request-optimizer
CommunityOptimize AI requests, save tokens, get better results.
Product & Management#workflow#token efficiency#AI optimization#task decomposition#model selection#AI strategy#request analysis
Authormatheusallvarenga
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This skill addresses the common issues of inefficient AI interactions: wasted tokens, unclear execution paths, and suboptimal model choices. It acts as an intelligent intermediary, ensuring every request is analyzed and executed strategically, saving time and resources.
Core Features & Use Cases
- 5-Point Analysis: Automatically assesses request specificity, exploration needs, subtask decomposition, tool coordination, and optimal model choice (Haiku/Sonnet/Opus).
- Strategic Recommendations: Provides a clear, actionable strategy before execution, including suggested tools (MCPs, Agents, other Skills) and context optimization.
- Approval Gates: Prevents costly or unintended operations by requiring user approval for heavy tasks like codebase exploration or model upgrades.
- Use Case: You send a vague request like "Continue implementing the project." This skill will analyze it, recommend using an Explore Agent, suggest breaking it into phases, and ask for your approval before spending tokens, ensuring a focused and efficient workflow.
Quick Start
Use the request-optimizer skill to analyze my request to "refactor the user authentication module".
Dependency Matrix
Required Modules
None requiredComponents
references
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: request-optimizer Download link: https://github.com/matheusallvarenga/claude-code-skills/archive/main.zip#request-optimizer Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.