Host: Codex CLI — This skill was designed for Claude Code and adapted for Codex. Cross-reference commands use installed skill names in Codex rather than
/octo:*slash commands. Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it. For host tool equivalents, seeskills/blocks/codex-host-adapter.md.
Meta-Prompt Generator Skill
Overview
Generate well-structured, verifiable prompts for any use case. Applies proven meta-prompting techniques to minimize hallucination and maximize effectiveness.
┌─────────────────────────────────────────────────────────────────────────────┐
│ META-PROMPT GENERATION │
├─────────────────────────────────────────────────────────────────────────────┤
│ │
│ Phase 1: Requirement Gathering │
│ → Understand the primary goal/role │
│ → Clarify expected outputs │
│ → Identify accuracy requirements │
│ ↓ │
│ Phase 2: Task Analysis │
│ → Apply Technique 1: Task Decomposition │
│ → Identify if complex enough for subtasks │
│ → Map dependencies between subtasks │
│ ↓ │
│ Phase 3: Expert Assignment │
│ → Apply Technique 5: Specialized Experts │
│ → Assign personas to subtasks │
│ → Apply Technique 2: Fresh Eyes Review │
│ ↓ │
│ Phase 4: Verification Design │
│ → Apply Technique 3: Iterative Verification │
│ → Build in checking steps │
│ → Apply Technique 4: No Guessing │
│ ↓ │
│ Phase 5: Prompt Assembly │
│ → Structure: Role, Context, Instructions, Constraints, Format │
│ → Add verification hooks │
│ → Include uncertainty disclaimers │
│ ↓ │
│ Phase 6: Output & Iteration │
│ → Present generated prompt │
│ → Offer refinement │
│ │
└─────────────────────────────────────────────────────────────────────────────┘
The Five Techniques
Technique 1: Task Decomposition
What: Break complex tasks into smaller, manageable subtasks.
When to use:
- Task has multiple distinct steps
- Different expertise needed for different parts
- Risk of getting lost in complexity
How to apply:
- List all components of the task
- Identify dependencies (what must happen first)
- Group related components
- Order by logical sequence
Example:
Task: "Create a technical blog post about OAuth 2.0"
Decomposition:
1. Research Phase
- Gather OAuth 2.0 specifications
- Find common implementation examples
- Identify security best practices
2. Structure Phase
- Outline main sections
- Plan code examples
- Design diagrams/visuals
3. Writing Phase
- Write introduction
- Write technical sections
- Write conclusion/CTA
4. Review Phase
- Technical accuracy check
- Code example testing
- Readability review
Technique 2: Fresh Eyes Review
What: Use different "experts" for creation vs. validation. Never use the same expert to both create and verify.
When to use:
- Output needs to be accurate
- Risk of blind spots from creator
- Quality assurance is critical
How to apply:
- Assign Creator Expert for initial work
- Assign different Reviewer Expert for validation
- Reviewer should not have seen creation process
- Loop back to Creator if issues found
Example:
Creator: "Expert Technical Writer" produces article
Reviewer: "Expert Security Engineer" verifies OAuth claims
Reviewer: "Expert Developer" tests code examples
NOT: Same expert writes AND reviews their own work
Technique 3: Iterative Verification
What: Build explicit verification steps into the task, especially for error-prone outputs.
When to use:
- Mathematical calculations
- Code generation
- Factual claims
- Multi-step reasoning
How to apply:
- After each significant output, add verification step
- For calculations: "Now verify this by [alternative method]"
- For code: "Test this code against [test cases]"
- For claims: "Confirm this by [citing source]"
Example:
Step 1: Calculate discount price
Step 2: VERIFY - recalculate from opposite direction
Step 3: If mismatch, identify error and recalculate
Step 4: Only proceed when both methods match
Technique 4: No Guessing
What: Never assume unverified facts. Disclaim uncertainty explicitly.
When to use:
- ALWAYS (this is a default behavior)
- Especially for: dates, statistics, quotes, technical specifications
How to apply:
- If uncertain, say "I'm not certain about..."
- If no data, say "I don't have information on..."
- Ask for sources rather than inventing
- Distinguish between "likely" and "confirmed"
Disclaimer templates:
"Note: This figure is approximate and should be verified."
"I don't have access to [specific data]. Please provide or verify."
"This is based on general patterns; your specific case may differ."
Technique 5: Specialized Experts
What: Spawn domain-specific personas for complex subtasks.
When to use:
- Task requires specialized knowledge
- Different perspectives would improve quality
- Cross-functional work needed
Available expert archetypes:
| Expert | Use For |
|---|---|
| Expert Writer | Content, copy, documentation |
| Expert Mathematician | Calculations, proofs, statistics |
| Expert Python | Python code, data analysis |
| Expert Security | Security review, threat modeling |
| Expert Architect | System design, trade-offs |
| Expert Reviewer | Quality assurance, error-finding |
| Expert Strategist | Planning, prioritization |
How to apply:
"For this subtask, adopt the persona of Expert [X].
Your expertise includes [specific areas].
Focus exclusively on [your assigned task].
You have no memory of previous context—all needed information is below."
Phase 1: Requirement Gathering
Initial Prompt
**Meta-Prompt Generator**
I'll help you create an effective, verifiable prompt.
**Questions:**
1. **What is the main goal?**
What should this prompt help someone accomplish?
2. **What's the expected output?**
(e.g., document, code, analysis, decision)
3. **How important is accuracy?**
- Critical (factual, technical, or high-stakes)
- Moderate (useful but not mission-critical)
- Flexible (creative, exploratory)
4. **Any specific constraints?**
(length, format, tone, tools available)
Minimum Information Needed
- Primary goal (REQUIRED)
- Output type (REQUIRED)
- Accuracy requirements (can assume moderate)
- Constraints