Back to guide/General Productivity

Tagging Taxonomy

Tags and folders serve different purposes. This taxonomy ensures tags add cross-cutting searchability (technique, status, model) rather than duplicating the folder hierarchy.

how-to-organize-promptscontext
Edit View
Prompt
Create a tagging taxonomy for a prompt library. Tags should be orthogonal to the folder structure (folders = what domain, tags = cross-cutting attributes).

Context: {{context}}

Design tags in these categories:

1. **Technique tags**: The prompting method used (e.g., few-shot, chain-of-thought, zero-shot, role-play, system-prompt)
2. **Status tags**: The prompt's lifecycle stage (e.g., draft, tested, production, deprecated)
3. **Model tags**: Which AI model it's optimized for (e.g., gpt-4, claude, gemini)
4. **Complexity tags**: How complex the prompt is (e.g., simple, intermediate, advanced)
5. **Output tags**: What the prompt produces (e.g., text, code, json, table, analysis)

For each category:
- List 4-6 recommended tags
- Explain when to use each one
- Note which tags should be required vs. optional

Taxonomy:

Variables to customize

{{context}}

Why this prompt works

Tags and folders serve different purposes. This taxonomy ensures tags add cross-cutting searchability (technique, status, model) rather than duplicating the folder hierarchy.

Save this prompt to your library

Organize, version, and access your best prompts across ChatGPT, Claude, and Cursor.

Related prompts

Task Decomposition Agent

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 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 Compressor

Explicitly requiring all functional requirements to be preserved prevents the model from over-compressing and losing critical instructions.

Memory Management Agent

Explicit memory read/write instructions create agents that improve over time. Categorization keeps memories organized, and the deduplication rule prevents context bloat.