| name | tool-selection-framework |
| description | Tool selection decision framework, domain validation (visual vs audio), cost awareness, and when to use which tool. Use when deciding which tools to use for a given task, especially when working with MCP servers. |
Tool Selection Framework
This skill provides a comprehensive framework for selecting appropriate tools for each task, with emphasis on domain validation, cost awareness, and tool appropriateness.
Overview
CRITICAL: Select appropriate tools for each task phase
Before calling any tool, ask:
- Is this tool appropriate for the current task phase?
- Is this tool necessary for the task?
- Has this tool failed recently?
- What are the cost implications?
Task Phase Validation
Phase-Appropriate Tool Selection
Testing phase โ agent-browser, not text_to_speech
Audio task โ text_to_speech, not agent-browser
VISUAL analysis task โ analyze_screenshot, NEVER text_to_speech
SCREENSHOT analysis task โ analyze_screenshot, NEVER ElevenLabs tools
Tool Selection Validation Checklist
Screenshot Analysis:
- If task involves "analyze screenshot", "check image", "describe what you see", "verify UI" โ MUST use
analyze_screenshot() from Screenshot Analyzer
Audio Tasks:
- If task involves "convert text to speech", "speech to text", "voice cloning", "sound effects" โ Use ElevenLabs tools
Domain Separation:
- NEVER CROSS DOMAINS: Visual tasks = Screenshot Analyzer, Audio tasks = ElevenLabs
- COST AWARENESS: ElevenLabs tools cost money - Screenshot Analyzer is free