/prompt
Create or optimize prompts using best practices
$ npx -y skills add fusengine/agents --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/prompt
Context preview
What this command does when you run it.
Create or optimize prompts using best practices
Command definition
prompt.mddescription: Create or optimize prompts using best practices
/prompt Command
Command for creating or optimizing prompts using the prompt-engineer agent.
Usage
/prompt [action] [description]
Actions
| Action | Description | |--------|-------------| | `create` | Create a new prompt | | `optimize` | Improve an existing prompt | | `agent` | Design a complete agent | | `review` | Analyze an existing prompt |
Workflow
1. Action Detection
IF $ARGUMENTS contains "create" or "new":
→ Action: CREATE
IF $ARGUMENTS contains "optimize" or "improve":
→ Action: OPTIMIZE
IF $ARGUMENTS contains "agent" or "assistant":
→ Action: AGENT_DESIGN
IF $ARGUMENTS contains "review" or "analyze":
→ Action: REVIEW
ELSE:
→ Ask for clarification
2. Agent Launch
Launch prompt-engineer agent with:
- Appropriate skill loaded
- User context
- Identified constraints
3. Workflow Execution
**For CREATE:** 1. Identify prompt type (system, task, few-shot, meta) 2. Identify constraints (model, format, domain) 3. Apply the 9-element Anthropic structure 4. Generate prompt with appropriate techniques 5. Validate with quality checklist
**For OPTIMIZE:** 1. Analyze current prompt 2. Identify issues (clarity, structure, completeness, guardrails) 3. Apply corrections 4. Generate before/after report 5. Propose optimized prompt
**For AGENT_DESIGN:** 1. Define identity and purpose 2. Choose architecture pattern 3. Define workflow 4. Configure tools and skills 5. Implement guardrails 6. Generate complete agent.md file
**For REVIEW:** 1. Analyze according to checklist 2. Score each criterion (clarity, structure, completeness, guardrails) 3. Identify strengths and weaknesses 4. Propose recommendations
Examples
Create a system prompt
/prompt create a technical support assistant for a mobile app
Optimize an existing prompt
/prompt optimize [paste the prompt to improve]
Design an agent
/prompt agent a Python-specialized code reviewer
Analyze a prompt
/prompt review [paste the prompt to analyze]
Output Format
For CREATE/OPTIMIZE
# [Prompt Name]
## Objective
[Description]
## Prompt
---
[THE COMPLETE PROMPT]
---
## Techniques Used
- [Technique 1]: [Why]
- [Technique 2]: [Why]
## Usage Notes
- [Note 1]
- [Note 2]
For AGENT_DESIGN
# Agent: [Name]
## Generated File
---
[CONTENT OF agent.md FILE]
---
## Architecture
- Pattern: [pattern used]
- Tools: [list of tools]
- Skills: [associated skills]
## Installation Instructions
1. [Step 1]
2. [Step 2]
For REVIEW
# Prompt Analysis
## Scores
| Criterion | Score | Comment |
|-----------|-------|---------|
| Clarity | X/10 | [...] |
| Structure | X/10 | [...] |
| Completeness | X/10 | [...] |
| Guardrails | X/10 | [...] |
## Strengths
- [Point 1]
- [Point 2]
## Areas for Improvement
1. [Area 1]: [Recommendation]
2. [Area 2]: [Recommendation]
Read more
description: Create or optimize prompts using best practices
/prompt Command
Command for creating or optimizing prompts using the prompt-engineer agent.
Usage
/prompt [action] [description]
Actions
| Action | Description | |--------|-------------| | `create` | Create a new prompt | | `optimize` | Improve an existing prompt | | `agent` | Design a complete agent | | `review` | Analyze an existing prompt |
Workflow
1. Action Detection
IF $ARGUMENTS contains "create" or "new": → Action: CREATE IF $ARGUMENTS contains "optimize" or "improve": → Action: OPTIMIZE IF $ARGUMENTS contains "agent" or "assistant": → Action: AGENT_DESIGN IF $ARGUMENTS contains "review" or "analyze": → Action: REVIEW ELSE: → Ask for clarification
2. Agent Launch
Launch prompt-engineer agent with: - Appropriate skill loaded - User context - Identified constraints
3. Workflow Execution
**For CREATE:** 1. Identify prompt type (system, task, few-shot, meta) 2. Identify constraints (model, format, domain) 3. Apply the 9-element Anthropic structure 4. Generate prompt with appropriate techniques 5. Validate with quality checklist
**For OPTIMIZE:** 1. Analyze current prompt 2. Identify issues (clarity, structure, completeness, guardrails) 3. Apply corrections 4. Generate before/after report 5. Propose optimized prompt
**For AGENT_DESIGN:** 1. Define identity and purpose 2. Choose architecture pattern 3. Define workflow 4. Configure tools and skills 5. Implement guardrails 6. Generate complete agent.md file
**For REVIEW:** 1. Analyze according to checklist 2. Score each criterion (clarity, structure, completeness, guardrails) 3. Identify strengths and weaknesses 4. Propose recommendations
Examples
Create a system prompt
/prompt create a technical support assistant for a mobile app
Optimize an existing prompt
/prompt optimize [paste the prompt to improve]
Design an agent
/prompt agent a Python-specialized code reviewer
Analyze a prompt
/prompt review [paste the prompt to analyze]
Output Format
For CREATE/OPTIMIZE
# [Prompt Name] ## Objective [Description] ## Prompt --- [THE COMPLETE PROMPT] --- ## Techniques Used - [Technique 1]: [Why] - [Technique 2]: [Why] ## Usage Notes - [Note 1] - [Note 2]
For AGENT_DESIGN
# Agent: [Name] ## Generated File --- [CONTENT OF agent.md FILE] --- ## Architecture - Pattern: [pattern used] - Tools: [list of tools] - Skills: [associated skills] ## Installation Instructions 1. [Step 1] 2. [Step 2]
For REVIEW
# Prompt Analysis ## Scores | Criterion | Score | Comment | |-----------|-------|---------| | Clarity | X/10 | [...] | | Structure | X/10 | [...] | | Completeness | X/10 | [...] | | Guardrails | X/10 | [...] | ## Strengths - [Point 1] - [Point 2] ## Areas for Improvement 1. [Area 1]: [Recommendation] 2. [Area 2]: [Recommendation]
A plugin ecosystem that turns Claude Code into a supervised, multi-agent development environment.
Repo: fusengine/agents
Other commands on fusengine-agents.
- /apex-quick
Quick Flow for simple fixes - Single expert handles explore, code, review, and validate in one pass. Inspired by BMAD Barry.
Open command - /apex
APEX Methodology - The systematic Analyze-Plan-Execute-eLicit-eXamine approach for intelligent development. Reduces hallucination and defect risk through mandatory parallel research, self-review, and validation gates.
Open command - /cleanup-context
Memory optimization - removes duplicates, consolidates knowledge, and cleans memory banks for better performance.
Open command - /create-pull-request
Auto-generate Pull Request with comprehensive description, test plan, and changelog. Uses gh CLI for creation.
Open command - /deep-code-analysis
Comprehensive codebase investigation using research-expert for documentation, explore-codebase for structure, and deep analysis. Perfect for understanding complex systems.
Open command - /epct
Systematic Explore-Plan-Code-Test methodology for structured development. Ensures comprehensive approach to feature implementation.
Open command

