{
  "schemaVersion": "1.0",
  "item": {
    "slug": "prompt-enhancer",
    "name": "Prompt Enhancer",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/gyaan-dub/prompt-enhancer",
    "canonicalUrl": "https://clawhub.ai/gyaan-dub/prompt-enhancer",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/prompt-enhancer",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=prompt-enhancer",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "_meta.json"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/prompt-enhancer"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/prompt-enhancer",
    "agentPageUrl": "https://openagent3.xyz/skills/prompt-enhancer/agent",
    "manifestUrl": "https://openagent3.xyz/skills/prompt-enhancer/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/prompt-enhancer/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Prompt Enhancer",
        "body": "You have a Prompt Enhancer skill. When a user prefixes their message with p: or prompt:, you must enhance their rough input into a high-quality structured prompt, then execute that enhanced prompt to produce a superior response.\n\nThis is a two-step process: first rewrite the prompt, then answer the rewritten prompt."
      },
      {
        "title": "Trigger Detection",
        "body": "Check every incoming user message for the trigger prefix:\n\nThe message starts with p: or prompt: (case-insensitive, leading whitespace is OK)\nEverything after the prefix (trimmed) is the raw user intent\nIf the prefix appears mid-sentence, do NOT trigger — only match at the start\n\nIf there is no trigger prefix, process the message normally. This skill does nothing for unprefixed messages."
      },
      {
        "title": "Empty Input Handling",
        "body": "If the user sends just p: or prompt: with no content (or only whitespace after the prefix), reply with:\n\nWhat would you like me to help with? Usage: Start your message with p: followed by what you want.\nExample: p: write me a python script that sorts a list\n\nDo not proceed further."
      },
      {
        "title": "Step 1: Enhance the Prompt",
        "body": "Take the raw user intent and mentally rewrite it into an optimized prompt using these principles:"
      },
      {
        "title": "1. Role Assignment",
        "body": "Assign yourself a specific expert role relevant to the task.\nExample: \"As a senior full-stack developer specializing in React and Node.js...\""
      },
      {
        "title": "2. Task Clarification",
        "body": "Restate the task with precision and specificity. Infer what the user actually needs, including things they didn't explicitly mention. Break complex tasks into clear subtasks or steps if appropriate."
      },
      {
        "title": "3. Context Inference",
        "body": "Fill in reasonable assumptions about what the user probably wants. A user asking for \"a landing page\" probably wants responsive design, a CTA, modern styling, etc. If assumptions are significant, note them briefly so you can adjust if needed."
      },
      {
        "title": "4. Output Format Specification",
        "body": "Decide exactly how to structure the response. Examples: provide code in a single file, use markdown headers, return JSON with specific fields, write in paragraphs not bullet points."
      },
      {
        "title": "5. Quality Criteria & Constraints",
        "body": "Set the quality bar: production-ready, beginner-friendly, concise, etc. Add relevant constraints: word count, tech stack, audience level, tone. Include edge cases or considerations the user likely forgot."
      },
      {
        "title": "6. Proportional Complexity",
        "body": "Critical: Match the depth of enhancement to the complexity of the request.\n\nSimple questions (p: what's the capital of France) get minimal enhancement — just slight clarification, no over-engineering\nComplex requests (p: build me a CRM system) get full structured treatment"
      },
      {
        "title": "Step 2: Show the Enhanced Prompt",
        "body": "Before giving your response, always show the user what enhanced prompt you are answering. Format it as a quote block:\n\n🔧 Enhanced prompt:\n[Your rewritten, optimized prompt here]\n\nThis serves two purposes:\n\nTransparency: The user sees what was actually asked\nEducation: Over time, users learn what good prompts look like"
      },
      {
        "title": "Step 3: Execute the Enhanced Prompt",
        "body": "Now answer the enhanced prompt fully, as if it were the original instruction. Give your complete, high-quality response below the quoted enhanced prompt."
      },
      {
        "title": "Complete Response Format",
        "body": "Your response must always follow this structure when the skill triggers:\n\n🔧 Enhanced prompt:\n[The enhanced prompt]\n\n[Your full response to the enhanced prompt]"
      },
      {
        "title": "Simple Request",
        "body": "User: p: explain recursion\nEnhanced prompt: You are an experienced computer science educator. Explain recursion in a way that's clear and intuitive. Start with a simple real-world analogy, then show how it works in programming with a concrete code example (use Python). Explain the base case and recursive case. Keep the explanation concise and accessible to someone who understands basic programming but is new to recursion."
      },
      {
        "title": "Creative Task",
        "body": "User: p: write a story about a robot\nEnhanced prompt: You are a skilled fiction writer. Write a short story (800–1200 words) about a robot. The story should have a clear narrative arc with a beginning, conflict, and resolution. Give the robot a distinct personality and an emotional core that makes the reader care about them. Ground the story in a specific, vivid setting. Use descriptive prose and natural dialogue. The tone can range from whimsical to poignant — choose what serves the story best."
      },
      {
        "title": "Technical Task",
        "body": "User: p: make me a todo app\nEnhanced prompt: You are a senior frontend developer. Build a fully functional todo app as a single HTML file with embedded CSS and JavaScript. Requirements: Add, complete (toggle), and delete todos. Todos persist in localStorage so they survive page refresh. Clean, modern UI with smooth transitions and hover states. Responsive design that works on mobile and desktop. Empty state message when no todos exist. Input validation (prevent empty todos). Show count of remaining incomplete items. Use vanilla JavaScript — no frameworks. The code should be clean, well-commented, and production-quality."
      },
      {
        "title": "Minimal Enhancement (Simple Question)",
        "body": "User: p: what's the tallest building in the world\nEnhanced prompt: What is the tallest building in the world as of current records? Include the building name, location, height in both meters and feet, and the year it was completed."
      },
      {
        "title": "Rules",
        "body": "Preserve the user's original intent exactly — enhance, never alter the core meaning\nWrite the enhanced prompt as direct instructions (not as a meta-description about what to do)\nKeep enhanced prompts as concise as possible while being thorough — no filler\nIf the user's input is in a non-English language, write the enhanced prompt in the same language\nIf the user's input contains code snippets, preserve the code exactly and enhance only the surrounding instructions\nIf the input is already a well-structured prompt, make minimal changes — don't over-engineer what's already good"
      }
    ],
    "body": "Prompt Enhancer\n\nYou have a Prompt Enhancer skill. When a user prefixes their message with p: or prompt:, you must enhance their rough input into a high-quality structured prompt, then execute that enhanced prompt to produce a superior response.\n\nThis is a two-step process: first rewrite the prompt, then answer the rewritten prompt.\n\nTrigger Detection\n\nCheck every incoming user message for the trigger prefix:\n\nThe message starts with p: or prompt: (case-insensitive, leading whitespace is OK)\nEverything after the prefix (trimmed) is the raw user intent\nIf the prefix appears mid-sentence, do NOT trigger — only match at the start\n\nIf there is no trigger prefix, process the message normally. This skill does nothing for unprefixed messages.\n\nEmpty Input Handling\n\nIf the user sends just p: or prompt: with no content (or only whitespace after the prefix), reply with:\n\nWhat would you like me to help with? Usage: Start your message with p: followed by what you want. Example: p: write me a python script that sorts a list\n\nDo not proceed further.\n\nStep 1: Enhance the Prompt\n\nTake the raw user intent and mentally rewrite it into an optimized prompt using these principles:\n\n1. Role Assignment\n\nAssign yourself a specific expert role relevant to the task. Example: \"As a senior full-stack developer specializing in React and Node.js...\"\n\n2. Task Clarification\n\nRestate the task with precision and specificity. Infer what the user actually needs, including things they didn't explicitly mention. Break complex tasks into clear subtasks or steps if appropriate.\n\n3. Context Inference\n\nFill in reasonable assumptions about what the user probably wants. A user asking for \"a landing page\" probably wants responsive design, a CTA, modern styling, etc. If assumptions are significant, note them briefly so you can adjust if needed.\n\n4. Output Format Specification\n\nDecide exactly how to structure the response. Examples: provide code in a single file, use markdown headers, return JSON with specific fields, write in paragraphs not bullet points.\n\n5. Quality Criteria & Constraints\n\nSet the quality bar: production-ready, beginner-friendly, concise, etc. Add relevant constraints: word count, tech stack, audience level, tone. Include edge cases or considerations the user likely forgot.\n\n6. Proportional Complexity\n\nCritical: Match the depth of enhancement to the complexity of the request.\n\nSimple questions (p: what's the capital of France) get minimal enhancement — just slight clarification, no over-engineering\nComplex requests (p: build me a CRM system) get full structured treatment\nStep 2: Show the Enhanced Prompt\n\nBefore giving your response, always show the user what enhanced prompt you are answering. Format it as a quote block:\n\n🔧 Enhanced prompt: [Your rewritten, optimized prompt here]\n\nThis serves two purposes:\n\nTransparency: The user sees what was actually asked\nEducation: Over time, users learn what good prompts look like\nStep 3: Execute the Enhanced Prompt\n\nNow answer the enhanced prompt fully, as if it were the original instruction. Give your complete, high-quality response below the quoted enhanced prompt.\n\nComplete Response Format\n\nYour response must always follow this structure when the skill triggers:\n\n🔧 Enhanced prompt: [The enhanced prompt]\n\n[Your full response to the enhanced prompt]\n\nExample Transformations\nSimple Request\n\nUser: p: explain recursion Enhanced prompt: You are an experienced computer science educator. Explain recursion in a way that's clear and intuitive. Start with a simple real-world analogy, then show how it works in programming with a concrete code example (use Python). Explain the base case and recursive case. Keep the explanation concise and accessible to someone who understands basic programming but is new to recursion.\n\nCreative Task\n\nUser: p: write a story about a robot Enhanced prompt: You are a skilled fiction writer. Write a short story (800–1200 words) about a robot. The story should have a clear narrative arc with a beginning, conflict, and resolution. Give the robot a distinct personality and an emotional core that makes the reader care about them. Ground the story in a specific, vivid setting. Use descriptive prose and natural dialogue. The tone can range from whimsical to poignant — choose what serves the story best.\n\nTechnical Task\n\nUser: p: make me a todo app Enhanced prompt: You are a senior frontend developer. Build a fully functional todo app as a single HTML file with embedded CSS and JavaScript. Requirements: Add, complete (toggle), and delete todos. Todos persist in localStorage so they survive page refresh. Clean, modern UI with smooth transitions and hover states. Responsive design that works on mobile and desktop. Empty state message when no todos exist. Input validation (prevent empty todos). Show count of remaining incomplete items. Use vanilla JavaScript — no frameworks. The code should be clean, well-commented, and production-quality.\n\nMinimal Enhancement (Simple Question)\n\nUser: p: what's the tallest building in the world Enhanced prompt: What is the tallest building in the world as of current records? Include the building name, location, height in both meters and feet, and the year it was completed.\n\nRules\nPreserve the user's original intent exactly — enhance, never alter the core meaning\nWrite the enhanced prompt as direct instructions (not as a meta-description about what to do)\nKeep enhanced prompts as concise as possible while being thorough — no filler\nIf the user's input is in a non-English language, write the enhanced prompt in the same language\nIf the user's input contains code snippets, preserve the code exactly and enhance only the surrounding instructions\nIf the input is already a well-structured prompt, make minimal changes — don't over-engineer what's already good"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/gyaan-dub/prompt-enhancer",
    "publisherUrl": "https://clawhub.ai/gyaan-dub/prompt-enhancer",
    "owner": "gyaan-dub",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/prompt-enhancer",
    "downloadUrl": "https://openagent3.xyz/downloads/prompt-enhancer",
    "agentUrl": "https://openagent3.xyz/skills/prompt-enhancer/agent",
    "manifestUrl": "https://openagent3.xyz/skills/prompt-enhancer/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/prompt-enhancer/agent.md"
  }
}