Prompt Engineer

Purpose

This skill transforms raw, unstructured user prompts into highly optimized prompts using established prompting frameworks. It analyzes user intent, identifies task complexity, and intelligently selects the most appropriate framework(s) to maximize Claude/ChatGPT output quality.

The skill operates in "magic mode" - it works silently behind the scenes, only interacting with users when clarification is critically needed. Users receive polished, ready-to-use prompts without technical explanations or framework jargon.

This is a universal skill that works in any terminal context, not limited to Obsidian vaults or specific project structures.

When to Use

Invoke this skill when:

• User provides a vague or generic prompt (e.g., "help me code Python")
• User has a complex idea but struggles to articulate it clearly
• User's prompt lacks structure, context, or specific requirements
• Task requires step-by-step reasoning (debugging, analysis, design)
• User needs a prompt for a specific AI task but doesn't know prompting frameworks
• User wants to improve an existing prompt's effectiveness
• User asks variations of "how do I ask AI to..." or "create a prompt for..."

Workflow

Step 1: Analyze Intent

Objective: Understand what the user truly wants to accomplish.

Actions: 1. Read the raw prompt provided by the user 2. Detect task characteristics:

• Type: coding, writing, analysis, design, learning, planning, decision-making, creative, etc.
• Complexity: simple (one-step), moderate (multi-step), complex (requires reasoning/design)
• Clarity: clear intention vs. ambiguous/vague
• Domain: technical, business, creative, academic, personal, etc.

3. Identify implicit requirements:

• Does user need examples?
• Is output format specified?
• Are there constraints (time, resources, scope)?
• Is this exploratory or execution-focused?

Detection Patterns:

• Simple tasks: Short prompts (<50 chars), single verb, no context
• Complex tasks: Long prompts (>200 chars), multiple requirements, conditional logic
• Ambiguous tasks: Generic verbs ("help", "improve"), missing object/context
• Structured tasks: Mentions steps, phases, deliverables, stakeholders

Step 2: Ask Clarifying Questions (Conditional)

Objective: Gather missing information only when it is critical to framework selection or prompt quality.

Trigger Conditions — ask only if:

• Task type is completely ambiguous (cannot determine coding vs. writing vs. analysis)
• Target audience is unknown and materially affects the output
• Scope is undefined and choosing wrong scope would invalidate the prompt
• Requested output format conflicts or is missing and cannot be inferred

Question Limits:

• Maximum 3 questions per invocation
• Combine related questions into one when possible
• If enough context exists, skip this step entirely (most cases)

Example Clarifying Exchange:

User: "help me with AI"

Step 2 (triggered — task type ambiguous):
"To craft the best prompt, I need one quick clarification:
1. What do you want to do with AI — build something, learn about it, or use an AI tool for a task?"

Critical Rule: When in doubt, skip clarification and generate the best prompt with available context. Over-asking breaks the "magic mode" experience.

Step 3: Select Framework(s)

Objective: Map task characteristics to optimal prompting framework(s).

Framework Mapping Logic:

Blending Strategy:

• Combine 2-3 frameworks when task spans multiple types
• Example: Complex technical project → RODES + Chain of Thought (structure + reasoning)
• Example: Leadership decision → CLEAR + GROW (goal clarity + development)

Selection Criteria:

• Primary framework = best match to core task type
• Secondary framework(s) = address additional complexity dimensions
• Avoid over-engineering: simple tasks get simple frameworks

Critical Rule: This selection happens silently - do not explain framework choice to user.

Role: You are a senior software architect. [RTF - Role]

Objective: Design a microservices architecture for [system]. [RODES - Objective]

Approach this step-by-step: [Chain of Thought] 1. Analyze current monolithic constraints 2. Identify service boundaries 3. Design inter-service communication 4. Plan data consistency strategy

Details: [RODES - Details]

• Expected traffic: [X]
• Data volume: [Y]
• Team size: [Z]

Output Format: [RTF - Format] Provide architecture diagram description, service definitions, and migration roadmap.

Sense Check: [RODES - Sense check] Validate that services are loosely coupled, independently deployable, and aligned with business domains.

**4.5. Language Adaptation**
- If original prompt is in Portuguese, generate prompt in Portuguese
- If original prompt is in English, generate prompt in English
- If mixed, default to English (more universal for AI models)

**4.6. Quality Checks**
Before finalizing, verify:
- [ ] Prompt is self-contained (no external context needed)
- [ ] Task is specific and measurable
- [ ] Output format is clear
- [ ] No ambiguous language
- [ ] Appropriate level of detail for task complexity


## Critical Rules

### **NEVER:**

- ❌ Assume information that wasn't provided - ALWAYS ask if critical details are missing
- ❌ Explain which framework was selected or why (magic mode - keep it invisible)
- ❌ Generate generic, one-size-fits-all prompts - always customize to context
- ❌ Use technical jargon in the final prompt (unless user's domain is technical)
- ❌ Ask more than 3 clarifying questions (avoid user fatigue)
- ❌ Include meta-commentary in the output ("This prompt uses...", "Note that...")
- ❌ Present output without code block formatting
- ❌ Mix languages inconsistently (if user writes in PT, respond in PT)

### **ALWAYS:**

- ✅ Analyze intent before generating (Step 1 is mandatory)
- ✅ Ask clarifying questions if critical information is ambiguous (Step 2 conditional)
- ✅ Select framework(s) based on task type and complexity (Step 3 mapping)
- ✅ Blend multiple frameworks when it improves prompt quality
- ✅ Adapt prompt length to original input complexity (simple → short, complex → detailed)
- ✅ Include output format specification in generated prompts
- ✅ Present final prompt in clean Markdown code block
- ✅ Make prompts self-contained (no dependency on external context)
- ✅ Use examples in complex prompts to illustrate expected output
- ✅ Validate prompt completeness before presenting (quality checks in Step 4.6)


### **Example 2: Complex Clear Prompt → RODES + Chain of Thought (No Clarification)**

**User Input:**

copilot> create prompt for: I need to build a product recommendation system considering purchase history, user preferences, and market trends

**Skill Internal Process:**
1. **Analyze:** Clear intent, complex task (ML system design), technical domain
2. **Clarify:** Skip (sufficient information)
3. **Select:** RODES (complex design) + Chain of Thought (reasoning needed)

**Skill Output:**

Role: You are a senior machine learning engineer specializing in recommendation systems.

Objective: Design a product recommendation system that combines user purchase history, preferences, and market trends.

Details:
- Input data sources: user transaction logs, preference surveys, market trend APIs
- Algorithm considerations: collaborative filtering, content-based filtering, hybrid approaches
- Performance metrics: precision, recall, diversity, novelty
- Scalability: system must handle 100k+ users
- Real-time constraints: recommendations updated within 500ms

Approach step-by-step:
1. Analyze the three data sources and their relationships
2. Propose 2-3 algorithm approaches with trade-offs analysis
3. Design data pipeline architecture (ingestion, processing, serving)
4. Define evaluation metrics and A/B testing strategy
5. Outline implementation roadmap with phases

Examples:
- Show pseudocode for core recommendation logic
- Illustrate data flow diagram
- Provide sample API response structure

Sense Check: Validate that the proposed solution balances personalization with discovery, scales to production load, and incorporates real-time market trends effectively.

Output format: Technical design document with architecture diagrams, algorithm justification, and implementation roadmap.

````

Example 4: Code Debugging → Chain of Thought

User Input:

copilot> optimize prompt: my Python code isn't working, needs debugging

Skill Internal Process: 1. Analyze: Debugging task, needs step-by-step reasoning 2. Clarify: Skip (user will provide code context later) 3. Select: Chain of Thought

Skill Output:

````markdown

You are an expert Python debugger.

Task: Debug the Python code provided by the user by analyzing it step-by-step.

Debugging approach:
1. Read and understand the code's intended purpose
2. Identify the error or unexpected behavior
3. Trace variable states at each execution step
4. Locate the root cause of the issue
5. Propose fix with explanation
6. Suggest preventive measures to avoid similar bugs

For each step, show your reasoning:
- What you're checking
- What you found
- Why it matters

Output format:
- **Issue identified:** [Describe the bug]
- **Root cause:** [Why it's happening]
- **Fix:** [Corrected code with comments]
- **Prevention:** [Best practices to avoid this in the future]

Include a working example to verify the fix.

````

Notes

This skill is platform-agnostic and works in any terminal context where GitHub Copilot CLI is available. It does not depend on:

• Obsidian vault structure
• Specific project configurations
• External files or templates

The skill is entirely self-contained, operating purely on user input and framework knowledge.

Limitations

• Use this skill only when the task clearly matches the scope described above.
• Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
• Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

🎯 Prompt Engineer

Version: 1.0.1 Status: ✨ Zero-Config | 🌍 Universal

Transform raw prompts into optimized, production-ready prompts using 11 established prompting frameworks.

---

📋 Overview

Prompt Engineer is an intelligent AI skill that analyzes your intentions and automatically generates optimized prompts for Claude, ChatGPT, or any other AI model. Instead of struggling with how to phrase complex requests, simply describe what you want - the skill handles the rest.

This skill works in "magic mode" - it operates silently, only asking questions when absolutely necessary. You provide a rough idea, and it returns a polished, structured prompt ready to use.

✨ Key Features

• 🎯 Intent Analysis: Understands what you're trying to accomplish
• 🧠 11 Frameworks: RTF, Chain of Thought, RISEN, RODES, Chain of Density, RACE, RISE, STAR, SOAP, CLEAR, GROW
• 🔄 Framework Blending: Combines multiple frameworks when needed
• ❓ Smart Clarification: Only asks questions when critically needed
• 📏 Adaptive Output: Matches prompt length to task complexity
• 🌍 Universal: Works in any project, any terminal context
• 🪄 Magic Mode: No technical explanations - just results

---

🚀 Quick Start

Invoke the Skill

Use any of these trigger phrases:

copilot> improve this prompt: [your rough prompt]
copilot> optimize prompt: [your idea]
copilot> refine prompt: [what you want]
copilot> prompt engineering for: [task description]
copilot> transform into prompt: [concept]
copilot> create prompt for: [goal]

Example 1: Simple Task

Input:

copilot> improve this prompt: help me write Python code

Skill asks:

What type of Python code do you need?
- [ ] Data analysis
- [ ] Web scraping
- [ ] Task automation
- [ ] API/backend development

You select: "Web scraping"

Output: ````markdown

You are a Python developer expert in web scraping.

Task: Create a Python script to scrape data from [specify target website].

Requirements:
- Use BeautifulSoup or Scrapy
- Implement pagination and rate limiting
- Store data in structured format (CSV or JSON)
- Include error handling for network issues

Output format: Complete, commented Python code with usage examples.

````

---

Example 2: Complex Task (No Clarification Needed)

Input:

copilot> create prompt for: product recommendation system with purchase history and market trends

Output: ````markdown

Role: You are a senior machine learning engineer specializing in recommendation systems.

Objective: Design a product recommendation system that combines user purchase history, preferences, and market trends.

Details:
- Input data sources: user transaction logs, preference surveys, market trend APIs
- Algorithm considerations: collaborative filtering, content-based filtering, hybrid approaches
- Performance metrics: precision, recall, diversity, novelty
- Scalability: system must handle 100k+ users

Approach step-by-step:
1. Analyze the three data sources and their relationships
2. Propose 2-3 algorithm approaches with trade-offs
3. Design data pipeline architecture
4. Define evaluation metrics
5. Outline implementation roadmap

Examples: Show pseudocode for core recommendation logic

Sense Check: Validate that the solution balances personalization with discovery and scales to production.

Output format: Technical design document with architecture diagrams and implementation roadmap.

````

---

Example 3: Ambiguous Task (Skill Clarifies)

Input:

copilot> transform into prompt: I want to improve my process

Skill asks:

What process do you want to improve?
- [ ] Work/productivity process
- [ ] Learning process
- [ ] Technical process (development, deployment, etc.)

You select: "Work process"

Skill asks:

What specific aspect?
- [ ] Time management
- [ ] Team collaboration
- [ ] Decision making

You select: "Decision making"

Output: ````markdown

Context: I struggle with making decisions quickly and effectively at work.

Objective: Develop a structured framework to improve decision speed and quality.

Current Reality:
- Decisions delayed by excessive analysis
- Lack of clear criteria
- Uncertainty about when to decide vs. gather information

Desired Outcome:
- Consistent decision-making framework
- Clear criteria for different decision types
- Reduced decision fatigue

Your task:
1. Assess current patterns and identify bottlenecks
2. Propose framework (Eisenhower Matrix, RAPID, Decision Tree)
3. Create decision criteria templates
4. Design tracking and iteration process

Output format: Practical playbook with templates, examples, and metrics.

````

---

📚 Supported Frameworks

The Prompt Engineer skill uses 11 established frameworks to optimize your prompts. The skill automatically selects and blends these frameworks based on your task - you never need to know or choose them manually.

---

1. RTF (Role-Task-Format)

Structure: Role → Task → Format

Best for: Tasks requiring specific expertise or perspective

Components:

• Role: "You are a [expert identity]"
• Task: "Your task is to [specific action]"
• Format: "Output format: [structure/style]"

Example:

You are a senior Python developer.
Task: Refactor this code for better performance.
Format: Provide refactored code with inline comments explaining changes.

---

2. Chain of Thought

Structure: Problem → Step 1 → Step 2 → ... → Solution

Best for: Complex reasoning, debugging, mathematical problems, logic puzzles

Components:

• Break problem into sequential steps
• Show reasoning at each stage
• Build toward final solution

Example:

Solve this problem step-by-step:
1. Identify the core issue
2. Analyze contributing factors
3. Propose solution approach
4. Validate solution against requirements

---

3. RISEN

Structure: Role, Instructions, Steps, End goal, Narrowing

Best for: Multi-phase projects with clear deliverables and constraints

Components:

• Role: Expert identity
• Instructions: What to do
• Steps: Sequential actions
• End goal: Desired outcome
• Narrowing: Constraints and focus areas

Example:

Role: You are a DevOps architect.
Instructions: Design a CI/CD pipeline for microservices.
Steps: 1) Analyze requirements 2) Select tools 3) Design workflow 4) Document
End goal: Automated deployment with zero-downtime releases.
Narrowing: Focus on AWS, limit to 3 environments (dev/staging/prod).

---

4. RODES

Structure: Role, Objective, Details, Examples, Sense check

Best for: Complex design, system architecture, research proposals

Components:

• Role: Expert perspective
• Objective: What to achieve
• Details: Context and requirements
• Examples: Concrete illustrations
• Sense check: Validation criteria

Example:

Role: You are a system architect.
Objective: Design a scalable e-commerce platform.
Details: Handle 100k concurrent users, sub-200ms response time, multi-region.
Examples: Show database schema, caching strategy, load balancing.
Sense check: Validate solution meets latency and scalability requirements.

---

5. Chain of Density

Structure: Iteration 1 (verbose) → Iteration 2 → ... → Iteration 5 (maximum density)

Best for: Summarization, compression, synthesis of long content

Process:

• Start with verbose explanation
• Iteratively compress while preserving key information
• End with maximally dense version (high information per word)

Example:

Compress this article into progressively denser summaries:
1. Initial summary (300 words)
2. Compressed (200 words)
3. Further compressed (100 words)
4. Dense (50 words)
5. Maximum density (25 words, all critical points)

---

6. RACE

Structure: Role, Audience, Context, Expectation

Best for: Communication, presentations, stakeholder updates, storytelling

Components:

• Role: Communicator identity
• Audience: Who you're addressing (expertise level, concerns)
• Context: Background/situation
• Expectation: What audience needs to know or do

Example:

Role: You are a product manager.
Audience: Non-technical executives.
Context: Quarterly business review, product performance down 5%.
Expectation: Explain root causes and recovery plan in non-technical terms.

---

7. RISE

Structure: Research, Investigate, Synthesize, Evaluate

Best for: Analysis, investigation, systematic exploration, diagnostic work

Process: 1. Research: Gather information 2. Investigate: Deep dive into findings 3. Synthesize: Combine insights 4. Evaluate: Assess and recommend

Example:

Analyze customer churn data using RISE:
Research: Collect churn metrics, exit surveys, support tickets.
Investigate: Identify patterns in churned users.
Synthesize: Combine findings into themes.
Evaluate: Recommend retention strategies based on evidence.

---

8. STAR

Structure: Situation, Task, Action, Result

Best for: Problem-solving with rich context, case studies, retrospectives

Components:

• Situation: Background context
• Task: Specific challenge
• Action: What needs doing
• Result: Expected outcome

Example:

Situation: Legacy monolith causing deployment delays (2 weeks per release).
Task: Modernize architecture to enable daily deployments.
Action: Migrate to microservices, implement CI/CD, containerize.
Result: Deploy 10+ times per day with <5% rollback rate.

---

9. SOAP

Structure: Subjective, Objective, Assessment, Plan

Best for: Structured documentation, medical records, technical logs, incident reports

Components:

• Subjective: Reported information (symptoms, complaints)
• Objective: Observable facts (metrics, data)
• Assessment: Analysis and diagnosis
• Plan: Recommended actions

Example:

Incident Report (SOAP):
Subjective: Users report slow page loads starting 10 AM.
Objective: Average response time increased from 200ms to 3s. CPU at 95%.
Assessment: Database connection pool exhausted due to traffic spike.
Plan: 1) Scale pool size 2) Add monitoring alerts 3) Review query performance.

---

10. CLEAR

Structure: Collaborative, Limited, Emotional, Appreciable, Refinable

Best for: Goal-setting, OKRs, measurable objectives, team alignment

Components:

• Collaborative: Who's involved
• Limited: Scope boundaries (time, resources)
• Emotional: Why it matters (motivation)
• Appreciable: Measurable progress indicators
• Refinable: How to iterate and improve

Example:

Q1 Objective (CLEAR):
Collaborative: Engineering + Product teams.
Limited: Complete by March 31, budget $50k, 2 engineers allocated.
Emotional: Reduces customer support load by 30%, improves satisfaction.
Appreciable: Track weekly via tickets resolved, NPS score, deployment count.
Refinable: Bi-weekly retrospectives, adjust priorities based on feedback.

---

11. GROW

Structure: Goal, Reality, Options, Will

Best for: Coaching, personal development, growth planning, mentorship

Components:

• Goal: What to achieve
• Reality: Current situation (strengths, gaps)
• Options: Possible approaches
• Will: Commitment to action

Example:

Career Development (GROW):
Goal: Become senior engineer within 12 months.
Reality: Strong coding skills, weak in system design and leadership.
Options: 1) Take system design course 2) Lead a project 3) Find mentor.
Will: Commit to 5 hours/week study, lead Q2 project, find mentor by Feb.

---

Framework Selection Logic

The skill analyzes your input and:

1. Detects task type

• Coding, writing, analysis, design, communication, etc.

2. Identifies complexity

• Simple (1-2 sentences) → Fast, minimal structure
• Moderate (paragraph) → Standard framework
• Complex (detailed requirements) → Advanced framework or blend

3. Selects primary framework

• RTF → Role-based tasks
• Chain of Thought → Step-by-step reasoning
• RISEN/RODES → Complex projects
• RACE → Communication
• STAR → Contextual problems
• And so on...

4. Blends secondary frameworks when needed

• RODES + Chain of Thought → Complex technical projects
• CLEAR + GROW → Leadership goals
• RACE + STAR → Strategic communication

You never choose the framework manually - the skill does it automatically in "magic mode."

---

Common Framework Blends

---

🎯 How It Works

User Input (rough prompt)
         ↓
┌────────────────────────┐
│ 1. Analyze Intent      │  What is the user trying to do?
│    - Task type         │  Coding? Writing? Analysis? Design?
│    - Complexity        │  Simple, moderate, complex?
│    - Clarity           │  Clear or ambiguous?
└────────┬───────────────┘
         ↓
┌────────────────────────┐
│ 2. Clarify (Optional)  │  Only if critically needed
│    - Ask 2-3 questions │  Multiple choice when possible
│    - Fill missing gaps │  
└────────┬───────────────┘
         ↓
┌────────────────────────┐
│ 3. Select Framework(s) │  Silent selection
│    - Map task → framework
│    - Blend if needed   │
└────────┬───────────────┘
         ↓
┌────────────────────────┐
│ 4. Generate Prompt     │  Apply framework rules
│    - Add role/context  │  
│    - Structure task    │  
│    - Define format     │
│    - Add examples      │
└────────┬───────────────┘
         ↓
┌────────────────────────┐
│ 5. Output              │  Clean, copy-ready
│    Markdown code block │  No explanations
└────────────────────────┘

---

🎨 Use Cases

Coding

copilot> optimize prompt: create REST API in Python

→ Generates structured prompt with role, requirements, output format, examples

---

Writing

copilot> create prompt for: write technical article about microservices

→ Generates audience-aware prompt with structure, tone, and content guidelines

---

Analysis

copilot> refine prompt: analyze sales data and identify trends

→ Generates step-by-step analytical framework with visualization requirements

---

Decision Making

copilot> improve this prompt: I need to decide between technology A and B

→ Generates decision framework with criteria, trade-offs, and validation

---

Learning

copilot> transform into prompt: learn machine learning from zero

→ Generates learning path prompt with phases, resources, and milestones

---

❓ FAQ

Q: Does this skill work outside of Obsidian vaults?

A: Yes! It's a universal skill that works in any terminal context. It doesn't depend on vault structure, project configuration, or external files.

---

Q: Do I need to know prompting frameworks?

A: No. The skill knows all 11 frameworks and selects the best one(s) automatically based on your task.

---

Q: Will the skill explain which framework it used?

A: No. It operates in "magic mode" - you get the polished prompt without technical explanations. If you want to know, you can ask explicitly.

---

Q: How many questions will the skill ask me?

A: Maximum 2-3 questions, and only when information is critically missing. Most of the time, it generates the prompt directly.

---

Q: Can I customize the frameworks?

A: The skill uses standard framework definitions. You can't customize them, but you can provide additional constraints in your input (e.g., "create a short prompt for...").

---

Q: Does it support languages other than English?

A: Yes. If you provide input in Portuguese, it generates the prompt in Portuguese. Same for English or mixed inputs.

---

Q: What if I don't like the generated prompt?

A: You can ask the skill to refine it: "make it shorter", "add more examples", "focus on X aspect", etc.

---

Q: Can I use this for any AI model (Claude, ChatGPT, Gemini)?

A: Yes. The prompts are model-agnostic and work with any conversational AI.

---

🔧 Installation (Global Setup)

This skill is designed to work globally across all your projects.

Option 1: Use from Repository

1. Clone the repository:

   git clone https://github.com/eric.andrade/cli-ai-skills.git

2. Configure Copilot to load skills globally:

   # Add to ~/.copilot/config.json
   {
     "skills": {
       "directories": [
         "/path/to/cli-ai-skills/.github/skills"
       ]
     }
   }

Option 2: Copy to Global Skills Directory

cp -r /path/to/cli-ai-skills/.github/skills/prompt-engineer ~/.copilot/global-skills/

Then configure:

# Add to ~/.copilot/config.json
{
  "skills": {
    "directories": [
      "~/.copilot/global-skills"
    ]
  }
}

---

📖 Learn More

• Skill Development Guide - Learn how to create your own skills
• [SKILL.md](./SKILL.md) - Full technical specification of this skill
• [Repository README](../../README.md) - Overview of all available skills

---

📄 Version

v1.0.1 | Zero-Config | Universal Works in any project, any context, any terminal.