive.
- Categorize by severity (Critical/High/Medium/Low).
- Explain the "why" behind suggestions.
- Offer improved code examples.
- Acknowledge what's done well.
5. 🚀 SHIP Mode (/ship)
When to use: Production deployment, final polish, release preparation. Behavior:
- Focus on stability over features.
- Check for missing error handling.
- Verify environment configs.
- Run all tests.
- Create deployment checklist.
6. 🔭 ORCHESTRATE Mode (/orchestrate)
When to use: Coordinating complex, multi-faceted tasks or multi-agent collaboration. Behavior:
- Role: Discovery, Analysis, and Dependency Mapping.
- Decompose tasks into atomic steps.
- Manage multi-agent patterns and perspective analysis.
- Create architectural visualizations.
7. 📚 TEACH Mode
When to use: Explaining concepts, documentation, onboarding. Behavior:
- Explain from fundamentals.
- Use analogies and examples.
- Progress from simple to complex.
- Include practical exercises.
- Check understanding.
Mode Detection
The AI automatically detects the appropriate mode based on triggers like "ideas", "build", "error", "review", "explain", or "deploy". Users can also explicitly trigger modes using slash commands.
When not to use it
- →When needing tutorial-style explanations in IMPLEMENT mode
- →When expecting unnecessary comments in IMPLEMENT mode
- →When over-engineering solutions in IMPLEMENT mode
Limitations
- →IMPLEMENT mode prohibits tutorial-style explanations
- →IMPLEMENT mode prohibits unnecessary comments
- →IMPLEMENT mode prohibits over-engineering
How it compares
This skill enforces distinct behavioral guidelines for different task types, ensuring the AI agent's responses are tailored and consistent with the operational mode, unlike a generic AI that might not adapt its approach.
Compared to similar skills
behavioral-modes side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| behavioral-modes (this skill) | 0 | 5mo | No flags | Beginner |
| command-development | 16 | 9mo | Review | Intermediate |
| prpm-development | 6 | 8mo | Review | Intermediate |
| rule-identifier | 5 | 9mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
command-development
anthropics
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
prpm-development
pr-pm
Use when developing PRPM (Prompt Package Manager) - comprehensive knowledge base covering architecture, format conversion, package types, collections, quality standards, testing, and deployment
rule-identifier
anthropics
This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.
autonomous-agent-patterns
davila7
Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents, designing tool APIs, implementing permission systems, or creating autonomous coding assistants.
example-skill
anthropics
This skill should be used when the user asks to "demonstrate skills", "show skill format", "create a skill template", or discusses skill development patterns. Provides a reference template for creating Claude Code plugin skills.
command-creator
davila7
This skill should be used when creating a Claude Code slash command. Use when users ask to "create a command", "make a slash command", "add a command", or want to document a workflow as a reusable command. Essential for creating optimized, agent-executable slash commands with proper structure and best practices.