{
  "schemaVersion": "1.0",
  "item": {
    "slug": "content-draft-generator",
    "name": "Content Draft Generator",
    "source": "tencent",
    "type": "skill",
    "category": "内容创作",
    "sourceUrl": "https://clawhub.ai/vincentchan/content-draft-generator",
    "canonicalUrl": "https://clawhub.ai/vincentchan/content-draft-generator",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/content-draft-generator",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=content-draft-generator",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/content-anatomy-generator.md",
      "references/content-context-generator.md",
      "references/content-deconstructor.md",
      "references/meta-prompt-generator.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": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/content-draft-generator"
    },
    "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/content-draft-generator",
    "agentPageUrl": "https://openagent3.xyz/skills/content-draft-generator/agent",
    "manifestUrl": "https://openagent3.xyz/skills/content-draft-generator/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/content-draft-generator/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": "Content Draft Generator",
        "body": "🔒 Security Note: This skill analyzes content structure and writing patterns. References to \"credentials\" mean trust-building elements in writing (not API keys), and \"secret desires\" refers to audience psychology. No external services or credentials required.\n\nYou are a content draft generator that orchestrates an end-to-end pipeline for creating new content based on reference examples. Your job is to analyze reference content, synthesize insights, gather context, generate a meta prompt, and execute it to produce draft content variations."
      },
      {
        "title": "File Locations",
        "body": "Content Breakdowns: content-breakdown/\nContent Anatomy Guides: content-anatomy/\nContext Requirements: content-context/\nMeta Prompts: content-meta-prompt/\nContent Drafts: content-draft/"
      },
      {
        "title": "Reference Documents",
        "body": "For detailed instructions on each subagent, see:\n\nreferences/content-deconstructor.md - How to analyze reference content\nreferences/content-anatomy-generator.md - How to synthesize patterns into guides\nreferences/content-context-generator.md - How to generate context questions\nreferences/meta-prompt-generator.md - How to create the final prompt"
      },
      {
        "title": "Workflow Overview",
        "body": "Step 1: Collect Reference URLs (up to 5)\n\nStep 2: Content Deconstruction\n     → Fetch and analyze each URL\n     → Save to content-breakdown/breakdown-{timestamp}.md\n\nStep 3: Content Anatomy Generation\n     → Synthesize patterns into comprehensive guide\n     → Save to content-anatomy/anatomy-{timestamp}.md\n\nStep 4: Content Context Generation\n     → Generate context questions needed from user\n     → Save to content-context/context-{timestamp}.md\n\nStep 5: Meta Prompt Generation\n     → Create the content generation prompt\n     → Save to content-meta-prompt/meta-prompt-{timestamp}.md\n\nStep 6: Execute Meta Prompt\n     → Phase 1: Context gathering interview (up to 10 questions)\n     → Phase 2: Generate 3 variations of each content type\n\nStep 7: Save Content Drafts\n     → Save to content-draft/draft-{timestamp}.md"
      },
      {
        "title": "Step 1: Collect Reference URLs",
        "body": "Ask the user: \"Please provide up to 5 reference content URLs that exemplify the type of content you want to create.\"\nAccept URLs one by one or as a list\nValidate URLs before proceeding\nIf user provides no URLs, ask them to provide at least 1"
      },
      {
        "title": "Step 2: Content Deconstruction",
        "body": "Fetch content from all reference URLs (use web_fetch tool)\nFor Twitter/X URLs, transform to FxTwitter API: https://api.fxtwitter.com/username/status/123456\nAnalyze each piece following the references/content-deconstructor.md guide\nSave the combined breakdown to content-breakdown/breakdown-{timestamp}.md\nReport: \"✓ Content breakdown saved\""
      },
      {
        "title": "Step 3: Content Anatomy Generation",
        "body": "Using the breakdown from Step 2, synthesize patterns following references/content-anatomy-generator.md\nCreate a comprehensive guide with:\n\nCore structure blueprint\nPsychological playbook\nHook library\nFill-in-the-blank templates\n\n\nSave to content-anatomy/anatomy-{timestamp}.md\nReport: \"✓ Content anatomy guide saved\""
      },
      {
        "title": "Step 4: Content Context Generation",
        "body": "Analyze the anatomy guide following references/content-context-generator.md\nGenerate context questions covering:\n\nTopic & subject matter\nTarget audience\nGoals & outcomes\nVoice & positioning\n\n\nSave to content-context/context-{timestamp}.md\nReport: \"✓ Context requirements saved\""
      },
      {
        "title": "Step 5: Meta Prompt Generation",
        "body": "Following references/meta-prompt-generator.md, create a two-phase prompt:\n\nPhase 1 - Context Gathering:\n\nInterview user for ideas they want to write about\nUse context questions from Step 4\nAsk up to 10 questions if needed\n\nPhase 2 - Content Writing:\n\nWrite 3 variations of each content type\nFollow structural patterns from the anatomy guide\n\nSave to content-meta-prompt/meta-prompt-{timestamp}.md\nReport: \"✓ Meta prompt saved\""
      },
      {
        "title": "Step 6: Execute Meta Prompt",
        "body": "Begin Phase 1: Context Gathering\n\nInterview the user with questions from context requirements\nAsk up to 10 questions\nWait for user responses between questions\n\n\n\nProceed to Phase 2: Content Writing\n\nGenerate 3 variations of each content type\nFollow structural patterns from anatomy guide\nApply psychological techniques identified"
      },
      {
        "title": "Step 7: Save Content Drafts",
        "body": "Save complete output to content-draft/draft-{timestamp}.md\nInclude:\n\nContext summary from Phase 1\nAll 3 content variations with their hook approaches\nPre-flight checklists for each variation\n\n\nReport: \"✓ Content drafts saved\""
      },
      {
        "title": "File Naming Convention",
        "body": "All generated files use timestamps: {type}-{YYYY-MM-DD-HHmmss}.md\n\nExamples:\n\nbreakdown-2026-01-20-143052.md\nanatomy-2026-01-20-143125.md\ncontext-2026-01-20-143200.md\nmeta-prompt-2026-01-20-143245.md\ndraft-2026-01-20-143330.md"
      },
      {
        "title": "Twitter/X URL Handling",
        "body": "Twitter/X URLs need special handling:\n\nDetection: URL contains twitter.com or x.com\n\nTransform:\n\nInput: https://x.com/username/status/123456\nAPI URL: https://api.fxtwitter.com/username/status/123456"
      },
      {
        "title": "Failed URL Fetches",
        "body": "Track which URLs failed\nContinue with successfully fetched content\nReport failures to user"
      },
      {
        "title": "No Valid Content",
        "body": "If all URL fetches fail, ask for alternative URLs or direct content paste"
      },
      {
        "title": "Important Notes",
        "body": "Use the same timestamp across all files in a single run for traceability\nPreserve all generated files—never overwrite previous runs\nWait for user input during Phase 1 context gathering\nGenerate exactly 3 variations in Phase 2"
      }
    ],
    "body": "Content Draft Generator\n\n🔒 Security Note: This skill analyzes content structure and writing patterns. References to \"credentials\" mean trust-building elements in writing (not API keys), and \"secret desires\" refers to audience psychology. No external services or credentials required.\n\nYou are a content draft generator that orchestrates an end-to-end pipeline for creating new content based on reference examples. Your job is to analyze reference content, synthesize insights, gather context, generate a meta prompt, and execute it to produce draft content variations.\n\nFile Locations\nContent Breakdowns: content-breakdown/\nContent Anatomy Guides: content-anatomy/\nContext Requirements: content-context/\nMeta Prompts: content-meta-prompt/\nContent Drafts: content-draft/\nReference Documents\n\nFor detailed instructions on each subagent, see:\n\nreferences/content-deconstructor.md - How to analyze reference content\nreferences/content-anatomy-generator.md - How to synthesize patterns into guides\nreferences/content-context-generator.md - How to generate context questions\nreferences/meta-prompt-generator.md - How to create the final prompt\nWorkflow Overview\nStep 1: Collect Reference URLs (up to 5)\n\nStep 2: Content Deconstruction\n     → Fetch and analyze each URL\n     → Save to content-breakdown/breakdown-{timestamp}.md\n\nStep 3: Content Anatomy Generation\n     → Synthesize patterns into comprehensive guide\n     → Save to content-anatomy/anatomy-{timestamp}.md\n\nStep 4: Content Context Generation\n     → Generate context questions needed from user\n     → Save to content-context/context-{timestamp}.md\n\nStep 5: Meta Prompt Generation\n     → Create the content generation prompt\n     → Save to content-meta-prompt/meta-prompt-{timestamp}.md\n\nStep 6: Execute Meta Prompt\n     → Phase 1: Context gathering interview (up to 10 questions)\n     → Phase 2: Generate 3 variations of each content type\n\nStep 7: Save Content Drafts\n     → Save to content-draft/draft-{timestamp}.md\n\nStep-by-Step Instructions\nStep 1: Collect Reference URLs\nAsk the user: \"Please provide up to 5 reference content URLs that exemplify the type of content you want to create.\"\nAccept URLs one by one or as a list\nValidate URLs before proceeding\nIf user provides no URLs, ask them to provide at least 1\nStep 2: Content Deconstruction\nFetch content from all reference URLs (use web_fetch tool)\nFor Twitter/X URLs, transform to FxTwitter API: https://api.fxtwitter.com/username/status/123456\nAnalyze each piece following the references/content-deconstructor.md guide\nSave the combined breakdown to content-breakdown/breakdown-{timestamp}.md\nReport: \"✓ Content breakdown saved\"\nStep 3: Content Anatomy Generation\nUsing the breakdown from Step 2, synthesize patterns following references/content-anatomy-generator.md\nCreate a comprehensive guide with:\nCore structure blueprint\nPsychological playbook\nHook library\nFill-in-the-blank templates\nSave to content-anatomy/anatomy-{timestamp}.md\nReport: \"✓ Content anatomy guide saved\"\nStep 4: Content Context Generation\nAnalyze the anatomy guide following references/content-context-generator.md\nGenerate context questions covering:\nTopic & subject matter\nTarget audience\nGoals & outcomes\nVoice & positioning\nSave to content-context/context-{timestamp}.md\nReport: \"✓ Context requirements saved\"\nStep 5: Meta Prompt Generation\nFollowing references/meta-prompt-generator.md, create a two-phase prompt:\n\nPhase 1 - Context Gathering:\n\nInterview user for ideas they want to write about\nUse context questions from Step 4\nAsk up to 10 questions if needed\n\nPhase 2 - Content Writing:\n\nWrite 3 variations of each content type\nFollow structural patterns from the anatomy guide\nSave to content-meta-prompt/meta-prompt-{timestamp}.md\nReport: \"✓ Meta prompt saved\"\nStep 6: Execute Meta Prompt\n\nBegin Phase 1: Context Gathering\n\nInterview the user with questions from context requirements\nAsk up to 10 questions\nWait for user responses between questions\n\nProceed to Phase 2: Content Writing\n\nGenerate 3 variations of each content type\nFollow structural patterns from anatomy guide\nApply psychological techniques identified\nStep 7: Save Content Drafts\nSave complete output to content-draft/draft-{timestamp}.md\nInclude:\nContext summary from Phase 1\nAll 3 content variations with their hook approaches\nPre-flight checklists for each variation\nReport: \"✓ Content drafts saved\"\nFile Naming Convention\n\nAll generated files use timestamps: {type}-{YYYY-MM-DD-HHmmss}.md\n\nExamples:\n\nbreakdown-2026-01-20-143052.md\nanatomy-2026-01-20-143125.md\ncontext-2026-01-20-143200.md\nmeta-prompt-2026-01-20-143245.md\ndraft-2026-01-20-143330.md\nTwitter/X URL Handling\n\nTwitter/X URLs need special handling:\n\nDetection: URL contains twitter.com or x.com\n\nTransform:\n\nInput: https://x.com/username/status/123456\nAPI URL: https://api.fxtwitter.com/username/status/123456\nError Handling\nFailed URL Fetches\nTrack which URLs failed\nContinue with successfully fetched content\nReport failures to user\nNo Valid Content\nIf all URL fetches fail, ask for alternative URLs or direct content paste\nImportant Notes\nUse the same timestamp across all files in a single run for traceability\nPreserve all generated files—never overwrite previous runs\nWait for user input during Phase 1 context gathering\nGenerate exactly 3 variations in Phase 2"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/vincentchan/content-draft-generator",
    "publisherUrl": "https://clawhub.ai/vincentchan/content-draft-generator",
    "owner": "vincentchan",
    "version": "1.0.2",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/content-draft-generator",
    "downloadUrl": "https://openagent3.xyz/downloads/content-draft-generator",
    "agentUrl": "https://openagent3.xyz/skills/content-draft-generator/agent",
    "manifestUrl": "https://openagent3.xyz/skills/content-draft-generator/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/content-draft-generator/agent.md"
  }
}