fuse-prompt-engineer
Expert Prompt Engineer with Context Engineering, Meta-Prompting, Chain-of-Thought, Few-Shot, Agent Design, 50+ Template Library, and A/B Testing
pinned to #7749d4dupdated 2 weeks ago
Ask your AI client: “install plugins/fuse-prompt-engineer”.
Requires the metahub MCP server installed in your client. Set up MCP.
mh install plugins/fuse-prompt-engineermetahub onboarded this repo on the author's behalf.
If you own github.com/fusengine/agents on GitHub, claim the listing to take over publishing. Your claim preserves the existing eval history and badges; only the curator label is replaced with verified-publisher on your next publish.
Stars
19
Last commit
2 weeks ago
Latest release
published
- #claude-agent
- #claude-agents
- #claude-code
- #claude-code-plugin
- #claude-skills
- #claudeagent
- #claudecode
Evaluation report
WarningsAutomated checks the publisher passed at publish time — structure, docs, safety, and whether the artifact behaves as claimed.7749d4d· 2 weeks ago
Kind-specific
31Plugin: manifest fields complete
Plugin: bundled artifacts presentwarn
Couldn't find a skills/ subdir or an MCP server config inside the plugin
A plugin is most useful when it bundles ≥ 1 skill or an MCP server.
Plugin: bundle shape
empty bundle
Plugin: manifest location
manifest at plugin.json
Release history
1- releasecurrent7749d4dwarn2 weeks ago
Contents
Prompt Engineer Plugin
Expert in AI prompt creation and optimization. Masters 2025 best practices: Context Engineering, Meta-Prompting, advanced Chain-of-Thought, and agent design.
Installation
claude plugins install prompt-engineer
Agent
prompt-engineer
Expert in prompt engineering and AI agent design.
Model: Opus Color: Purple
Capabilities:
- Optimal prompt creation (system, task, few-shot, meta)
- Existing prompt optimization
- Complete agent design
- Security guardrails implementation
Skills
| Skill | Description |
|---|---|
prompt-creation | Techniques and templates for prompt creation |
prompt-optimization | Improve and optimize existing prompts |
agent-design | Design agents with recommended patterns |
guardrails | Security and quality control |
Command
/prompt
/prompt [action] [description]
Actions:
create- Create a new promptoptimize- Improve an existing promptagent- Design a complete agentreview- Analyze a prompt
Mastered Techniques
Structuring
- Chain-of-Thought (Zero-shot, Few-shot, Extended Thinking)
- Few-Shot Prompting (2-5 optimal examples)
- XML Tags for clear structure
- Structured Outputs (JSON Schema)
Context Engineering
- CLAUDE.md for automatic context
- Fresh Eyes Principle (contextual isolation)
- Meta-Prompting (Conductor-Expert pattern)
Guardrails
- Input Guardrails (topical, jailbreak, PII)
- Output Guardrails (format, hallucination, compliance)
- Ethical Boundaries
Plugin Structure
prompt-engineer/
├── .mcp.json # MCP servers config
├── README.md
├── agents/
│ └── prompt-engineer.md # Main agent
├── skills/
│ ├── prompt-creation/
│ │ ├── SKILL.md
│ │ └── docs/
│ │ ├── techniques.md
│ │ └── templates.md
│ ├── prompt-optimization/
│ │ └── SKILL.md
│ ├── agent-design/
│ │ ├── SKILL.md
│ │ └── docs/
│ │ ├── patterns.md
│ │ └── workflows.md
│ └── guardrails/
│ └── SKILL.md
└── commands/
└── prompt.md
Usage Examples
Create a support assistant
/prompt create a technical support assistant for an e-commerce mobile app
Optimize an existing prompt
/prompt optimize
[Paste your current prompt]
Design a code review agent
/prompt agent a Python-specialized code reviewer focused on security
Documentation
License
MIT
Reviews
No reviews yet. Be the first.
Related
claude-magic-compact
Lossless context compression for Claude Code.
mega-brain
OKF-powered knowledge context for Claude Code — injects your project knowledge base at every session
cc10x
The Loop Engine — harness and loop engineering plugin for Claude Code. Router-kernel orchestration, workflow artifacts, sub-agent delegation, hook enforcement, Test Honesty Gates, fresh-context verification, and memory that persists. 73% leaner than v11, zero quality regression.
mh install plugins/fuse-prompt-engineer