FoundryVTT/.claude/output-styles/.OUTPUT_STYLES_TEMPLATE.md

name, description

name	description
Output Style Name	Brief description of this output style's purpose and behavior

Output Style Name

Purpose: One-sentence explanation of when and why to use this output style. Best For: [Type of tasks this style excels at]

Overview

This output style transforms Claude's behavior to [primary behavioral change]. Use this style when you need [specific scenario or requirement].

Key Characteristics

Communication Style

• Tone: [Formal/Casual/Technical/Educational/etc.]
• Verbosity: [Concise/Detailed/Balanced]
• Explanation Level: [Minimal/Moderate/Extensive]
• Technical Depth: [High-level/Detailed/Expert]

Interaction Patterns

• Proactivity: [Waits for instructions / Suggests next steps / Highly proactive]
• Question Asking: [Rarely/When needed/Frequently for clarity]
• Feedback Frequency: [After completion / During process / Continuous]
• Confirmation: [Assumes intent / Confirms before action / Always asks]

Output Format

• Code Comments: [None/Minimal/Comprehensive]
• Explanations: [Code only / Brief summaries / Detailed reasoning]
• Examples: [Rarely/When helpful/Always]
• Documentation: [Not included / Basic / Comprehensive]

Instructions for Claude

When using this output style, you should:

Primary Behaviors

DO:

• ✅ [Specific behavior 1 - be very explicit]
• ✅ [Specific behavior 2 - be very explicit]
• ✅ [Specific behavior 3 - be very explicit]
• ✅ [Specific behavior 4 - be very explicit]
• ✅ [Specific behavior 5 - be very explicit]

DON'T:

• ❌ [Behavior to avoid 1]
• ❌ [Behavior to avoid 2]
• ❌ [Behavior to avoid 3]
• ❌ [Behavior to avoid 4]

Response Structure

Follow this structure for all responses:

[Your response structure template here]

Example:
1. Brief summary (1-2 sentences)
2. Implementation/Answer
3. Key points or notes (if relevant)
4. Next steps (if applicable)

Code Generation Guidelines

When writing code:

• Comments: [Style of comments to include/exclude]
• Documentation: [Level of docstrings/JSDoc]
• Error Handling: [How comprehensive]
• Edge Cases: [How to address]
• Optimization: [Priority level]

Communication Guidelines

When interacting:

• Questions: [When and how to ask clarifying questions]
• Assumptions: [How to handle unclear requirements]
• Progress Updates: [How frequently to provide updates]
• Error Reporting: [How to communicate issues]

Use Cases

Ideal For:

1. [Use Case 1]: [Why this style is perfect for it]
2. [Use Case 2]: [Why this style is perfect for it]
3. [Use Case 3]: [Why this style is perfect for it]

Not Ideal For:

1. [Scenario 1]: [Why to use a different style]
2. [Scenario 2]: [Why to use a different style]

Examples

Example 1: [Scenario Name]

User Query:

[Example user request]

Response with This Style:

[How Claude would respond with this output style]

Why It's Different: [Explain how this differs from default style]

---

Example 2: [Scenario Name]

User Query:

[Example user request]

Response with This Style:

[How Claude would respond with this output style]

Why It's Different: [Explain how this differs from default style]

---

Example 3: [Complex Scenario]

User Query:

[Example complex request]

Response with This Style:

[How Claude would respond with this output style]

Why It's Different: [Explain how this differs from default style]

Comparison to Other Styles

vs. Default Style

• Default: [How default behaves]
• This Style: [How this style differs]
• When to Switch: [Use this when...]

vs. [Another Similar Style]

• [Other Style]: [How that style behaves]
• This Style: [Key differences]
• When to Choose This: [Use this when...]

Customization Options

Variants You Can Create

Based on this template, you could create:

1. [Variant 1]: [Modified version for specific need]
2. [Variant 2]: [Modified version for specific need]
3. [Variant 3]: [Modified version for specific need]

Adjusting the Style

To make this style more [characteristic]:

• Increase/decrease [specific aspect]
• Add/remove [specific element]
• Emphasize [specific behavior]

Special Instructions

Domain-Specific Considerations

If working with [Domain/Technology]:

• [Special instruction 1]
• [Special instruction 2]
• [Special instruction 3]

If user is [Type of User]:

• [Adaptation 1]
• [Adaptation 2]
• [Adaptation 3]

Context-Specific Adaptations

For quick tasks:

• [How to adapt for speed]

For complex projects:

• [How to adapt for depth]

For learning scenarios:

• [How to adapt for education]

Technical Details

Token Efficiency

• Typical Response Length: [Short/Medium/Long]
• Explanation Overhead: [Low/Medium/High]
• Best For Cost: [Yes/No - when]

Model Recommendations

• Recommended Model: [Sonnet/Opus/Haiku]
• Why: [Reasoning for model choice]
• Alternative: [When to use different model]

Activation & Usage

How to Activate

# Switch to this style
> /output-style [style-name]

# Verify active style
> /output-style

# Return to default
> /output-style default

When to Use

Activate this style when:

• ✅ [Trigger condition 1]
• ✅ [Trigger condition 2]
• ✅ [Trigger condition 3]

Switch away when:

• ❌ [Condition where different style is better]
• ❌ [Another condition]

Best Practices

Getting the Most From This Style

1. [Practice 1]: [How to effectively use this style]
2. [Practice 2]: [Another effective technique]
3. [Practice 3]: [Another tip]

Common Pitfalls

1. [Pitfall 1]: [What to avoid]

   • Solution: [How to handle it]

2. [Pitfall 2]: [What to avoid]

   • Solution: [How to handle it]

Combining With Other Features

With Commands:

• This style works well with: [specific commands]
• Modify command behavior: [how]

With Skills:

• Skills that complement this style: [which ones]
• How they interact: [explanation]

With Agents:

• Agent behaviors in this style: [how agents adapt]
• Best agent types: [which ones]

Troubleshooting

Style Not Working As Expected

Issue: Claude isn't following the style guidelines Solutions:

1. Clear conversation and restart: /clear
2. Re-activate style: /output-style [name]
3. Provide explicit reminder: "Remember to use [style] style"
4. Check for conflicting instructions in CLAUDE.md

Issue: Style is too [extreme characteristic] Solutions:

1. Create modified version with adjusted parameters
2. Give inline instructions to adjust
3. Switch to different style temporarily

Feedback & Iteration

Improving This Style

Track these metrics:

• Achieves desired behavior consistently
• User satisfaction with responses
• Efficiency for intended use cases
• No negative side effects

Update when:

• User feedback indicates issues
• Better patterns discovered
• New use cases emerge
• Technology changes

Version History

Version	Date	Changes	Author
1.0.0	YYYY-MM-DD	Initial creation	[Name]

Related Resources

Similar Styles

• [Related Style 1] - [How it differs]
• [Related Style 2] - [How it differs]

Documentation

• [Link to related docs]
• [Link to examples]

Community Examples

• [Link to community versions]
• [Link to discussions]

---

Quick Reference Card

Attribute	Value
Name	[Style Name]
Purpose	[One-line purpose]
Best For	[Primary use case]
Tone	[Communication style]
Verbosity	[Output length]
Proactivity	[Low/Medium/High]
Code Comments	[None/Minimal/Extensive]
Explanations	[Brief/Moderate/Detailed]
Model	[Recommended model]
Token Cost	[Low/Medium/High]

---

Template Usage Notes

Creating Your Own Output Style

1. Copy this template to .claude/output-styles/your-style-name.md
2. Fill in the frontmatter (name and description)
3. Define key characteristics - be specific about behavior
4. Write clear instructions - tell Claude exactly what to do
5. Provide examples - show the style in action
6. Test thoroughly - try with various tasks
7. Iterate based on feedback - refine over time

Key Principles

• Be specific: Vague instructions lead to inconsistent behavior
• Show examples: Concrete examples are more effective than descriptions
• Define boundaries: Say what NOT to do as clearly as what to do
• Consider context: Different tasks may need different approaches
• Test extensively: Try edge cases and complex scenarios

Common Output Style Patterns

Specialized Expert Styles:

• Security Reviewer
• Performance Optimizer
• Accessibility Expert
• Documentation Writer

User Type Styles:

• Beginner-Friendly (more explanation)
• Expert Mode (assumptions, less explanation)
• Pair Programming (collaborative)

Task Type Styles:

• Rapid Prototyping (speed over perfection)
• Production Code (thorough and careful)
• Learning Mode (educational)
• Debugging Mode (systematic investigation)

---

Template Version: 1.0.0 Last Updated: YYYY-MM-DD Harmonized with: SKILL_TEMPLATE.md, COMMANDS_TEMPLATE.md, AGENT_TEMPLATE.md

Remember: Output styles modify Claude's system prompt entirely. They're powerful but should be used thoughtfully. Test your custom styles thoroughly before relying on them for important work.