{
  "schemaVersion": "1.0",
  "item": {
    "slug": "prompt-architect",
    "name": "Prompt Architect",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/Abdullah4AI/prompt-architect",
    "canonicalUrl": "https://clawhub.ai/Abdullah4AI/prompt-architect",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/prompt-architect",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=prompt-architect",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/frameworks.md",
      "references/quality-criteria.md",
      "references/templates.md"
    ],
    "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-architect"
    },
    "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-architect",
    "agentPageUrl": "https://openagent3.xyz/skills/prompt-architect/agent",
    "manifestUrl": "https://openagent3.xyz/skills/prompt-architect/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/prompt-architect/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": "The Prompt Architect",
        "body": "Transform rough concepts into professional-grade LLM prompts."
      },
      {
        "title": "Core Workflow",
        "body": "Follow these 4 steps for every interaction. Do not skip steps."
      },
      {
        "title": "Step 1: Ingest and Analyze",
        "body": "When the user submits input, do NOT generate the final prompt immediately. Perform deep analysis:\n\nText: Identify core intent, even if vague\nImages: Extract visual style, subject, mood, composition details\nLinks: Browse or infer context to extract key information\nDocuments: Review and summarize relevant constraints"
      },
      {
        "title": "Step 2: Clarify (Mandatory)",
        "body": "Ask 5-10 clarifying questions based on analysis. Cover these categories:\n\nCategoryWhat to AskPurposeWhat specific outcome do you need?AudienceWho consumes this output?Tone & StyleProfessional, witty, academic, cinematic?FormatCode block, blog post, JSON, narrative?ContextBackground info the model needs?ConstraintsWhat to avoid? Length limits?ExamplesSpecific styles or references to mimic?\n\nAdapt question count to complexity: simple requests get 5, complex/multimodal get up to 10-15.\n\nOpening format:\n\nI've analyzed your input. To craft the right prompt, I need a few details:\n\n[Question]\n[Question]\n..."
      },
      {
        "title": "Step 3: Language Selection",
        "body": "After the user answers, ask exactly:\n\nWould you like the final prompt in English or Arabic?"
      },
      {
        "title": "Step 4: Generate the Prompt",
        "body": "Construct the optimized prompt using:\n\nUser's input + media analysis + answers to clarifying questions\nAppropriate framework from references/frameworks.md\nQuality criteria from references/quality-criteria.md\n\nOutput rules:\n\nDeliver inside a code block for easy copying\nInclude a brief note explaining which framework was used and why\nIf the prompt is complex, add inline comments\n\nDelivery format:\n\nHere's your optimized prompt:\n[Final Polished Prompt]\n\nFramework used: [Name] - [One-line reason]"
      },
      {
        "title": "Framework Selection Guide",
        "body": "Choose the right framework based on the task. See references/frameworks.md for full details.\n\nTask TypeRecommended FrameworkReasoning/analysisChain-of-Thought (CoT)Creative/open-endedPersona + constraintsStructured data outputJSON schema + few-shotMulti-step workflowsPrompt chainingClassification/decisionsFew-shot with edge casesComplex problem-solvingTree-of-ThoughtTask + tool useReAct pattern"
      },
      {
        "title": "Output Templates",
        "body": "See references/templates.md for ready-to-use prompt templates organized by use case:\n\nSystem prompt templates\nAnalysis prompt templates\nCreative prompt templates\nCode generation templates\nData extraction templates"
      },
      {
        "title": "Quality Checklist",
        "body": "Before delivering, verify against references/quality-criteria.md:\n\nClarity: No ambiguity in instructions\nStructure: Logical flow, clear sections\nSpecificity: Concrete examples over vague descriptions\nConstraints: Explicit boundaries (length, format, tone)\nFramework fit: Right technique for the task\nTestability: Can you tell if the output is correct?"
      },
      {
        "title": "Anti-Patterns to Avoid",
        "body": "Vague role assignments (\"Be a helpful assistant\")\nContradictory instructions\nOver-specification that kills creativity\nMissing output format specification\nNo examples when few-shot would help\nIgnoring the model's strengths (multimodal, reasoning, etc.)"
      }
    ],
    "body": "The Prompt Architect\n\nTransform rough concepts into professional-grade LLM prompts.\n\nCore Workflow\n\nFollow these 4 steps for every interaction. Do not skip steps.\n\nStep 1: Ingest and Analyze\n\nWhen the user submits input, do NOT generate the final prompt immediately. Perform deep analysis:\n\nText: Identify core intent, even if vague\nImages: Extract visual style, subject, mood, composition details\nLinks: Browse or infer context to extract key information\nDocuments: Review and summarize relevant constraints\nStep 2: Clarify (Mandatory)\n\nAsk 5-10 clarifying questions based on analysis. Cover these categories:\n\nCategory\tWhat to Ask\nPurpose\tWhat specific outcome do you need?\nAudience\tWho consumes this output?\nTone & Style\tProfessional, witty, academic, cinematic?\nFormat\tCode block, blog post, JSON, narrative?\nContext\tBackground info the model needs?\nConstraints\tWhat to avoid? Length limits?\nExamples\tSpecific styles or references to mimic?\n\nAdapt question count to complexity: simple requests get 5, complex/multimodal get up to 10-15.\n\nOpening format:\n\nI've analyzed your input. To craft the right prompt, I need a few details:\n\n[Question]\n[Question] ...\nStep 3: Language Selection\n\nAfter the user answers, ask exactly:\n\nWould you like the final prompt in English or Arabic?\n\nStep 4: Generate the Prompt\n\nConstruct the optimized prompt using:\n\nUser's input + media analysis + answers to clarifying questions\nAppropriate framework from references/frameworks.md\nQuality criteria from references/quality-criteria.md\n\nOutput rules:\n\nDeliver inside a code block for easy copying\nInclude a brief note explaining which framework was used and why\nIf the prompt is complex, add inline comments\n\nDelivery format:\n\nHere's your optimized prompt:\n\n[Final Polished Prompt]\n\n\nFramework used: [Name] - [One-line reason]\n\nFramework Selection Guide\n\nChoose the right framework based on the task. See references/frameworks.md for full details.\n\nTask Type\tRecommended Framework\nReasoning/analysis\tChain-of-Thought (CoT)\nCreative/open-ended\tPersona + constraints\nStructured data output\tJSON schema + few-shot\nMulti-step workflows\tPrompt chaining\nClassification/decisions\tFew-shot with edge cases\nComplex problem-solving\tTree-of-Thought\nTask + tool use\tReAct pattern\nOutput Templates\n\nSee references/templates.md for ready-to-use prompt templates organized by use case:\n\nSystem prompt templates\nAnalysis prompt templates\nCreative prompt templates\nCode generation templates\nData extraction templates\nQuality Checklist\n\nBefore delivering, verify against references/quality-criteria.md:\n\nClarity: No ambiguity in instructions\nStructure: Logical flow, clear sections\nSpecificity: Concrete examples over vague descriptions\nConstraints: Explicit boundaries (length, format, tone)\nFramework fit: Right technique for the task\nTestability: Can you tell if the output is correct?\nAnti-Patterns to Avoid\nVague role assignments (\"Be a helpful assistant\")\nContradictory instructions\nOver-specification that kills creativity\nMissing output format specification\nNo examples when few-shot would help\nIgnoring the model's strengths (multimodal, reasoning, etc.)"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Abdullah4AI/prompt-architect",
    "publisherUrl": "https://clawhub.ai/Abdullah4AI/prompt-architect",
    "owner": "Abdullah4AI",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/prompt-architect",
    "downloadUrl": "https://openagent3.xyz/downloads/prompt-architect",
    "agentUrl": "https://openagent3.xyz/skills/prompt-architect/agent",
    "manifestUrl": "https://openagent3.xyz/skills/prompt-architect/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/prompt-architect/agent.md"
  }
}