Optimise Claude
Optimise Claude refines Claude’s responses for better clarity and relevance, saving you time and ensuring higher-quality outputs.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add optimise-claude npx -- -y @trustedskills/optimise-claude
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"optimise-claude": {
"command": "npx",
"args": [
"-y",
"@trustedskills/optimise-claude"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill, optimise-claude, refines prompts for use with the Claude AI model. It aims to improve response quality and reduce token usage through prompt engineering techniques. The skill is designed to be easily integrated into workflows requiring efficient and high-quality Claude outputs.
When to use it
- You're experiencing inconsistent or low-quality responses from Claude.
- You want to minimize the cost of using Claude by reducing token consumption.
- You need to ensure Claude understands complex instructions clearly.
- You are iterating on a prompt and want to quickly test different phrasing options.
Key capabilities
- Prompt refinement for Claude AI model
- Improved response quality
- Token usage reduction
- Easy integration into workflows
Example prompts
- "Optimise this prompt for Claude: 'Write a short story about a cat.'"
- "Refine the following instruction to be more effective with Claude: 'Summarize this article.'"
- “Can you optimise this prompt to reduce token usage? [Long, complex prompt here]”
Tips & gotchas
The skill's effectiveness depends on the initial quality of the prompt. While it can improve existing prompts, a fundamentally flawed instruction may still yield suboptimal results.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.