Skip to content
Back to skills

1336 Performance Adb3d432

ASecurity

**Haiku 4.5** (90% of Sonnet capability, 3x cost savings): - Lightweight agents with frequent invocation - Pair programming and code generation - Worker agents in multi-agent systems

  • 9 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 11, 2026
code-qualitydebuggingrefactoringperformancedocumentation

Security analysis

A100/100

Scanned October 11, 2026

npx -y skills add tools-only/X-Skills --skill 1336-performance_adb3d432 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of 1336 Performance Adb3d432?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for 1336 Performance Adb3d432
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tools-only-1336-performance-adb3d432/badge)](https://www.skillsdirectory.com/skills/tools-only-1336-performance-adb3d432)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

SKILL.md
# Performance Optimization

## Model Selection Strategy

**Haiku 4.5** (90% of Sonnet capability, 3x cost savings):
- Lightweight agents with frequent invocation
- Pair programming and code generation
- Worker agents in multi-agent systems

**Sonnet 4.5** (Best coding model):
- Main development work
- Orchestrating multi-agent workflows
- Complex coding tasks

**Opus 4.5** (Deepest reasoning):
- Complex architectural decisions
- Maximum reasoning requirements
- Research and analysis tasks

## Context Window Management

Avoid last 20% of context window for:
- Large-scale refactoring
- Feature implementation spanning multiple files
- Debugging complex interactions

Lower context sensitivity tasks:
- Single-file edits
- Independent utility creation
- Documentation updates
- Simple bug fixes

## Ultrathink + Plan Mode

For complex tasks requiring deep reasoning:
1. Use `ultrathink` for enhanced thinking
2. Enable **Plan Mode** for structured approach
3. "Rev the engine" with multiple critique rounds
4. Use split role sub-agents for diverse analysis

## Build Troubleshooting

If build fails:
1. Use **build-error-resolver** agent
2. Analyze error messages
3. Fix incrementally
4. Verify after each fix

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.