Optimize AI assistant configurations for maximum effectiveness. USE THIS SKILL when user says "improve CLAUDE.md", "better copilot instructions", "tune AI", "optimize prompts", "MCP configuration", or wants to enhance AI assistant behavior. See .github/instructions/ai-tuning.instructions.md for standards.
Scanned 2/12/2026
Install to Claude Code
Skills Directorynpx -y skills add majiayu000/claude-skill-registry --skill ai-tuning --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Ai Tuning?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/majiayu000-ai-tuning)More formats (shields.io, HTML) on the badges page.
---
name: ai-tuning
description: Optimize AI assistant configurations for maximum effectiveness. USE THIS SKILL when user says "improve CLAUDE.md", "better copilot instructions", "tune AI", "optimize prompts", "MCP configuration", or wants to enhance AI assistant behavior. See .github/instructions/ai-tuning.instructions.md for standards.
user-invocable: true
allowed-tools: Bash Read Write Edit Glob Grep
---
# AI Tuning Skill
## Purpose
Optimize AI assistant configurations for maximum effectiveness, including CLAUDE.md, copilot-instructions.md, and MCP server setup.
## Standards Reference
**Complete standards**: See `.github/instructions/ai-tuning.instructions.md`
## Triggers
- "improve my CLAUDE.md"
- "better copilot instructions"
- "tune AI for this project"
- "add MCP servers"
- "optimize AI prompts"
## Usage
Provide your existing AI configuration files or describe your project, and this skill will generate optimized CLAUDE.md, copilot-instructions.md, and MCP configurations following best practices defined in the instructions file.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
