[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MKB4A9R6T1HKA0D1KFKADM":3,"skill-same:01M6MKB4A9R6T1HKA0D1KFKADM":76},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":28,"publishedAt":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":52,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":69},"01M6MKB4A9R6T1HKA0D1KFKADM","skill-meta-prompt",null,"Craft better prompts using proven optimization techniques — use when your prompt needs refinement","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnyldn\u002Fclaude-octopus\u002Fskills\u002Fskill-meta-prompt\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000031","产品经理","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40],"Meta","prompt","skill meta prompt","meta prompt","Optimization","use","prompts","craft","refinement","true","techniques","when","2026-11-10 10:12:30",false,"---\nname: skill-meta-prompt\ndescription: \"Craft better prompts using proven optimization techniques — use when your prompt needs refinement\"\ndisable-model-invocation: true\n---\n\n> **Host: Codex CLI** — This skill was designed for Claude Code and adapted for Codex.\n> Cross-reference commands use installed skill names in Codex rather than `\u002Focto:*` slash commands.\n> 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.\n> For host tool equivalents, see `skills\u002Fblocks\u002Fcodex-host-adapter.md`.\n\n\n# Meta-Prompt Generator Skill\n\n## Overview\n\nGenerate well-structured, verifiable prompts for any use case. Applies proven meta-prompting techniques to minimize hallucination and maximize effectiveness.\n\n```\n┌─────────────────────────────────────────────────────────────────────────────┐\n│                       META-PROMPT GENERATION                                 │\n├─────────────────────────────────────────────────────────────────────────────┤\n│                                                                             │\n│  Phase 1: Requirement Gathering                                             │\n│       → Understand the primary goal\u002Frole                                    │\n│       → Clarify expected outputs                                            │\n│       → Identify accuracy requirements                                      │\n│       ↓                                                                     │\n│  Phase 2: Task Analysis                                                     │\n│       → Apply Technique 1: Task Decomposition                               │\n│       → Identify if complex enough for subtasks                             │\n│       → Map dependencies between subtasks                                   │\n│       ↓                                                                     │\n│  Phase 3: Expert Assignment                                                 │\n│       → Apply Technique 5: Specialized Experts                              │\n│       → Assign personas to subtasks                                         │\n│       → Apply Technique 2: Fresh Eyes Review                                │\n│       ↓                                                                     │\n│  Phase 4: Verification Design                                               │\n│       → Apply Technique 3: Iterative Verification                           │\n│       → Build in checking steps                                             │\n│       → Apply Technique 4: No Guessing                                      │\n│       ↓                                                                     │\n│  Phase 5: Prompt Assembly                                                   │\n│       → Structure: Role, Context, Instructions, Constraints, Format         │\n│       → Add verification hooks                                              │\n│       → Include uncertainty disclaimers                                     │\n│       ↓                                                                     │\n│  Phase 6: Output & Iteration                                                │\n│       → Present generated prompt                                            │\n│       → Offer refinement                                                    │\n│                                                                             │\n└─────────────────────────────────────────────────────────────────────────────┘\n```\n\n\n## The Five Techniques\n\n### Technique 1: Task Decomposition\n\n**What:** Break complex tasks into smaller, manageable subtasks.\n\n**When to use:**\n- Task has multiple distinct steps\n- Different expertise needed for different parts\n- Risk of getting lost in complexity\n\n**How to apply:**\n1. List all components of the task\n2. Identify dependencies (what must happen first)\n3. Group related components\n4. Order by logical sequence\n\n**Example:**\n```\nTask: \"Create a technical blog post about OAuth 2.0\"\n\nDecomposition:\n1. Research Phase\n   - Gather OAuth 2.0 specifications\n   - Find common implementation examples\n   - Identify security best practices\n   \n2. Structure Phase\n   - Outline main sections\n   - Plan code examples\n   - Design diagrams\u002Fvisuals\n   \n3. Writing Phase\n   - Write introduction\n   - Write technical sections\n   - Write conclusion\u002FCTA\n   \n4. Review Phase\n   - Technical accuracy check\n   - Code example testing\n   - Readability review\n```\n\n\n### Technique 2: Fresh Eyes Review\n\n**What:** Use different \"experts\" for creation vs. validation. Never use the same expert to both create and verify.\n\n**When to use:**\n- Output needs to be accurate\n- Risk of blind spots from creator\n- Quality assurance is critical\n\n**How to apply:**\n1. Assign Creator Expert for initial work\n2. Assign different Reviewer Expert for validation\n3. Reviewer should not have seen creation process\n4. Loop back to Creator if issues found\n\n**Example:**\n```\nCreator: \"Expert Technical Writer\" produces article\nReviewer: \"Expert Security Engineer\" verifies OAuth claims\nReviewer: \"Expert Developer\" tests code examples\n\nNOT: Same expert writes AND reviews their own work\n```\n\n\n### Technique 3: Iterative Verification\n\n**What:** Build explicit verification steps into the task, especially for error-prone outputs.\n\n**When to use:**\n- Mathematical calculations\n- Code generation\n- Factual claims\n- Multi-step reasoning\n\n**How to apply:**\n1. After each significant output, add verification step\n2. For calculations: \"Now verify this by [alternative method]\"\n3. For code: \"Test this code against [test cases]\"\n4. For claims: \"Confirm this by [citing source]\"\n\n**Example:**\n```\nStep 1: Calculate discount price\nStep 2: VERIFY - recalculate from opposite direction\nStep 3: If mismatch, identify error and recalculate\nStep 4: Only proceed when both methods match\n```\n\n\n### Technique 4: No Guessing\n\n**What:** Never assume unverified facts. Disclaim uncertainty explicitly.\n\n**When to use:**\n- ALWAYS (this is a default behavior)\n- Especially for: dates, statistics, quotes, technical specifications\n\n**How to apply:**\n1. If uncertain, say \"I'm not certain about...\"\n2. If no data, say \"I don't have information on...\"\n3. Ask for sources rather than inventing\n4. Distinguish between \"likely\" and \"confirmed\"\n\n**Disclaimer templates:**\n```\n\"Note: This figure is approximate and should be verified.\"\n\"I don't have access to [specific data]. Please provide or verify.\"\n\"This is based on general patterns; your specific case may differ.\"\n```\n\n\n### Technique 5: Specialized Experts\n\n**What:** Spawn domain-specific personas for complex subtasks.\n\n**When to use:**\n- Task requires specialized knowledge\n- Different perspectives would improve quality\n- Cross-functional work needed\n\n**Available expert archetypes:**\n| Expert | Use For |\n|--------|---------|\n| Expert Writer | Content, copy, documentation |\n| Expert Mathematician | Calculations, proofs, statistics |\n| Expert Python | Python code, data analysis |\n| Expert Security | Security review, threat modeling |\n| Expert Architect | System design, trade-offs |\n| Expert Reviewer | Quality assurance, error-finding |\n| Expert Strategist | Planning, prioritization |\n\n**How to apply:**\n```\n\"For this subtask, adopt the persona of Expert [X].\nYour expertise includes [specific areas].\nFocus exclusively on [your assigned task].\nYou have no memory of previous context—all needed information is below.\"\n```\n\n\n## Phase 1: Requirement Gathering\n\n### Initial Prompt\n\n```markdown\n**Meta-Prompt Generator**\n\nI'll help you create an effective, verifiable prompt.\n\n**Questions:**\n\n1. **What is the main goal?**\n   What should this prompt help someone accomplish?\n\n2. **What's the expected output?**\n   (e.g., document, code, analysis, decision)\n\n3. **How important is accuracy?**\n   - Critical (factual, technical, or high-stakes)\n   - Moderate (useful but not mission-critical)\n   - Flexible (creative, exploratory)\n\n4. **Any specific constraints?**\n   (length, format, tone, tools available)\n```\n\n### Minimum Information Needed\n\n- Primary goal (REQUIRED)\n- Output type (REQUIRED)\n- Accuracy requirements (can assume moderate)\n- Constraints (optional, will use sensible defaults)\n\n**If information is missing, ask ONE clarifying question at a time.**\n\n\n## Phase 2-4: Analysis & Design\n\nAfter gathering requirements, analyze internally:\n\n### Task Complexity Assessment\n\n| Complexity | Indicators | Approach |\n|------------|------------|----------|\n| **Simple** | Single step, one output | Direct prompt, no decomposition |\n| **Moderate** | 2-3 steps, clear sequence | Light decomposition, one expert |\n| **Complex** | 4+ steps, dependencies | Full decomposition, multiple experts |\n\n### Expert Assignment Matrix\n\n| Task Type | Creator Expert | Reviewer Expert |\n|-----------|----------------|-----------------|\n| Technical writing | Expert Writer | Expert Engineer |\n| Code generation | Expert Developer | Expert Reviewer |\n| Analysis | Expert Analyst | Expert Strategist |\n| Creative | Expert Creative | Expert Editor |\n\n### Verification Points\n\nFor the task, identify where verification is needed:\n\n| Step | Risk | Verification Method |\n|------|------|---------------------|\n| [step] | [what could go wrong] | [how to verify] |\n\n\n## Phase 5: Prompt Assembly\n\n### Output Format\n\nYou MUST return the generated prompt in this exact format:\n\n```markdown\n# [Prompt Title]\n\n## Role\n[Short, direct role definition]\n[Emphasize verification and uncertainty disclaimers]\n\n## Context\n[User's task and goals]\n[Background information provided]\n[Clarifications gathered]\n\n## Instructions\n\n### Phase 1: [First Phase Name]\n1. [Step 1]\n2. [Step 2]\n3. **Verification:** [How to verify this phase]\n\n### Phase 2: [Second Phase Name]\n1. [Step 1]\n2. [Step 2]\n3. **Verification:** [How to verify this phase]\n\n[Continue phases as needed...]\n\n### Expert Assignments (if applicable)\n- **[Expert Type]:** Handles [specific subtask]\n- **[Reviewer Type]:** Validates [what they check]\n\n## Constraints\n- [Constraint 1]\n- [Constraint 2]\n- [Accuracy requirement: how to handle uncertainty]\n\n## Output Format\n[Specify exactly how the output should be structured]\n[Include all required sections]\n\n## Verification Checklist\nBefore considering complete:\n- [ ] [Verification item 1]\n- [ ] [Verification item 2]\n- [ ] [Accuracy disclaimers added where needed]\n\n## Examples (if provided)\n[Context or examples from user]\n```\n\n### Model-Specific Adjustments\n\nTune the assembled prompt to the model that will execute it:\n\n- **Current frontier roster**: apply `skills\u002Fblocks\u002Ffrontier-model-routing.md` when choosing between Opus 5, GPT-5.6, Sonnet 5, Fable 5.1, Astra, or cheaper seats.\n- **Claude Fable 5.1 or 5**: apply `skills\u002Fblocks\u002Ffable5-prompting.md` to either model ID. In short: never instruct the model to reveal or transcribe its reasoning; replace step-by-step micromanagement with a boundary plus checkable acceptance criteria; drop \"CRITICAL\"\u002F\"MUST\" emphasis unless strict compliance is required; add grounded-progress and act-when-ready language for long runs.\n- **GPT-6 Astra**: reserve it for a bounded pass after GPT-5.6 Sol fails a hard acceptance test. Do not treat Astra plus GPT-5.6 as independent review.\n- **Codex \u002F GPT-5.6**: apply `docs\u002FGPT-5.6-PROMPTING.md`; give it a concrete outcome, scoped repository constraints, checkable acceptance criteria, non-goals, and the required verification.\n- **Older Claude models**: the fuller template below applies as written.\n\n\n## Phase 6: Output & Iteration\n\n### Present the Prompt\n\n```markdown\n**Generated Meta-Prompt**\n\n[The prompt in the format above]\n\n\n**Techniques Applied:**\n- ✓ Task Decomposition: [Yes\u002FNo, how]\n- ✓ Fresh Eyes Review: [Yes\u002FNo, which experts]\n- ✓ Iterative Verification: [Yes\u002FNo, where]\n- ✓ No Guessing: [Where disclaimers needed]\n- ✓ Specialized Experts: [Which ones assigned]\n\n**Would you like me to:**\n1. Refine any section\n2. Add more verification steps\n3. Adjust the complexity level\n4. Execute this prompt now\n```\n\n\n## Example: Complete Meta-Prompt Generation\n\n### User Request\n\"Create a prompt to help me write API documentation\"\n\n### Generated Prompt\n\n```markdown\n# API Documentation Generator\n\n## Role\nYou are an Expert Technical Writer specializing in API documentation.\nYour documentation will be reviewed by an Expert Developer for accuracy.\nWhen uncertain about behavior, note \"Verify with implementation\" rather than guessing.\n\n## Context\nCreating comprehensive API documentation for developers.\nDocumentation should be usable without reading source code.\n\n## Instructions\n\n### Phase 1: API Discovery\n1. List all endpoints with methods (GET, POST, etc.)\n2. Document request\u002Fresponse schemas\n3. Identify authentication requirements\n4. **Verification:** Cross-reference with OpenAPI spec if available\n\n### Phase 2: Documentation Writing\n1. Write endpoint descriptions (what it does, not how)\n2. Create request examples with all parameters\n3. Create response examples for success and error cases\n4. Document rate limits and constraints\n5. **Verification:** Each example should be valid JSON\u002Fcode\n\n### Phase 3: Review Cycle\nExpert Developer reviews for:\n- Technical accuracy of examples\n- Missing edge cases\n- Unclear descriptions\n\n### Expert Assignments\n- **Expert Technical Writer:** Creates documentation prose\n- **Expert Developer:** Validates examples and accuracy\n\n## Constraints\n- Use consistent terminology throughout\n- Examples must be syntactically valid\n- Note any undocumented or unclear behaviors\n- Accuracy: Mark assumptions with \"Assumed behavior - verify\"\n\n## Output Format\n```markdown\n# [Endpoint Name]\n\n**Method:** [HTTP method]\n**Path:** [\u002Fapi\u002Fpath]\n**Auth:** [Required\u002FOptional\u002FNone]\n\n## Description\n[What this endpoint does]\n\n## Request\n[Parameters, body schema, headers]\n\n## Response\n[Success and error responses with examples]\n\n## Notes\n[Rate limits, deprecation, related endpoints]\n```\n\n## Verification Checklist\n- [ ] All endpoints documented\n- [ ] All examples are valid\n- [ ] Authentication clearly specified\n- [ ] Error responses included\n- [ ] Assumptions marked for verification\n```\n\n\n## Error Handling\n\n### Unclear Requirements\n\n```markdown\nI need a bit more clarity to create an effective prompt.\n\n**Specifically:**\n[Question about the unclear part]\n\n[Offer 2-3 options if applicable]\n```\n\n### Over-Complex Request\n\n```markdown\nThis task has [N] distinct components. I recommend:\n\n1. **Split into multiple prompts** - One per major component\n2. **Simplify scope** - Focus on [core element] first\n3. **Proceed as-is** - Full complexity, longer prompt\n\nWhich approach works best for you?\n```\n\n### Can't Apply Techniques\n\nIf techniques don't fit the task:\n\n```markdown\nℹ️ **Note on Techniques**\n\nThis task is straightforward enough that some techniques\ndon't apply:\n\n- Task Decomposition: Not needed (single step)\n- Fresh Eyes: [Explain why\u002Fwhy not]\n- Specialized Experts: Not needed (single domain)\n\nThe generated prompt focuses on clarity and verification instead.\n```\n\n\n## Integration\n\n### With skill-content-pipeline\nGenerate prompts for content creation based on anatomy guides.\n\n### With skill-thought-partner\nTransform brainstorming insights into actionable prompts.\n\n### With skill-prd\nEnhance PRD generation with meta-prompting techniques.\n\n### With flow-develop\nGenerate implementation prompts with built-in verification.\n\n\n## The Bottom Line\n\n```\nMeta-prompt → Decompose → Assign experts → Build verification → Generate\nOtherwise → Vague prompts → Hallucination → Unreliable output\n```\n\n**Structure breeds reliability. Verification breeds accuracy. Experts breed quality.**\n","> **Host: Codex CLI** — This skill was designed for Claude Code and adapted for Codex.\n> Cross-reference commands use installed skill names in Codex rather than `\u002Focto:*` slash commands.\n> 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.\n> For host tool equivalents, see `skills\u002Fblocks\u002Fcodex-host-adapter.md`.\n\n\n# Meta-Prompt Generator Skill\n\n## Overview\n\nGenerate well-structured, verifiable prompts for any use case. Applies proven meta-prompting techniques to minimize hallucination and maximize effectiveness.\n\n```\n┌─────────────────────────────────────────────────────────────────────────────┐\n│                       META-PROMPT GENERATION                                 │\n├─────────────────────────────────────────────────────────────────────────────┤\n│                                                                             │\n│  Phase 1: Requirement Gathering                                             │\n│       → Understand the primary goal\u002Frole                                    │\n│       → Clarify expected outputs                                            │\n│       → Identify accuracy requirements                                      │\n│       ↓                                                                     │\n│  Phase 2: Task Analysis                                                     │\n│       → Apply Technique 1: Task Decomposition                               │\n│       → Identify if complex enough for subtasks                             │\n│       → Map dependencies between subtasks                                   │\n│       ↓                                                                     │\n│  Phase 3: Expert Assignment                                                 │\n│       → Apply Technique 5: Specialized Experts                              │\n│       → Assign personas to subtasks                                         │\n│       → Apply Technique 2: Fresh Eyes Review                                │\n│       ↓                                                                     │\n│  Phase 4: Verification Design                                               │\n│       → Apply Technique 3: Iterative Verification                           │\n│       → Build in checking steps                                             │\n│       → Apply Technique 4: No Guessing                                      │\n│       ↓                                                                     │\n│  Phase 5: Prompt Assembly                                                   │\n│       → Structure: Role, Context, Instructions, Constraints, Format         │\n│       → Add verification hooks                                              │\n│       → Include uncertainty disclaimers                                     │\n│       ↓                                                                     │\n│  Phase 6: Output & Iteration                                                │\n│       → Present generated prompt                                            │\n│       → Offer refinement                                                    │\n│                                                                             │\n└─────────────────────────────────────────────────────────────────────────────┘\n```\n\n\n## The Five Techniques\n\n### Technique 1: Task Decomposition\n\n**What:** Break complex tasks into smaller, manageable subtasks.\n\n**When to use:**\n- Task has multiple distinct steps\n- Different expertise needed for different parts\n- Risk of getting lost in complexity\n\n**How to apply:**\n1. List all components of the task\n2. Identify dependencies (what must happen first)\n3. Group related components\n4. Order by logical sequence\n\n**Example:**\n```\nTask: \"Create a technical blog post about OAuth 2.0\"\n\nDecomposition:\n1. Research Phase\n   - Gather OAuth 2.0 specifications\n   - Find common implementation examples\n   - Identify security best practices\n   \n2. Structure Phase\n   - Outline main sections\n   - Plan code examples\n   - Design diagrams\u002Fvisuals\n   \n3. Writing Phase\n   - Write introduction\n   - Write technical sections\n   - Write conclusion\u002FCTA\n   \n4. Review Phase\n   - Technical accuracy check\n   - Code example testing\n   - Readability review\n```\n\n\n### Technique 2: Fresh Eyes Review\n\n**What:** Use different \"experts\" for creation vs. validation. Never use the same expert to both create and verify.\n\n**When to use:**\n- Output needs to be accurate\n- Risk of blind spots from creator\n- Quality assurance is critical\n\n**How to apply:**\n1. Assign Creator Expert for initial work\n2. Assign different Reviewer Expert for validation\n3. Reviewer should not have seen creation process\n4. Loop back to Creator if issues found\n\n**Example:**\n```\nCreator: \"Expert Technical Writer\" produces article\nReviewer: \"Expert Security Engineer\" verifies OAuth claims\nReviewer: \"Expert Developer\" tests code examples\n\nNOT: Same expert writes AND reviews their own work\n```\n\n\n### Technique 3: Iterative Verification\n\n**What:** Build explicit verification steps into the task, especially for error-prone outputs.\n\n**When to use:**\n- Mathematical calculations\n- Code generation\n- Factual claims\n- Multi-step reasoning\n\n**How to apply:**\n1. After each significant output, add verification step\n2. For calculations: \"Now verify this by [alternative method]\"\n3. For code: \"Test this code against [test cases]\"\n4. For claims: \"Confirm this by [citing source]\"\n\n**Example:**\n```\nStep 1: Calculate discount price\nStep 2: VERIFY - recalculate from opposite direction\nStep 3: If mismatch, identify error and recalculate\nStep 4: Only proceed when both methods match\n```\n\n\n### Technique 4: No Guessing\n\n**What:** Never assume unverified facts. Disclaim uncertainty explicitly.\n\n**When to use:**\n- ALWAYS (this is a default behavior)\n- Especially for: dates, statistics, quotes, technical specifications\n\n**How to apply:**\n1. If uncertain, say \"I'm not certain about...\"\n2. If no data, say \"I don't have information on...\"\n3. Ask for sources rather than inventing\n4. Distinguish between \"likely\" and \"confirmed\"\n\n**Disclaimer templates:**\n```\n\"Note: This figure is approximate and should be verified.\"\n\"I don't have access to [specific data]. Please provide or verify.\"\n\"This is based on general patterns; your specific case may differ.\"\n```\n\n\n### Technique 5: Specialized Experts\n\n**What:** Spawn domain-specific personas for complex subtasks.\n\n**When to use:**\n- Task requires specialized knowledge\n- Different perspectives would improve quality\n- Cross-functional work needed\n\n**Available expert archetypes:**\n| Expert | Use For |\n|--------|---------|\n| Expert Writer | Content, copy, documentation |\n| Expert Mathematician | Calculations, proofs, statistics |\n| Expert Python | Python code, data analysis |\n| Expert Security | Security review, threat modeling |\n| Expert Architect | System design, trade-offs |\n| Expert Reviewer | Quality assurance, error-finding |\n| Expert Strategist | Planning, prioritization |\n\n**How to apply:**\n```\n\"For this subtask, adopt the persona of Expert [X].\nYour expertise includes [specific areas].\nFocus exclusively on [your assigned task].\nYou have no memory of previous context—all needed information is below.\"\n```\n\n\n## Phase 1: Requirement Gathering\n\n### Initial Prompt\n\n```markdown\n**Meta-Prompt Generator**\n\nI'll help you create an effective, verifiable prompt.\n\n**Questions:**\n\n1. **What is the main goal?**\n   What should this prompt help someone accomplish?\n\n2. **What's the expected output?**\n   (e.g., document, code, analysis, decision)\n\n3. **How important is accuracy?**\n   - Critical (factual, technical, or high-stakes)\n   - Moderate (useful but not mission-critical)\n   - Flexible (creative, exploratory)\n\n4. **Any specific constraints?**\n   (length, format, tone, tools available)\n```\n\n### Minimum Information Needed\n\n- Primary goal (REQUIRED)\n- Output type (REQUIRED)\n- Accuracy requirements (can assume moderate)\n- Constraints (optional, will use sensible defaults)\n\n**If information is missing, ask ONE clarifying question at a time.**\n\n\n## Phase 2-4: Analysis & Design\n\nAfter gathering requirements, analyze internally:\n\n### Task Complexity Assessment\n\n| Complexity | Indicators | Approach |\n|------------|------------|----------|\n| **Simple** | Single step, one output | Direct prompt, no decomposition |\n| **Moderate** | 2-3 steps, clear sequence | Light decomposition, one expert |\n| **Complex** | 4+ steps, dependencies | Full decomposition, multiple experts |\n\n### Expert Assignment Matrix\n\n| Task Type | Creator Expert | Reviewer Expert |\n|-----------|----------------|-----------------|\n| Technical writing | Expert Writer | Expert Engineer |\n| Code generation | Expert Developer | Expert Reviewer |\n| Analysis | Expert Analyst | Expert Strategist |\n| Creative | Expert Creative | Expert Editor |\n\n### Verification Points\n\nFor the task, identify where verification is needed:\n\n| Step | Risk | Verification Method |\n|------|------|---------------------|\n| [step] | [what could go wrong] | [how to verify] |\n\n\n## Phase 5: Prompt Assembly\n\n### Output Format\n\nYou MUST return the generated prompt in this exact format:\n\n```markdown\n# [Prompt Title]\n\n## Role\n[Short, direct role definition]\n[Emphasize verification and uncertainty disclaimers]\n\n## Context\n[User's task and goals]\n[Background information provided]\n[Clarifications gathered]\n\n## Instructions\n\n### Phase 1: [First Phase Name]\n1. [Step 1]\n2. [Step 2]\n3. **Verification:** [How to verify this phase]\n\n### Phase 2: [Second Phase Name]\n1. [Step 1]\n2. [Step 2]\n3. **Verification:** [How to verify this phase]\n\n[Continue phases as needed...]\n\n### Expert Assignments (if applicable)\n- **[Expert Type]:** Handles [specific subtask]\n- **[Reviewer Type]:** Validates [what they check]\n\n## Constraints\n- [Constraint 1]\n- [Constraint 2]\n- [Accuracy requirement: how to handle uncertainty]\n\n## Output Format\n[Specify exactly how the output should be structured]\n[Include all required sections]\n\n## Verification Checklist\nBefore considering complete:\n- [ ] [Verification item 1]\n- [ ] [Verification item 2]\n- [ ] [Accuracy disclaimers added where needed]\n\n## Examples (if provided)\n[Context or examples from user]\n```\n\n### Model-Specific Adjustments\n\nTune the assembled prompt to the model that will execute it:\n\n- **Current frontier roster**: apply `skills\u002Fblocks\u002Ffrontier-model-routing.md` when choosing between Opus 5, GPT-5.6, Sonnet 5, Fable 5.1, Astra, or cheaper seats.\n- **Claude Fable 5.1 or 5**: apply `skills\u002Fblocks\u002Ffable5-prompting.md` to either model ID. In short: never instruct the model to reveal or transcribe its reasoning; replace step-by-step micromanagement with a boundary plus checkable acceptance criteria; drop \"CRITICAL\"\u002F\"MUST\" emphasis unless strict compliance is required; add grounded-progress and act-when-ready language for long runs.\n- **GPT-6 Astra**: reserve it for a bounded pass after GPT-5.6 Sol fails a hard acceptance test. Do not treat Astra plus GPT-5.6 as independent review.\n- **Codex \u002F GPT-5.6**: apply `docs\u002FGPT-5.6-PROMPTING.md`; give it a concrete outcome, scoped repository constraints, checkable acceptance criteria, non-goals, and the required verification.\n- **Older Claude models**: the fuller template below applies as written.\n\n\n## Phase 6: Output & Iteration\n\n### Present the Prompt\n\n```markdown\n**Generated Meta-Prompt**\n\n[The prompt in the format above]\n\n\n**Techniques Applied:**\n- ✓ Task Decomposition: [Yes\u002FNo, how]\n- ✓ Fresh Eyes Review: [Yes\u002FNo, which experts]\n- ✓ Iterative Verification: [Yes\u002FNo, where]\n- ✓ No Guessing: [Where disclaimers needed]\n- ✓ Specialized Experts: [Which ones assigned]\n\n**Would you like me to:**\n1. Refine any section\n2. Add more verification steps\n3. Adjust the complexity level\n4. Execute this prompt now\n```\n\n\n## Example: Complete Meta-Prompt Generation\n\n### User Request\n\"Create a prompt to help me write API documentation\"\n\n### Generated Prompt\n\n```markdown\n# API Documentation Generator\n\n## Role\nYou are an Expert Technical Writer specializing in API documentation.\nYour documentation will be reviewed by an Expert Developer for accuracy.\nWhen uncertain about behavior, note \"Verify with implementation\" rather than guessing.\n\n## Context\nCreating comprehensive API documentation for developers.\nDocumentation should be usable without reading source code.\n\n## Instructions\n\n### Phase 1: API Discovery\n1. List all endpoints with methods (GET, POST, etc.)\n2. Document request\u002Fresponse schemas\n3. Identify authentication requirements\n4. **Verification:** Cross-reference with OpenAPI spec if available\n\n### Phase 2: Documentation Writing\n1. Write endpoint descriptions (what it does, not how)\n2. Create request examples with all parameters\n3. Create response examples for success and error cases\n4. Document rate limits and constraints\n5. **Verification:** Each example should be valid JSON\u002Fcode\n\n### Phase 3: Review Cycle\nExpert Developer reviews for:\n- Technical accuracy of examples\n- Missing edge cases\n- Unclear descriptions\n\n### Expert Assignments\n- **Expert Technical Writer:** Creates documentation prose\n- **Expert Developer:** Validates examples and accuracy\n\n## Constraints\n- Use consistent terminology throughout\n- Examples must be syntactically valid\n- Note any undocumented or unclear behaviors\n- Accuracy: Mark assumptions with \"Assumed behavior - verify\"\n\n## Output Format\n```markdown\n# [Endpoint Name]\n\n**Method:** [HTTP method]\n**Path:** [\u002Fapi\u002Fpath]\n**Auth:** [Required\u002FOptional\u002FNone]\n\n## Description\n[What this endpoint does]\n\n## Request\n[Parameters, body schema, headers]\n\n## Response\n[Success and error responses with examples]\n\n## Notes\n[Rate limits, deprecation, related endpoints]\n```\n\n## Verification Checklist\n- [ ] All endpoints documented\n- [ ] All examples are valid\n- [ ] Authentication clearly specified\n- [ ] Error responses included\n- [ ] Assumptions marked for verification\n```\n\n\n## Error Handling\n\n### Unclear Requirements\n\n```markdown\nI need a bit more clarity to create an effective prompt.\n\n**Specifically:**\n[Question about the unclear part]\n\n[Offer 2-3 options if applicable]\n```\n\n### Over-Complex Request\n\n```markdown\nThis task has [N] distinct components. I recommend:\n\n1. **Split into multiple prompts** - One per major component\n2. **Simplify scope** - Focus on [core element] first\n3. **Proceed as-is** - Full complexity, longer prompt\n\nWhich approach works best for you?\n```\n\n### Can't Apply Techniques\n\nIf techniques don't fit the task:\n\n```markdown\nℹ️ **Note on Techniques**\n\nThis task is straightforward enough that some techniques\ndon't apply:\n\n- Task Decomposition: Not needed (single step)\n- Fresh Eyes: [Explain why\u002Fwhy not]\n- Specialized Experts: Not needed (single domain)\n\nThe generated prompt focuses on clarity and verification instead.\n```\n\n\n## Integration\n\n### With skill-content-pipeline\nGenerate prompts for content creation based on anatomy guides.\n\n### With skill-thought-partner\nTransform brainstorming insights into actionable prompts.\n\n### With skill-prd\nEnhance PRD generation with meta-prompting techniques.\n\n### With flow-develop\nGenerate implementation prompts with built-in verification.\n\n\n## The Bottom Line\n\n```\nMeta-prompt → Decompose → Assign experts → Build verification → Generate\nOtherwise → Vague prompts → Hallucination → Unreliable output\n```\n\n**Structure breeds reliability. Verification breeds accuracy. Experts breed quality.**\n",{"name":5,"description":7,"disable-model-invocation":46},true,"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fnyldn\u002Fclaude-octopus\u002Fskills\u002Fskill-meta-prompt",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":46},[59,62,65],{"tool":60,"command":61},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill skill-meta-prompt",{"tool":63,"command":64},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill skill-meta-prompt",{"tool":66,"command":67},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill skill-meta-prompt","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnyldn\u002Fclaude-octopus\u002Fskills\u002Fskill-meta-prompt\u002FSKILL.md",[70],{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"agents\u002Fopenai.yaml","REFERENCE","参考文档",172,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnyldn\u002Fclaude-octopus\u002Fskills\u002Fskill-meta-prompt\u002Fagents\u002Fopenai.yaml",[77,87,95,103,111,119],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":82,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":86},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":91,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":86},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":99,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":86},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":107,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":86},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":115,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":86},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":123,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":86},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]