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 improve clarity. Output quality depends on the model and task and requires evaluation.

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, single verb, no context (weak hints, not reliable complexity tests)
• Complex tasks: Multiple requirements and conditional logic; length alone does not establish complexity
• 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 - explain framework choice when the user requests it.

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
• ❌ Hide framework selection when the user asks for an explanation
• ❌ 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: [confirm available purchase, preference and market-trend data; do not assume surveys or API access]
- Algorithm considerations: collaborative filtering, content-based filtering, hybrid approaches
- Performance metrics: precision, recall, diversity, novelty
- Scalability: [confirmed user scale, or mark unknown]
- Latency constraints: [confirmed requirement, or mark unknown]

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:

```
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

Provide concise findings, evidence and a decision rationale rather than private internal reasoning traces:
- 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.