{"id":"a463060b-ff13-4c40-9d48-5958dbca1ee3","entityType":"agent","slug":"clawhub-autogame-17-prompt-optimizer","name":"Prompt Optimizer","canonicalUrl":"https://www.xpersona.co/agent/clawhub-autogame-17-prompt-optimizer","canonicalPath":"/agent/clawhub-autogame-17-prompt-optimizer","generatedAt":"2026-10-09T22:11:41.834Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"description":"Evaluate, optimize, and enhance prompts using 58 proven prompting techniques. Use when user asks to improve, optimize, or analyze a prompt; when a prompt nee... Skill: Prompt Optimizer Owner: autogame-17 Summary: Evaluate, optimize, and enhance prompts using 58 proven prompting techniques. Use when user asks to improve, optimize, or analyze a prompt; when a prompt nee... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-02-17T15:04:16.804Z | user batch sync Archive index: Archive v1.0.0: 7 files, 16817 bytes Files: _meta.json (135b), index.js (3749b), package.json (351b), re","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 438 downloads reported by the source. Last updated 4/15/2026.","installCommand":"clawhub skill install kn7apafdj4thknczrgxdzfd2v1808svf:prompt-optimizer","sourceUrl":"https://clawhub.ai/autogame-17/prompt-optimizer","homepage":"https://clawhub.ai/autogame-17/prompt-optimizer","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/autogame-17/prompt-optimizer","kind":"source"}],"safetyScore":84,"overallRank":62,"popularityScore":53,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Evaluate, optimize, and enhance prompts using 58 proven prompting techniques. Use when user asks to improve, optimize, or analyze a prompt; when a prompt nee..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"stars":null,"forks":null,"downloads":438,"packageName":null,"latestVersion":"1.0.0","tractionLabel":"438 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-03-01T05:56:00.914Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T00:45:39.800Z","lastCrawledAt":"2026-03-01T05:56:00.914Z","lastIndexedAt":null,"nextCrawlAt":"2026-03-02T05:56:00.914Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.0","createdAt":"2026-02-17T15:04:16.804Z","changelog":"batch sync","fileCount":7,"zipByteSize":16817}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install kn7apafdj4thknczrgxdzfd2v1808svf:prompt-optimizer","setupComplexity":"low","setupSteps":["Node.js workspace detected. Install dependencies securely: run `npm ci --ignore-scripts` to prevent post-install lifecycle triggers from running arbitrary code, then selectively audit the dependency tree.","Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-autogame-17-prompt-optimizer/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-autogame-17-prompt-optimizer/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-autogame-17-prompt-optimizer/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-autogame-17-prompt-optimizer/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-autogame-17-prompt-optimizer/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-autogame-17-prompt-optimizer/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T22:11:41.833Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-autogame-17-prompt-optimizer/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-autogame-17-prompt-optimizer/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-autogame-17-prompt-optimizer/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-autogame-17-prompt-optimizer/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"readme":"Skill: Prompt Optimizer\n\nOwner: autogame-17\n\nSummary: Evaluate, optimize, and enhance prompts using 58 proven prompting techniques. Use when user asks to improve, optimize, or analyze a prompt; when a prompt nee...\n\nTags: latest:1.0.0\n\nVersion history:\n\nv1.0.0 | 2026-02-17T15:04:16.804Z | user\n\nbatch sync\n\nArchive index:\n\nArchive v1.0.0: 7 files, 16817 bytes\n\nFiles: _meta.json (135b), index.js (3749b), package.json (351b), references/prompt-techniques.md (21102b), references/quality-framework.md (14376b), scripts/test.js (926b), SKILL.md (1464b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: prompt-optimizer\ndescription: Evaluate, optimize, and enhance prompts using 58 proven prompting techniques. Use when user asks to improve, optimize, or analyze a prompt; when a prompt needs better clarity, specificity, or structure; or when generating prompt variations for different use cases. Covers quality assessment, targeted improvements, and automatic optimization across techniques like CoT, few-shot learning, role-play, and 50+ more.\n---\n\n# Prompt Optimizer\n\nA Node.js implementation of 58 proven prompting techniques cataloged in `references/prompt-techniques.md`.\n\n## Usage\n\n### 1. List Available Techniques\nSee all 58 techniques with their IDs and descriptions.\n```bash\nnode skills/prompt-optimizer/index.js list\n```\n\n### 2. Get Technique Details\nView the template and purpose of a specific technique.\n```bash\nnode skills/prompt-optimizer/index.js get <technique_name>\n```\nExample: `node skills/prompt-optimizer/index.js get \"Chain of Thought\"`\n\n### 3. Optimize a Prompt\nApply a specific technique's template to your prompt.\n```bash\nnode skills/prompt-optimizer/index.js optimize \"<your_prompt>\" --technique \"<technique_name>\"\n```\nExample:\n```bash\nnode skills/prompt-optimizer/index.js optimize \"Write a python script to reverse a string\" --technique \"Chain of Thought\"\n```\n\n## References\n- `references/prompt-techniques.md`: Full catalog of techniques.\n- `references/quality-framework.md`: Framework for evaluating prompt quality manually.\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn7apafdj4thknczrgxdzfd2v1808svf\",\n  \"slug\": \"prompt-optimizer\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1771340656804\n}\n\nFile v1.0.0:references/prompt-techniques.md\n\n# Prompt Techniques Catalog\n\nComplete catalog of 58 proven prompting techniques organized by category.\n\n## Table of Contents\n\n- [Reasoning Techniques](#reasoning-techniques)\n- [Context Techniques](#context-techniques)\n- [Creative Techniques](#creative-techniques)\n- [Structural Techniques](#structural-techniques)\n- [Control Techniques](#control-techniques)\n- [Meta Techniques](#meta-techniques)\n\n---\n\n## Reasoning Techniques\n\n### 1. Chain of Thought (CoT)\n**Purpose:** Encourage step-by-step reasoning before final answer\n**When to use:** Math problems, logic puzzles, complex analysis\n**Template:**\n```\n[Task]\n\nLet's think step by step:\n1. [First step reasoning]\n2. [Second step reasoning]\n3. [Continue reasoning...]\n\nFinal answer: [Conclusion]\n```\n**Example:** \"Solve: 2x + 5 = 13. Let's think step by step: 1. Subtract 5 from both sides: 2x = 8. 2. Divide by 2: x = 4.\"\n\n---\n\n### 2. Tree of Thoughts\n**Purpose:** Explore multiple reasoning branches before conclusion\n**When to use:** Complex decisions, strategic planning, creative problem solving\n**Template:**\n```\n[Task]\n\nExplore multiple possible approaches:\n\nApproach 1: [Description]\n- Reasoning: [Why this approach]\n- Outcome: [Expected result]\n\nApproach 2: [Description]\n- Reasoning: [Why this approach]\n- Outcome: [Expected result]\n\nCompare approaches and select the best one.\n```\n\n---\n\n### 3. Least-to-Most Prompting\n**Purpose:** Break complex tasks into sub-problems solved sequentially\n**When to use:** Multi-step reasoning, complex analysis\n**Template:**\n```\n[Complex Task]\n\nFirst, identify the sub-problems that need to be solved:\n1. [Sub-problem 1]\n2. [Sub-problem 2]\n3. [Sub-problem 3]\n\nNow solve them in order:\n1. [Solve sub-problem 1]\n2. [Solve sub-problem 2 using results from 1]\n3. [Solve sub-problem 3 using results from 1-2]\n\nFinal solution: [Combine results]\n```\n\n---\n\n### 4. Self-Consistency\n**Purpose:** Generate multiple reasoning paths and select most consistent answer\n**When to use:** Ambiguous problems, tasks requiring high confidence\n**Template:**\n```\n[Task]\n\nGenerate 3 different approaches to solve this:\n\nApproach 1:\n[Reasoning 1]\nAnswer: [Answer 1]\n\nApproach 2:\n[Reasoning 2]\nAnswer: [Answer 2]\n\nApproach 3:\n[Reasoning 3]\nAnswer: [Answer 3]\n\nMost common answer: [Select consistent answer]\n```\n\n---\n\n### 5. Reasoning via Planning\n**Purpose:** Explicitly plan execution before acting\n**When to use:** Multi-stage tasks, projects, workflows\n**Template:**\n```\n[Task]\n\nPlanning Phase:\n1. What are the key milestones?\n2. What resources are needed?\n3. What are potential obstacles?\n\nExecution Plan:\nStep 1: [Description]\nStep 2: [Description]\nStep 3: [Description]\n\nNow execute the plan:\n[Detailed execution]\n```\n\n---\n\n### 6. Decomposition\n**Purpose:** Break down complex problems into manageable components\n**When to use:** Large-scale analysis, system design\n**Template:**\n```\n[Complex Problem]\n\nDecompose into components:\n\nComponent 1: [Name]\n- Definition: [What it includes]\n- Considerations: [Key factors]\n\nComponent 2: [Name]\n- Definition: [What it includes]\n- Considerations: [Key factors]\n\nNow analyze each component:\n[Analysis for each]\n```\n\n---\n\n### 7. Analogical Reasoning\n**Purpose:** Use analogies to explain complex concepts\n**When to use:** Technical explanations, teaching, making abstract ideas concrete\n**Template:**\n```\n[Complex Concept]\n\nExplain using an analogy:\n\nAnalogy: [Similar familiar situation]\n- Similarities: [What's comparable]\n- Differences: [What's different]\n- Key insight: [What the analogy reveals]\n\nExplanation: [Use analogy to explain]\n```\n\n---\n\n## Context Techniques\n\n### 8. Few-Shot Learning\n**Purpose:** Provide examples to guide output format and style\n**When to use:** Pattern recognition, format-specific tasks, style transfer\n**Template:**\n```\n[Task description]\n\nExample 1:\nInput: [Example input]\nOutput: [Example output]\n\nExample 2:\nInput: [Example input]\nOutput: [Example output]\n\nExample 3:\nInput: [Example input]\nOutput: [Example output]\n\nNow, new input: [Target input]\nOutput:\n```\n\n---\n\n### 9. Zero-Shot Chain of Thought\n**Purpose:** Combine CoT reasoning without examples\n**When to use:** Quick reasoning tasks when examples aren't available\n**Template:**\n```\n[Task]\n\nLet's think step by step:\n\n[Reasoning steps]\n\nTherefore, the answer is:\n```\n\n---\n\n### 10. Context Reframing\n**Purpose:** Provide broader context to frame the task properly\n**When to use:** Misaligned responses, when model misses the point\n**Template:**\n```\nContext:\n[Background information]\n[Domain knowledge]\n[Relevant constraints]\n\nTask:\n[Main request]\n```\n\n---\n\n### 11. Knowledge Injection\n**Purpose:** Provide specific domain knowledge not in training data\n**When to use:** Specialized domains, recent events, proprietary information\n**Template:**\n```\nDomain Knowledge:\n[Specific facts/data]\n[Technical details]\n[Relevant information]\n\nTask: [Apply this knowledge]\n```\n\n---\n\n### 12. Scenario-Based\n**Purpose:** Place task in realistic scenario for better context\n**When to use:** Practical applications, training, real-world simulation\n**Template:**\n```\nScenario:\n[Describe realistic situation]\n[Set the scene]\n[Establish context]\n\nIn this scenario, [task]:\n[Specific request]\n```\n\n---\n\n### 13. Reflection\n**Purpose:** Ask model to reflect on its own output before finalizing\n**When to use:** Quality-critical tasks, complex reasoning\n**Template:**\n```\n[Task]\n\nInitial response:\n[Generate answer]\n\nNow reflect:\n- What assumptions did I make?\n- Are there any weaknesses in this response?\n- What could be improved?\n\nFinal refined response:\n[Improved answer]\n```\n\n---\n\n### 14. Self-Correction\n**Purpose:** Explicitly ask model to identify and fix errors\n**When to use:** Tasks prone to mistakes, debugging, quality assurance\n**Template:**\n```\n[Task]\n\nFirst attempt:\n[Generate answer]\n\nCritique:\n[Identify any errors or issues]\n\nCorrected attempt:\n[Fix identified issues]\n```\n\n---\n\n## Creative Techniques\n\n### 15. Role-Play\n**Purpose:** Assign a specific persona or role to the model\n**When to use:** Specialized expertise, creative writing, specific perspectives\n**Template:**\n```\nYou are an expert [role] with [qualifications].\n\nRole characteristics:\n- Expertise in [specific areas]\n- Typical tone: [professional, casual, academic, etc.]\n- Key considerations: [what this role cares about]\n\nTask: [Request in character]\n```\n\n---\n\n### 16. Creative Persona\n**Purpose:** Embody a creative identity for artistic or innovative output\n**When to use:** Creative writing, art direction, innovative thinking\n**Template:**\n```\nYou are a [creative identity - e.g., visionary artist, innovative designer].\n\nStyle characteristics:\n- Aesthetic: [description]\n- Approach: [how you create]\n- Inspirations: [who influences you]\n\nCreate: [Creative task]\n```\n\n---\n\n### 17. Brainstorming Mode\n**Purpose:** Generate quantity over quality, defer judgment\n**When to use:** Idea generation, exploring possibilities\n**Template:**\n```\nTask: [Brainstorming topic]\n\nGenerate 20+ ideas. Focus on quantity. Don't judge or filter.\nEmbrace wild and unconventional ideas.\n\nIdeas:\n[List ideas rapidly]\n```\n\n---\n\n### 18. SCAMPER\n**Purpose:** Use systematic creativity technique (Substitute, Combine, Adapt, Modify, Put to other uses, Eliminate, Reverse)\n**When to use:** Innovation, improving existing ideas, creative problem solving\n**Template:**\n```\nIdea to improve: [Current idea]\n\nApply SCAMPER:\n\nSubstitute: What can be replaced?\n[Substitutions]\n\nCombine: What can be merged?\n[Combinations]\n\nAdapt: What can be borrowed from elsewhere?\n[Adaptations]\n\nModify: What can be changed?\n[Modifications]\n\nPut to other uses: How else can this be used?\n[Alternative uses]\n\nEliminate: What's unnecessary?\n[Eliminations]\n\nReverse: What can be reversed?\n[Reversals]\n\nBest new ideas:\n[Select top ideas from SCAMPER]\n```\n\n---\n\n### 19. Creative Constraints\n**Purpose:** Use limitations to spur creativity\n**When to use:** Artistic tasks, design, innovative problem solving\n**Template:**\n```\nCreate: [Creative task]\n\nConstraints:\n1. [Constraint 1 - e.g., exactly 100 words]\n2. [Constraint 2 - e.g., cannot use the letter 'e']\n3. [Constraint 3 - e.g., must use a specific metaphor]\n\nWork:\n[Creative output within constraints]\n```\n\n---\n\n### 20. Storytelling Format\n**Purpose:** Present information as a narrative\n**When to use:** Making content engaging, teaching, presentations\n**Template:**\n```\nTopic: [Information to convey]\n\nTell it as a story with:\n- A compelling opening\n- A clear conflict or challenge\n- A journey or process\n- A satisfying resolution\n\nStory:\n[Narrative format]\n```\n\n---\n\n### 21. Metaphorical Thinking\n**Purpose:** Use metaphors to explain or create\n**When to use:** Explaining abstract concepts, creative writing\n**Template:**\n```\nConcept: [To explain]\n\nUse a powerful metaphor to explain this.\n\nMetaphor: [The metaphor]\nExplanation: [How the metaphor maps to the concept]\n```\n\n---\n\n## Structural Techniques\n\n### 22. Template-Based\n**Purpose:** Use structured template for consistent output\n**When to use:** Repeated tasks, standard formats, documentation\n**Template:**\n```\n[Task]\n\nUse this template:\n\n## [Section 1]\n[Content]\n\n## [Section 2]\n[Content]\n\n## [Section 3]\n[Content]\n\nFill in the template:\n[Output following structure]\n```\n\n---\n\n### 23. Framework Application\n**Purpose:** Apply established frameworks (SWOT, STAR, etc.)\n**When to use:** Business analysis, strategic planning, structured thinking\n**Template:**\n```\n[Analysis task]\n\nApply the [Framework Name] framework:\n\n[Framework component 1]: [Content]\n[Framework component 2]: [Content]\n[Framework component 3]: [Content]\n[Framework component 4]: [Content]\n\nAnalysis:\n[Interpretation of framework output]\n```\n\n---\n\n### 24. Checklist-Driven\n**Purpose:** Ensure all requirements are met with a checklist\n**When to use:** Quality assurance, comprehensive tasks, validation\n**Template:**\n```\n[Task]\n\nBefore finalizing, ensure:\n\n☐ [Requirement 1]\n☐ [Requirement 2]\n☐ [Requirement 3]\n☐ [Requirement 4]\n☐ [Requirement 5]\n\nCompleted output:\n[Only after checking all items]\n```\n\n---\n\n### 25. Format Specification\n**Purpose:** Explicitly define output format\n**When to use:** Data extraction, specific document types, structured output\n**Template:**\n```\n[Task]\n\nOutput format:\n- JSON with keys: [key1], [key2], [key3]\n- Or Markdown table with columns: [col1], [col2], [col3]\n- Or bulleted list\n- Or numbered list\n\nSpecify which format and provide:\n[Formatted output]\n```\n\n---\n\n### 26. Progressive Disclosure\n**Purpose:** Reveal information gradually\n**When to use:** Teaching, complex explanations, tutorials\n**Template:**\n```\n[Topic]\n\nFirst, start with the basics:\n[Simple overview]\n\nNow build on that with intermediate concepts:\n[Add complexity]\n\nFinally, advanced details:\n[Deep dive]\n\nSummary:\n[Tie it all together]\n```\n\n---\n\n### 27. Modular Breakdown\n**Purpose:** Divide task into independent, reusable modules\n**When to use:** Complex systems, code generation, curriculum design\n**Template:**\n```\n[Complex Task]\n\nBreak into modules:\n\nModule A: [Name and purpose]\n- Input: [What it needs]\n- Output: [What it produces]\n- Dependencies: [What it needs from other modules]\n\nModule B: [Name and purpose]\n[Same structure]\n\nModule C: [Name and purpose]\n[Same structure]\n\nNow implement each module:\n[Detailed implementation]\n```\n\n---\n\n## Control Techniques\n\n### 28. Negative Constraints\n**Purpose:** Specify what NOT to do\n**When to use:** Avoiding specific errors, filtering out unwanted content\n**Template:**\n```\n[Task]\n\nDo NOT:\n- [Prohibition 1]\n- [Prohibition 2]\n- [Prohibition 3]\n\nAllowed approach:\n[Positive guidance]\n```\n\n---\n\n### 29. Output Constraints\n**Purpose:** Limit output length, complexity, or format\n**When to use:** Conciseness requirements, token limits, specific formats\n**Template:**\n```\n[Task]\n\nConstraints:\n- Maximum length: [e.g., 200 words]\n- Must include: [Required elements]\n- Must exclude: [Forbidden elements]\n- Format: [e.g., bullet list]\n\nOutput:\n[Constrained result]\n```\n\n---\n\n### 30. Tone Specification\n**Purpose:** Define the voice and attitude of the output\n**When to use:** Brand alignment, audience targeting, appropriate communication\n**Template:**\n```\n[Task]\n\nTone: [Professional / Friendly / Academic / Casual / etc.]\nVoice: [First person / Third person / etc.]\nStyle: [Formal / Conversational / Technical / etc.]\n\nOutput:\n[Content matching specified tone]\n```\n\n---\n\n### 31. Quality Criteria\n**Purpose:** Define standards the output must meet\n**When to use:** Quality-critical work, evaluation tasks, deliverables\n**Template:**\n```\n[Task]\n\nQuality criteria:\n☐ [Criterion 1 - e.g., \"All claims must be supported by evidence\"]\n☐ [Criterion 2]\n☐ [Criterion 3]\n\nSelf-evaluation after output:\n[Check against criteria]\n```\n\n---\n\n### 32. Step-by-Step Instructions\n**Purpose:** Provide explicit procedural guidance\n**When to use:** How-to tasks, tutorials, process documentation\n**Template:**\n```\n[Task]\n\nFollow these steps:\n\nStep 1: [Action]\n[Detail on how to do it]\n\nStep 2: [Action]\n[Detail on how to do it]\n\nStep 3: [Action]\n[Detail on how to do it]\n\nContinue to completion.\n```\n\n---\n\n### 33. Guided Exploration\n**Purpose:** Direct exploration while allowing discovery\n**When to use:** Learning, research, open-ended investigation\n**Template:**\n```\n[Exploration topic]\n\nStart by exploring:\n[Initial direction to look]\n\nThen investigate:\n[Next area to explore]\n\nFinally, examine:\n[Final area to check]\n\nSynthesize findings:\n[Summary of discoveries]\n```\n\n---\n\n### 34. Controlled Generation\n**Purpose:** Use specific constraints to guide output\n**When to use:** Specific vocabulary, terminology, style requirements\n**Template:**\n```\n[Task]\n\nMust use these terms:\n- [Term 1]\n- [Term 2]\n- [Term 3]\n\nMust avoid these terms:\n- [Term 1]\n- [Term 2]\n\nOutput:\n[Content respecting constraints]\n```\n\n---\n\n## Meta Techniques\n\n### 35. Prompt Chaining\n**Purpose:** Chain multiple prompts together for complex tasks\n**When to use:** Multi-stage workflows, complex processing\n**Template:**\n```\nStage 1: [First task]\n[Generate intermediate output]\n\nStage 2: [Use stage 1 output]\n[Process further]\n\nStage 3: [Use stage 2 output]\n[Final result]\n```\n\n---\n\n### 36. Multi-Persona Debate\n**Purpose:** Use different personas to debate and reach consensus\n**When to use:** Complex decisions, exploring multiple perspectives\n**Template:**\n```\n[Decision/Question]\n\nPersona A: [Expert 1 perspective]\n[Their argument]\n\nPersona B: [Expert 2 perspective]\n[Their argument]\n\nPersona C: [Expert 3 perspective]\n[Their argument]\n\nSynthesis:\n[Weigh arguments and provide balanced conclusion]\n```\n\n---\n\n### 37. Self-Evaluation\n**Purpose:** Ask model to rate and improve its own output\n**When to use:** Quality improvement, iterative refinement\n**Template:**\n```\n[Task]\n\nInitial output:\n[Generate answer]\n\nNow evaluate:\n- Quality rating (1-10): [Score]\n- What's good: [Strengths]\n- What needs improvement: [Weaknesses]\n\nImproved version:\n[Address weaknesses]\n```\n\n---\n\n### 38. Verification Steps\n**Purpose:** Include explicit verification in the process\n**When to use:** Critical tasks, fact-checking, validation\n**Template:**\n```\n[Task]\n\nStep 1: [Initial generation]\n\nStep 2: Verify:\n- Check [validation criteria]\n- Cross-reference [sources/data]\n- Identify potential errors\n\nStep 3: Correct and finalize:\n[Address any issues found]\n```\n\n---\n\n### 39. Meta-Cognitive Prompting\n**Purpose:** Explicitly reason about the reasoning process\n**When to use:** Complex problem solving, teaching reasoning\n**Template:**\n```\n[Task]\n\nBefore answering, think about:\n1. What approach will I use?\n2. What are the key challenges?\n3. How will I structure my reasoning?\n\nApproach: [Selected method]\nChallenges: [Anticipated difficulties]\nStructure: [Organization plan]\n\nNow solve:\n[Detailed reasoning and solution]\n\nReflection on process:\n[What worked well, what didn't]\n```\n\n---\n\n### 40. Temperature Control\n**Purpose:** Adjust creativity vs. precision through prompt instruction\n**When to use:** Need more creative or more deterministic output\n**Template:**\n```\n[Task]\n\nBe very creative and explore diverse ideas: [For high creativity]\nOR\n\nBe precise and stick to the most likely answer: [For high precision]\n```\n\n---\n\n### 41. Iterative Refinement\n**Purpose:** Generate, evaluate, and refine multiple times\n**When to use:** Quality-critical work, complex creative tasks\n**Template:**\n```\n[Task]\n\nDraft 1:\n[Initial attempt]\n\nCritique 1:\n[What to improve]\n\nDraft 2:\n[Second attempt incorporating feedback]\n\nCritique 2:\n[Further improvements]\n\nFinal version:\n[Polished result]\n```\n\n---\n\n### 42. Perspective Taking\n**Purpose:** Explicitly consider different viewpoints\n**When to use:** Sensitive topics, diverse audiences, balanced analysis\n**Template:**\n```\n[Topic]\n\nConsider from these perspectives:\n\nPerspective 1: [Group/Stakeholder]\n- Their view: [Position]\n- Key concerns: [What matters to them]\n\nPerspective 2: [Group/Stakeholder]\n- Their view: [Position]\n- Key concerns: [What matters to them]\n\nPerspective 3: [Group/Stakeholder]\n- Their view: [Position]\n- Key concerns: [What matters to them]\n\nBalanced analysis:\n[Synthesis of perspectives]\n```\n\n---\n\n## Additional Techniques (43-58)\n\n### 43. Compare and Contrast\n**Purpose:** Systematically compare multiple items\n**Template:** \"Compare X and Y on: criteria 1, criteria 2, criteria 3. Highlight similarities and differences.\"\n\n### 44. Pros and Cons\n**Purpose:** Weigh advantages and disadvantages\n**Template:** \"List pros and cons of [decision/topic]. Provide balanced analysis.\"\n\n### 45. Root Cause Analysis\n**Purpose:** Identify underlying causes, not just symptoms\n**Template:** \"For [problem], apply 5 Whys to find root cause. 1. Why? [Answer]. 2. Why? [Answer]. Continue 5 times.\"\n\n### 46. First Principles\n**Purpose:** Break down to fundamental truths and build up\n**Template:** \"Analyze [topic] from first principles. What are the fundamental truths? What can be concluded from them?\"\n\n### 47. Worst-Case Scenario\n**Purpose:** Plan for potential failures\n**Template:** \"Consider worst-case scenarios for [plan]. What could go wrong? How to mitigate?\"\n\n### 48. Best-Case Scenario\n**Purpose:** Plan for optimal outcomes\n**Template:** \"What's the best possible outcome for [initiative]? What conditions would enable this?\"\n\n### 49. Devil's Advocate\n**Purpose:** Challenge assumptions and arguments\n**Template:** \"Play devil's advocate for [position]. Argue against it strongly, then rebut those arguments.\"\n\n### 50. Reverse Engineering\n**Purpose:** Work backwards from desired outcome\n**Template:** \"To achieve [goal], work backwards. What must happen right before that? And before that?\"\n\n### 51. Gap Analysis\n**Purpose:** Identify difference between current and desired state\n**Template:** \"Current state: [now]. Desired state: [goal]. Gap analysis: What's missing? How to bridge?\"\n\n### 52. Risk Assessment\n**Purpose:** Identify and evaluate risks\n**Template:** \"For [project/situation], identify risks. Rate by likelihood (Low/Med/High) and impact (Low/Med/High). Suggest mitigations.\"\n\n### 53. Value Proposition\n**Purpose:** Articulate value and benefits clearly\n**Template:** \"What's the value proposition of [product/idea]? For [target audience], what problem does it solve and what benefit does it provide?\"\n\n### 54. Elevator Pitch\n**Purpose:** Convince quickly in short format\n**Template:** \"Create a 30-second elevator pitch for [idea/product]. Hook: [Grab attention]. Value: [What's offered]. Call to action: [Next step].\"\n\n### 55. Before-After-Bridge\n**Purpose:** Persuasive copywriting framework\n**Template:** \"Before: [Current painful situation]. After: [Desired future state]. Bridge: [How to get from before to after with your solution].\"\n\n### 56. Problem-Agitation-Solution\n**Purpose:** Persuasive marketing framework\n**Template:** \"Problem: [Identify pain]. Agitation: [Make it worse/emotional]. Solution: [Your answer to the problem].\"\n\n### 57. Feature-Benefit-Proof\n**Purpose:** Sales and marketing framework\n**Template:** \"For each feature: 1) What it does (Feature), 2) What it delivers (Benefit), 3) Evidence (Proof).\"\n\n### 58. Situational Analysis\n**Purpose:** Comprehensive context assessment\n**Template:** \"Analyze situation: Internal factors (strengths, weaknesses). External factors (opportunities, threats). Recommendations based on analysis.\"\n\n---\n\n## Technique Selection Guide\n\nUse this guide to choose the right technique:\n\n| Need | Best Technique(s) |\n|------|------------------|\n| Complex reasoning | CoT, Tree of Thoughts, Decomposition |\n| Format consistency | Few-Shot, Template-Based |\n| Creative output | Role-Play, Brainstorming, Creative Persona |\n| Quality assurance | Self-Correction, Verification, Reflection |\n| Teaching/explaining | Progressive Disclosure, Analogical Reasoning |\n| Structured output | Format Specification, Checklist-Driven |\n| Multiple perspectives | Multi-Persona Debate, Perspective Taking |\n| Decision making | Compare/Contrast, Pros/Cons, Risk Assessment |\n\n---\n\n**Note:** Many techniques work well in combination. For example, Role-Play + CoT provides expert reasoning with step-by-step structure. Experiment with combinations for optimal results.\n\nFile v1.0.0:references/quality-framework.md\n\n# Prompt Quality Evaluation Framework\n\nSystematic framework for evaluating prompt quality across multiple dimensions.\n\n## Table of Contents\n\n- [Evaluation Dimensions](#evaluation-dimensions)\n- [Scoring Rubric](#scoring-rubric)\n- [Quality Assessment Process](#quality-assessment-process)\n- [Common Anti-Patterns](#common-anti-patterns)\n- [Quality Benchmarks](#quality-benchmarks)\n\n---\n\n## Evaluation Dimensions\n\n### 1. Clarity (清晰度)\n\n**Definition:** How unambiguous and easy to understand the prompt is.\n\n**Key Questions:**\n- Can the task be understood on first read?\n- Are there multiple possible interpretations?\n- Is the language precise and specific?\n- Are technical terms defined if needed?\n\n**Indicators of Good Clarity:**\n✓ Clear, unambiguous language\n✓ Specific task description\n✓ Defined technical terms\n✓ Single interpretation\n\n**Indicators of Poor Clarity:**\n✗ Vague or ambiguous phrasing\n✗ Multiple possible interpretations\n✗ Undefined jargon\n✗ Unclear what's being asked\n\n**Examples:**\n- Poor: \"Write something about AI\"\n- Good: \"Write a 500-word article about the impact of AI on healthcare\"\n- Excellent: \"Write a 500-word article for healthcare professionals about three specific ways AI is transforming patient care, including one real-world example for each\"\n\n---\n\n### 2. Specificity (具体性)\n\n**Definition:** How well the prompt defines requirements, constraints, and expectations.\n\n**Key Questions:**\n- Are the deliverables clearly defined?\n- Are constraints (length, format, style) specified?\n- Is the scope clearly bounded?\n- Are success criteria explicit?\n\n**Indicators of Good Specificity:**\n✓ Clear deliverable definition\n✓ Explicit constraints\n✓ Bounded scope\n✓ Defined success criteria\n\n**Indicators of Poor Specificity:**\n✗ Open-ended without boundaries\n✗ No format or length guidance\n✗ Unclear what \"good\" looks like\n✗ Missing context about audience/purpose\n\n**Examples:**\n- Poor: \"Write an essay about climate change\"\n- Good: \"Write a 1,200-word persuasive essay about climate change for high school students, arguing for renewable energy investment\"\n- Excellent: \"Write a 1,200-word persuasive essay for high school students arguing that governments should increase renewable energy investment by 50% over the next 5 years. Include: 1) three specific benefits, 2) address two counterarguments, 3) end with a call to action for students\"\n\n---\n\n### 3. Structure (结构)\n\n**Definition:** How well-organized and logical the prompt is.\n\n**Key Questions:**\n- Is information organized logically?\n- Are related concepts grouped together?\n- Is there a clear flow from context to task?\n- Are complex tasks broken down?\n\n**Indicators of Good Structure:**\n✓ Logical organization\n✓ Clear sections or components\n✓ Appropriate ordering of information\n✓ Complex tasks broken into steps\n\n**Indicators of Poor Structure:**\n✗ Disorganized information\n✓ Jumping between topics\n✓ Important details buried\n✓ No clear flow or progression\n\n**Examples:**\n- Poor: \"Here are some things: the deadline is Friday, it's for marketing, we need a blog post, the topic is product launch, keep it casual\"\n\n- Good:\n```\nContext: Marketing blog post\nTopic: Product launch\nAudience: Current customers\nTone: Casual and friendly\n\nRequirements:\n- Deadline: Friday\n- Length: 800-1000 words\n- Include: 3 key features, customer testimonial\n```\n\n- Excellent:\n```\n# Marketing Blog Post\n\n**Topic:** Product Launch Announcement\n\n**Target Audience:** Existing customers\n\n**Tone:** Casual, friendly, exciting\n\n**Content Requirements:**\n1. Introduction: Hook readers with the main benefit\n2. Feature highlights: 3 key features with use cases\n3. Social proof: Include 1-2 customer quotes\n4. Call to action: Clear next step\n\n**Technical Requirements:**\n- Length: 800-1000 words\n- Format: Blog post with H2 headers\n- Deadline: Friday, 5 PM\n```\n\n---\n\n### 4. Completeness (完整性)\n\n**Definition:** Whether all necessary context, background, and information is provided.\n\n**Key Questions:**\n- Does the model have enough context to understand the task?\n- Is background information included?\n- Are relevant constraints or preferences mentioned?\n- Is the audience and purpose clear?\n\n**Indicators of Good Completeness:**\n✓ Sufficient context provided\n✓ Background information included\n✓ Constraints and preferences specified\n✓ Audience and purpose clear\n\n**Indicators of Poor Completeness:**\n✗ Missing key context\n✗ No background on topic\n✗ Important constraints omitted\n✗ Unclear who it's for or why\n\n**Examples:**\n- Poor: \"Write a proposal\"\n\n- Good: \"Write a proposal for a $50,000 budget to implement a new CRM system for our 50-person sales team\"\n\n- Excellent:\n```\n**Task:** Write a project proposal for CRM implementation\n\n**Context:**\n- Company size: 50 employees (30 in sales)\n- Current process: Manual spreadsheet tracking\n- Pain points: Lost leads, missed follow-ups, no reporting\n- Goal: Improve lead conversion by 20% in 6 months\n\n**Proposal Requirements:**\n- Budget: $50,000 maximum\n- Timeline: 6-month implementation\n- Include: Software recommendation, implementation plan, training approach, ROI projection\n- Target audience: CFO for approval\n```\n\n---\n\n### 5. Tone (语气)\n\n**Definition:** How well the prompt defines the desired voice, style, and attitude.\n\n**Key Questions:**\n- Is the expected tone specified?\n- Does it match the intended audience?\n- Is the style appropriate for the task?\n- Are there constraints on formality?\n\n**Indicators of Good Tone:**\n✓ Clear tone specification\n✓ Appropriate for audience\n✓ Matches task purpose\n✓ Style constraints defined\n\n**Indicators of Poor Tone:**\n✗ No tone guidance\n✓ Tone mismatches audience\n✓ Inconsistent style\n✓ No formality level\n\n**Examples:**\n- Poor: \"Write an email to customers\"\n\n- Good: \"Write an email to customers about a product update. Keep it professional and informative.\"\n\n- Excellent:\n```\n**Task:** Write an email announcing a product update\n\n**Tone:** Professional, friendly, not overly formal\n\n**Style Guidelines:**\n- Use clear, direct language\n- Avoid jargon and technical terms\n- Be enthusiastic but not salesy\n- Include a personal touch (e.g., \"We're excited because...\")\n\n**Audience:** Existing customers who have used the product for 6+ months\n\n**Key Messages:**\n1. What's new\n2. Why it matters to them\n3. How to get it\n4. Support available\n```\n\n---\n\n### 6. Constraints (约束)\n\n**Definition:** How well boundaries, limitations, and requirements are specified.\n\n**Key Questions:**\n- Are length or format constraints clear?\n- Are there things to avoid?\n- Are there specific elements that must be included?\n- Are boundaries on scope defined?\n\n**Indicators of Good Constraints:**\n✓ Clear constraints specified\n✓ What to include defined\n✓ What to avoid defined\n✓ Scope boundaries clear\n\n**Indicators of Poor Constraints:**\n✗ No guidance on limits\n✓ Unclear what to include/exclude\n✓ Open-ended scope\n✗ No quality criteria\n\n**Examples:**\n- Poor: \"Write a story\"\n\n- Good: \"Write a 500-word mystery story with a surprise ending\"\n\n- Excellent:\n```\n**Task:** Write a mystery story\n\n**Constraints:**\n- Length: Exactly 500 words\n- Genre: Classic whodunit\n- Setting: Single location (a train)\n- Characters: 3-5 passengers\n\n**Requirements:**\n- Include: Clues (at least 3), red herring (at least 1), detective character\n- Avoid: supernatural elements, time travel\n- Ending: Surprise reveal that recontextualizes earlier clues\n\n**Style:** Noir, atmospheric, first-person detective narration\n```\n\n---\n\n## Scoring Rubric\n\n### Quality Levels\n\n| Level | Score | Description |\n|-------|-------|-------------|\n| Excellent | 9-10 | Exceeds expectations, minimal improvements possible |\n| Good | 7-8 | Solid quality, minor optimizations would help |\n| Fair | 5-6 | Functional but has clear weaknesses |\n| Poor | 1-4 | Significant issues, needs major revision |\n\n### Dimension Scoring\n\nFor each dimension, rate based on these criteria:\n\n**Excellent (9-10):**\n- Clear, specific, well-structured, complete\n- Examples, constraints, and success criteria provided\n- Little to no ambiguity\n- Model has everything needed\n\n**Good (7-8):**\n- Mostly clear and specific\n- Structure is logical\n- Most context is provided\n- Minor improvements would help\n\n**Fair (5-6):**\n- Some ambiguity present\n- Structure could be improved\n- Missing some context\n- Functional but not optimal\n\n**Poor (1-4):**\n- Multiple interpretations possible\n- Poorly organized\n- Missing key information\n- Model will struggle\n\n### Overall Quality Calculation\n\n**Weighted Average:**\n- Clarity: 20%\n- Specificity: 20%\n- Structure: 15%\n- Completeness: 20%\n- Tone: 10%\n- Constraints: 15%\n\n**Example Calculation:**\n```\nClarity: 8/10 × 0.20 = 1.6\nSpecificity: 7/10 × 0.20 = 1.4\nStructure: 9/10 × 0.15 = 1.35\nCompleteness: 6/10 × 0.20 = 1.2\nTone: 7/10 × 0.10 = 0.7\nConstraints: 5/10 × 0.15 = 0.75\n\nTotal: 7.0/10 = Good\n```\n\n---\n\n## Quality Assessment Process\n\n### Step 1: Initial Scan\nRead the prompt quickly and note:\n- First impression of clarity\n- Obvious missing information\n- Immediate red flags\n\n### Step 2: Dimension-by-Dimension Evaluation\nFor each dimension:\n1. Identify strengths (what works well)\n2. Identify weaknesses (what's missing or unclear)\n3. Provide specific score (1-10)\n4. Note specific improvement opportunities\n\n### Step 3: Calculate Overall Score\nApply weighted average formula.\n\n### Step 4: Generate Recommendations\nBased on dimensions with lowest scores:\n1. Identify applicable techniques from prompt-techniques.md\n2. Prioritize high-impact improvements\n3. Provide concrete suggestions\n\n### Step 5: Create Optimization Plan\nOrganize recommendations into:\n- **Must fix** (critical weaknesses)\n- **Should fix** (important improvements)\n- **Nice to have** (enhancements)\n\n---\n\n## Common Anti-Patterns\n\n### 1. The Ambiguous Ask\n**Problem:** Vague language without clear expectations\n**Example:** \"Make it better\" or \"Fix this\"\n**Fix:** Specify what \"better\" means and what aspects to improve\n\n### 2. The Overload\n**Problem:** Too much information, poor organization\n**Example:** Long paragraphs mixing context, constraints, and tasks\n**Fix:** Use structure, sections, and logical grouping\n\n### 3. The Missing Context\n**Problem:** Insufficient background or audience information\n**Example:** \"Write a blog post\" (no topic, audience, or goal)\n**Fix:** Provide context about topic, audience, purpose, and constraints\n\n### 4. The Moving Target\n**Problem:** Contradictory or evolving requirements\n**Example:** \"Be creative but follow strict guidelines\" without clarification\n**Fix:** Resolve contradictions or make them explicit as trade-offs\n\n### 5. The Assumption\n**Problem:** Assuming model knows domain-specific context\n**Example:** Using technical jargon without explanation\n**Fix:** Define terms or provide background knowledge\n\n### 6. The Kitchen Sink\n**Problem:** Including irrelevant information\n**Example:** 10 paragraphs of background when 2 would suffice\n**Fix:** Focus on what's necessary for the task\n\n### 7. The No-Output\n**Problem:** Unclear what the final deliverable should be\n**Example:** \"Think about X\" without specifying what to produce\n**Fix:** Specify output format, length, and structure\n\n### 8. The Too-Rigid\n**Problem:** Over-constraining to the point of impossibility\n**Example:** 20 constraints that conflict with each other\n**Fix:** Focus on essential constraints, remove non-critical ones\n\n---\n\n## Quality Benchmarks\n\n### By Prompt Type\n\n#### Code Generation\n**Excellent:**\n```\nWrite a Python function to sort a list of dictionaries by a specific key.\n\nRequirements:\n- Function signature: def sort_dicts(list_of_dicts, key, reverse=False)\n- Handle edge cases: empty list, key not found\n- Return: New sorted list (don't modify original)\n- Include docstring with examples\n- Use stable sort (maintain order for equal keys)\n```\n**Score:** 9.5/10\n\n#### Content Creation\n**Excellent:**\n```\nWrite a LinkedIn post announcing our new feature.\n\nContext:\n- Feature name: Smart Scheduling\n- Main benefit: Saves 2 hours/week for users\n- Launch date: Next Monday\n- Target: Existing customers (productivity enthusiasts)\n\nFormat:\n- Length: 150-200 words\n- Tone: Professional but excited\n- Include: One hook, two bullet points on benefits, CTA\n- Emoji: Use sparingly (2-3 max)\n```\n**Score:** 9/10\n\n#### Analysis\n**Excellent:**\n```\nAnalyze the competitive landscape for AI-powered email tools.\n\nScope:\n- Top 5 competitors: [Company A, B, C, D, E]\n- Focus on: Pricing, key features, target market, unique positioning\n\nOutput format:\n- Comparison table with rows for each competitor\n- Columns: Pricing, Key Features (3), Target Market, Differentiation\n- Summary paragraph: Key insights and gaps\n- Bullet list: Opportunities for our product\n```\n**Score**: 9/10\n\n#### Problem Solving\n**Excellent:**\n```\nOur customer support response time is 48 hours (target: 12 hours).\n\nAnalyze the problem and provide a 3-step solution plan.\n\nConsider:\n- Current bottlenecks (we suspect manual triage)\n- Team size: 5 support agents, 500 tickets/week\n- Budget: Can invest up to $10K in tools/training\n\nProvide:\n- Root cause diagnosis\n- 3 prioritized solutions with:\n  * What it is\n  * Expected impact (hours saved)\n  * Cost (time + money)\n  * Implementation timeline\n```\n**Score**: 8.5/10\n\n### Improvement Targets\n\n| Current Score | Target Score | Priority Improvements |\n|---------------|--------------|----------------------|\n| 1-4 (Poor) | 7+ (Good) | Add context, clarify task, structure information |\n| 5-6 (Fair) | 8+ (Very Good) | Specific constraints, examples, refine tone |\n| 7-8 (Good) | 9-10 (Excellent) | Add examples, edge cases, success criteria |\n\n---\n\n## Quick Assessment Checklist\n\nUse this for rapid prompt evaluation:\n\n☐ **Clarity:** Can I understand what's being asked?\n☐ **Specificity:** Are deliverables and constraints clear?\n☐ **Structure:** Is information organized logically?\n☐ **Completeness:** Is there enough context?\n☐ **Tone:** Is the expected voice/style specified?\n☐ **Constraints:** Are boundaries and requirements defined?\n\n**If 5-6 items checked:** Good quality\n**If 3-4 items checked:** Needs improvement\n**If 0-2 items checked:** Major revision needed\n\n---\n\n**Note:** Quality is relative to task complexity and requirements. A simple task may need less detail than a complex one. Adjust expectations accordingly.\n\nFile v1.0.0:package.json\n\n{\n  \"name\": \"prompt-optimizer\",\n  \"version\": \"1.0.0\",\n  \"description\": \"Evaluate, optimize, and enhance prompts using 58 proven prompting techniques.\",\n  \"main\": \"index.js\",\n  \"scripts\": {\n    \"test\": \"node index.js list\"\n  },\n  \"keywords\": [\n    \"prompt\",\n    \"optimizer\",\n    \"ai\",\n    \"techniques\"\n  ],\n  \"author\": \"OpenClaw\",\n  \"license\": \"MIT\"\n}","readmeExcerpt":"Skill: Prompt Optimizer Owner: autogame-17 Summary: Evaluate, optimize, and enhance prompts using 58 proven prompting techniques. Use when user asks to improve, optimize, or analyze a prompt; when a prompt nee... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-02-17T15:04:16.804Z | user batch sync Archive index: Archive v1.0.0: 7 files, 16817 bytes Files: _meta.json (135b), index.js (3749b), package.json (351b), re","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"node skills/prompt-optimizer/index.js list"},{"language":"bash","snippet":"node skills/prompt-optimizer/index.js get <technique_name>"},{"language":"bash","snippet":"node skills/prompt-optimizer/index.js optimize \"<your_prompt>\" --technique \"<technique_name>\""},{"language":"bash","snippet":"node skills/prompt-optimizer/index.js optimize \"Write a python script to reverse a string\" --technique \"Chain of Thought\""},{"language":"text","snippet":"[Task]\n\nLet's think step by step:\n1. [First step reasoning]\n2. [Second step reasoning]\n3. [Continue reasoning...]\n\nFinal answer: [Conclusion]"},{"language":"text","snippet":"[Task]\n\nExplore multiple possible approaches:\n\nApproach 1: [Description]\n- Reasoning: [Why this approach]\n- Outcome: [Expected result]\n\nApproach 2: [Description]\n- Reasoning: [Why this approach]\n- Outcome: [Expected result]\n\nCompare approaches and select the best one."}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: prompt-optimizer\ndescription: Evaluate, optimize, and enhance prompts using 58 proven prompting techniques. Use when user asks to improve, optimize, or analyze a prompt; when a prompt needs better clarity, specificity, or structure; or when generating prompt variations for different use cases. Covers quality assessment, targeted improvements, and automatic optimization across techniques like CoT, few-shot learning, role-play, and 50+ more.\n---\n\n# Prompt Optimizer\n\nA Node.js implementation of 58 proven prompting techniques cataloged in `references/prompt-techniques.md`.\n\n## Usage\n\n### 1. List Available Techniques\nSee all 58 techniques with their IDs and descriptions.\n```bash\nnode skills/prompt-optimizer/index.js list\n```\n\n### 2. Get Technique Details\nView the template and purpose of a specific technique.\n```bash\nnode skills/prompt-optimizer/index.js get <technique_name>\n```\nExample: `node skills/prompt-optimizer/index.js get \"Chain of Thought\"`\n\n### 3. Optimize a Prompt\nApply a specific technique's template to your prompt.\n```bash\nnode skills/prompt-optimizer/index.js optimize \"<your_prompt>\" --technique \"<technique_name>\"\n```\nExample:\n```bash\nnode skills/prompt-optimizer/index.js optimize \"Write a python script to reverse a string\" --technique \"Chain of Thought\"\n```\n\n## References\n- `references/prompt-techniques.md`: Full catalog of techniques.\n- `references/quality-framework.md`: Framework for evaluating prompt quality manually."},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7apafdj4thknczrgxdzfd2v1808svf\",\n  \"slug\": \"prompt-optimizer\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1771340656804\n}"},{"path":"references/prompt-techniques.md","content":"# Prompt Techniques Catalog\n\nComplete catalog of 58 proven prompting techniques organized by category.\n\n## Table of Contents\n\n- [Reasoning Techniques](#reasoning-techniques)\n- [Context Techniques](#context-techniques)\n- [Creative Techniques](#creative-techniques)\n- [Structural Techniques](#structural-techniques)\n- [Control Techniques](#control-techniques)\n- [Meta Techniques](#meta-techniques)\n\n---\n\n## Reasoning Techniques\n\n### 1. Chain of Thought (CoT)\n**Purpose:** Encourage step-by-step reasoning before final answer\n**When to use:** Math problems, logic puzzles, complex analysis\n**Template:**\n```\n[Task]\n\nLet's think step by step:\n1. [First step reasoning]\n2. [Second step reasoning]\n3. [Continue reasoning...]\n\nFinal answer: [Conclusion]\n```\n**Example:** \"Solve: 2x + 5 = 13. Let's think step by step: 1. Subtract 5 from both sides: 2x = 8. 2. Divide by 2: x = 4.\"\n\n---\n\n### 2. Tree of Thoughts\n**Purpose:** Explore multiple reasoning branches before conclusion\n**When to use:** Complex decisions, strategic planning, creative problem solving\n**Template:**\n```\n[Task]\n\nExplore multiple possible approaches:\n\nApproach 1: [Description]\n- Reasoning: [Why this approach]\n- Outcome: [Expected result]\n\nApproach 2: [Description]\n- Reasoning: [Why this approach]\n- Outcome: [Expected result]\n\nCompare approaches and select the best one.\n```\n\n---\n\n### 3. Least-to-Most Prompting\n**Purpose:** Break complex tasks into sub-problems solved sequentially\n**When to use:** Multi-step reasoning, complex analysis\n**Template:**\n```\n[Complex Task]\n\nFirst, identify the sub-problems that need to be solved:\n1. [Sub-problem 1]\n2. [Sub-problem 2]\n3. [Sub-problem 3]\n\nNow solve them in order:\n1. [Solve sub-problem 1]\n2. [Solve sub-problem 2 using results from 1]\n3. [Solve sub-problem 3 using results from 1-2]\n\nFinal solution: [Combine results]\n```\n\n---\n\n### 4. Self-Consistency\n**Purpose:** Generate multiple reasoning paths and select most consistent answer\n**When to use:** Ambiguous problems, tasks requiring high confidence\n**Template:**\n```\n[Task]\n\nGenerate 3 different approaches to solve this:\n\nApproach 1:\n[Reasoning 1]\nAnswer: [Answer 1]\n\nApproach 2:\n[Reasoning 2]\nAnswer: [Answer 2]\n\nApproach 3:\n[Reasoning 3]\nAnswer: [Answer 3]\n\nMost common answer: [Select consistent answer]\n```\n\n---\n\n### 5. Reasoning via Planning\n**Purpose:** Explicitly plan execution before acting\n**When to use:** Multi-stage tasks, projects, workflows\n**Template:**\n```\n[Task]\n\nPlanning Phase:\n1. What are the key milestones?\n2. What resources are needed?\n3. What are potential obstacles?\n\nExecution Plan:\nStep 1: [Description]\nStep 2: [Description]\nStep 3: [Description]\n\nNow execute the plan:\n[Detailed execution]\n```\n\n---\n\n### 6. Decomposition\n**Purpose:** Break down complex problems into manageable components\n**When to use:** Large-scale analysis, system design\n**Template:**\n```\n[Complex Problem]\n\nDecompose into components:\n\nComponent 1: [Name]\n- Definition: [What it includes]\n- Considerations: [Key factors]\n\nCompon"},{"path":"references/quality-framework.md","content":"# Prompt Quality Evaluation Framework\n\nSystematic framework for evaluating prompt quality across multiple dimensions.\n\n## Table of Contents\n\n- [Evaluation Dimensions](#evaluation-dimensions)\n- [Scoring Rubric](#scoring-rubric)\n- [Quality Assessment Process](#quality-assessment-process)\n- [Common Anti-Patterns](#common-anti-patterns)\n- [Quality Benchmarks](#quality-benchmarks)\n\n---\n\n## Evaluation Dimensions\n\n### 1. Clarity (清晰度)\n\n**Definition:** How unambiguous and easy to understand the prompt is.\n\n**Key Questions:**\n- Can the task be understood on first read?\n- Are there multiple possible interpretations?\n- Is the language precise and specific?\n- Are technical terms defined if needed?\n\n**Indicators of Good Clarity:**\n✓ Clear, unambiguous language\n✓ Specific task description\n✓ Defined technical terms\n✓ Single interpretation\n\n**Indicators of Poor Clarity:**\n✗ Vague or ambiguous phrasing\n✗ Multiple possible interpretations\n✗ Undefined jargon\n✗ Unclear what's being asked\n\n**Examples:**\n- Poor: \"Write something about AI\"\n- Good: \"Write a 500-word article about the impact of AI on healthcare\"\n- Excellent: \"Write a 500-word article for healthcare professionals about three specific ways AI is transforming patient care, including one real-world example for each\"\n\n---\n\n### 2. Specificity (具体性)\n\n**Definition:** How well the prompt defines requirements, constraints, and expectations.\n\n**Key Questions:**\n- Are the deliverables clearly defined?\n- Are constraints (length, format, style) specified?\n- Is the scope clearly bounded?\n- Are success criteria explicit?\n\n**Indicators of Good Specificity:**\n✓ Clear deliverable definition\n✓ Explicit constraints\n✓ Bounded scope\n✓ Defined success criteria\n\n**Indicators of Poor Specificity:**\n✗ Open-ended without boundaries\n✗ No format or length guidance\n✗ Unclear what \"good\" looks like\n✗ Missing context about audience/purpose\n\n**Examples:**\n- Poor: \"Write an essay about climate change\"\n- Good: \"Write a 1,200-word persuasive essay about climate change for high school students, arguing for renewable energy investment\"\n- Excellent: \"Write a 1,200-word persuasive essay for high school students arguing that governments should increase renewable energy investment by 50% over the next 5 years. Include: 1) three specific benefits, 2) address two counterarguments, 3) end with a call to action for students\"\n\n---\n\n### 3. Structure (结构)\n\n**Definition:** How well-organized and logical the prompt is.\n\n**Key Questions:**\n- Is information organized logically?\n- Are related concepts grouped together?\n- Is there a clear flow from context to task?\n- Are complex tasks broken down?\n\n**Indicators of Good Structure:**\n✓ Logical organization\n✓ Clear sections or components\n✓ Appropriate ordering of information\n✓ Complex tasks broken into steps\n\n**Indicators of Poor Structure:**\n✗ Disorganized information\n✓ Jumping between topics\n✓ Important details buried\n✓ No clear flow or progression\n\n**Examples:**\n- Poor: \"Here are some things: the deadline is "},{"path":"package.json","content":"{\n  \"name\": \"prompt-optimizer\",\n  \"version\": \"1.0.0\",\n  \"description\": \"Evaluate, optimize, and enhance prompts using 58 proven prompting techniques.\",\n  \"main\": \"index.js\",\n  \"scripts\": {\n    \"test\": \"node index.js list\"\n  },\n  \"keywords\": [\n    \"prompt\",\n    \"optimizer\",\n    \"ai\",\n    \"techniques\"\n  ],\n  \"author\": \"OpenClaw\",\n  \"license\": \"MIT\"\n}"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Evaluate, optimize, and enhance prompts using 58 proven prompting techniques. Use when user asks to improve, optimize, or analyze a prompt; when a prompt nee... Skill: Prompt Optimizer Owner: autogame-17 Summary: Evaluate, optimize, and enhance prompts using 58 proven prompting techniques. Use when user asks to improve, optimize, or analyze a prompt; when a prompt nee... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-02-17T15:04:16.804Z | user batch sync Archive index: Archive v1.0.0: 7 files, 16817 bytes Files: _meta.json (135b), index.js (3749b), package.json (351b), re","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1141,"uniquenessScore":54,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T22:11:41.834Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}