From tac
Displays seven levels of agentic prompts reference with table, decision guide, 80/20 rule, and related commands to select prompt complexity.
How this skill is triggered — by the user, by Claude, or both
Slash command
/tac:list-prompt-levelsThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Show the seven levels of agentic prompts with quick reference.
Show the seven levels of agentic prompts with quick reference.
Display the seven levels framework for quick reference.
## The Seven Levels of Agentic Prompts
| Level | Name | Key Capability | Use When |
| --- | --- | --- | --- |
| **1** | High-Level Prompt | One-off tasks | Simple, repeatable task |
| **2** | Workflow Prompt | Sequential execution | Need step-by-step |
| **3** | Control Flow | Conditionals/loops | Need branching/iteration |
| **4** | Delegation Prompt | Multi-agent work | Need parallel agents |
| **5** | Higher-Order | Process other prompts | Building on specs |
| **6** | Template Meta | Generate prompts | Creating prompt libraries |
| **7** | Self-Improving | Knowledge accumulation | Long-term expertise |
---
## The 80/20 Rule
> "Levels 3-4 cover 80% of practical use cases."
**Don't over-engineer.** Start simple, upgrade only when needed.
---
## Quick Decision Guide
- **Simple task?** -> Level 1
- **Need steps?** -> Level 2
- **If/else or loops?** -> Level 3
- **Multiple agents?** -> Level 4
- **Process specs?** -> Level 5
- **Create prompts?** -> Level 6
- **Self-evolving?** -> Level 7
---
## Related Commands
- `/create-prompt [level] [description]` - Create new prompt at level
- `/analyze-prompt [path]` - Analyze existing prompt
- `/upgrade-prompt [path] [level]` - Upgrade to higher level
## More Information
See @seven-levels.md for detailed level descriptions.
npx claudepluginhub melodic-software/claude-code-plugins --plugin tacGuides prompt level selection for tasks using seven levels framework, decision tree, complexity indicators, and examples to match investment to needs.
Crafts or updates LLM prompts from first principles by discovering goals, constraints, and context through targeted questions. Use for new prompts, updates, or reviews.
Interactive prompt engineering coach that transforms vague prompts through Socratic dialogue, scoring, and multiple transformation styles. Never auto-executes.