Team Sharing Guidelines
Shared prompt libraries fail without lightweight governance. This template creates just enough process to keep the library useful without bureaucracy that discourages contribution.
Write a brief guide for our team on how to share and reuse prompts effectively. Team context: {{team_context}} Tools we use: {{tools}} Current pain points: {{pain_points}} The guide should cover: 1. **When to share a prompt**: What qualifies a prompt for the shared library vs. keeping it personal? 2. **How to document a shared prompt**: What metadata must be included (description, example input/output, model requirements, known limitations)? 3. **How to request changes**: Process for suggesting improvements to shared prompts without breaking others' workflows 4. **Ownership and maintenance**: Who is responsible for keeping shared prompts updated? 5. **Naming and tagging standards**: Summary of our conventions (reference existing taxonomy) Keep it under 500 words. Use bullet points. Make it practical, not theoretical. Guide:
Variables to customize
Why this prompt works
Shared prompt libraries fail without lightweight governance. This template creates just enough process to keep the library useful without bureaucracy that discourages contribution.
Save this prompt to your library
Organize, version, and access your best prompts across ChatGPT, Claude, and Cursor.
Related prompts
Forcing the agent to plan before acting prevents premature execution and wasted steps. Explicit dependency mapping enables parallel execution and catches logical gaps early.
Tool Selection AgentThe ReAct pattern (Reason + Act) creates an explicit reasoning trace that improves tool selection accuracy. The error-handling rule prevents infinite retry loops.
Prompt CompressorExplicitly requiring all functional requirements to be preserved prevents the model from over-compressing and losing critical instructions.
Memory Management AgentExplicit memory read/write instructions create agents that improve over time. Categorization keeps memories organized, and the deduplication rule prevents context bloat.