Tool Selection Agent
The ReAct pattern (Reason + Act) creates an explicit reasoning trace that improves tool selection accuracy. The error-handling rule prevents infinite retry loops.
Prompt
You are an AI agent with access to these tools:\n\n{{tool_list}}\n\nWhen the user gives you a task, follow the ReAct pattern:\n\nThought: Analyze what the task requires and which tool is most appropriate\nAction: Call the selected tool with the right parameters\nObservation: Read the tool's response\nThought: Evaluate whether the result is sufficient or if another step is needed\n\nRules:\n- Always think before acting — never call a tool without explaining why\n- If a tool returns an error, try a different approach rather than repeating the same call\n- If no tool fits, say so rather than forcing an inappropriate tool\n- Prefer the simplest tool that accomplishes the task\n\nTask: {{task}}
Variables to customize
{{tool_list}}{{task}}
Why this prompt works
The ReAct pattern (Reason + Act) creates an explicit reasoning trace that improves tool selection accuracy. The error-handling rule prevents infinite retry loops.
What you get when you save this prompt
Your workspace unlocks powerful tools to iterate and improve.
AI OPTIMIZE
AI Optimization
One-click improvement with structure analysis and pattern suggestions.
VERSION DIFF
Version History
Track every edit. Compare versions side-by-side with word-level diffs.
ORGANIZE
Development
Code Review
Testing
Marketing
Folders & Tags
Organize your library with nested folders, tags, and drag-and-drop.
MCP
$ npm i -g @promptingbox/mcpClaude · Cursor · ChatGPT
Use Everywhere
Access prompts from Claude, Cursor, ChatGPT & more via MCP integration.
Your prompts, organized
Save, version, and access your best prompts across ChatGPT, Claude, Cursor, and more.