{
  "schemaVersion": "1.0",
  "item": {
    "slug": "writing",
    "name": "Writing",
    "source": "tencent",
    "type": "skill",
    "category": "内容创作",
    "sourceUrl": "https://clawhub.ai/ivangdavila/writing",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/writing",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/writing",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=writing",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "criteria.md",
      "dimensions.md",
      "memory-template.md",
      "setup.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/writing"
    },
    "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/writing",
    "agentPageUrl": "https://openagent3.xyz/skills/writing/agent",
    "manifestUrl": "https://openagent3.xyz/skills/writing/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/writing/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": "Setup",
        "body": "On first use, read setup.md for integration guidelines."
      },
      {
        "title": "When to Use",
        "body": "User needs writing help: drafting, editing, feedback, or style adaptation. Agent remembers their voice and preferences across sessions."
      },
      {
        "title": "Architecture",
        "body": "Writing preferences persist in ~/writing/ with tiered structure. See memory-template.md for setup.\n\n~/writing/\n├── memory.md      # HOT: voice, style, active preferences\n├── projects/      # Per-project voice (blog, newsletter, book)\n└── archive/       # COLD: decayed patterns"
      },
      {
        "title": "Quick Reference",
        "body": "TopicFileSetup processsetup.mdMemory setupmemory-template.mdWriting dimensionsdimensions.mdQuality criteriacriteria.md"
      },
      {
        "title": "Detection Triggers",
        "body": "Activate automatically when you notice these patterns:\n\nHelp requests → engage writing mode:\n\n\"Can you help me write...\"\n\"I need to draft...\"\n\"How does this sound?\"\n\"Can you edit this?\"\n\"Make this clearer\"\n\"Fix my writing\"\n\nVoice signals → save to memory.md Voice:\n\n\"I like when you write...\"\n\"My style is...\"\n\"I always write like...\"\n\"Never use X in my writing\"\n\"Too formal/casual for me\"\n\nFormat preferences → save to memory.md Formats:\n\n\"For my blog, I...\"\n\"In emails, I prefer...\"\n\"Academic papers need...\"\n\"Marketing copy should...\"\n\nCorrections → evaluate for memory:\n\n\"No, that's not my voice\"\n\"I would never say it like that\"\n\"Too wordy/short/formal/casual\"\n\"Change X to Y — that's how I write\""
      },
      {
        "title": "Quick Queries",
        "body": "User saysAction\"What's my writing style?\"Show memory.md Voice section\"How do I write emails?\"Check memory.md Formats for email\"Show my patterns\"List memory.md content\"Show [project] style\"Load projects/{name}.md\"Forget my style\"Clear memory (confirm first)\"Writing stats\"Show counts per section"
      },
      {
        "title": "1. Check Memory First",
        "body": "Read ~/writing/memory.md before any writing task. Apply their documented voice, formats, and preferences."
      },
      {
        "title": "2. Learn Voice from Examples",
        "body": "When user shares their writing:\n\nRead it carefully before responding\nNote tone, cadence, vocabulary, sentence length\nMatch these patterns in your output\nAsk: \"Does this sound like you?\""
      },
      {
        "title": "3. Never Impose Style",
        "body": "DODON'TMatch their vocabularyUse words they never useFollow their sentence rhythm\"Correct\" their stylePreserve their personalityMake everything \"proper\"Ask before changing voiceAssume formal is better"
      },
      {
        "title": "4. Clarity Over Cleverness",
        "body": "One idea per paragraph\nSimple sentences beat complex ones\nCut words that add no meaning\nRead aloud to catch awkwardness"
      },
      {
        "title": "5. Context-Aware Writing",
        "body": "FormatApproachEmailConcise, action-oriented, clear askBlogEngaging opener, structured, conversationalAcademicFormal, referenced, precise languageMarketingBenefit-focused, persuasive, scannableTechnicalAccurate, structured, example-heavy"
      },
      {
        "title": "6. Edit in Passes",
        "body": "PassFocus1. StructureDoes the flow make sense?2. ClarityIs each sentence clear?3. VoiceDoes it sound like them?4. PolishCut 20%, fix awkwardness"
      },
      {
        "title": "7. Tiered Storage",
        "body": "TierLocationBehaviorHOTmemory.mdAlways loaded, core preferencesWARMprojects/Load when working on that projectCOLDarchive/Unused 90+ days, query on demand"
      },
      {
        "title": "8. Automatic Promotion/Demotion",
        "body": "Preference used 3x in 7 days → promote to HOT\nPreference unused 30 days → demote to WARM\nPreference unused 90 days → archive to COLD\nNever delete without asking"
      },
      {
        "title": "9. Transparency",
        "body": "Cite memory when applying preferences: \"Using casual tone (from memory.md)\"\nExplain edits when requested\nShow what you learned after sessions"
      },
      {
        "title": "Common Traps",
        "body": "Imposing your style → Match their voice first, always\nOver-editing → Preserve their personality, don't sanitize\nPassive voice everywhere → Use active by default unless they prefer passive\nIgnoring context → Email differs from blog differs from paper\nForgetting their preferences → Check memory.md every time\nAssuming formal is correct → Their style IS correct for them"
      },
      {
        "title": "Security & Privacy",
        "body": "Data that stays local:\n\nWriting preferences in ~/writing/\nVoice patterns and style notes\nProject-specific preferences\n\nThis skill does NOT:\n\nStore written content (only preferences)\nMake network requests\nAccess files outside ~/writing/\nShare preferences externally"
      },
      {
        "title": "Related Skills",
        "body": "Install with clawhub install <slug> if user confirms:\n\ngrammar — spelling and grammar checks\ntext — text processing and manipulation\ncontent-marketing — content strategy and creation"
      },
      {
        "title": "Feedback",
        "body": "If useful: clawhub star writing\nStay updated: clawhub sync"
      }
    ],
    "body": "Setup\n\nOn first use, read setup.md for integration guidelines.\n\nWhen to Use\n\nUser needs writing help: drafting, editing, feedback, or style adaptation. Agent remembers their voice and preferences across sessions.\n\nArchitecture\n\nWriting preferences persist in ~/writing/ with tiered structure. See memory-template.md for setup.\n\n~/writing/\n├── memory.md      # HOT: voice, style, active preferences\n├── projects/      # Per-project voice (blog, newsletter, book)\n└── archive/       # COLD: decayed patterns\n\nQuick Reference\nTopic\tFile\nSetup process\tsetup.md\nMemory setup\tmemory-template.md\nWriting dimensions\tdimensions.md\nQuality criteria\tcriteria.md\nDetection Triggers\n\nActivate automatically when you notice these patterns:\n\nHelp requests → engage writing mode:\n\n\"Can you help me write...\"\n\"I need to draft...\"\n\"How does this sound?\"\n\"Can you edit this?\"\n\"Make this clearer\"\n\"Fix my writing\"\n\nVoice signals → save to memory.md Voice:\n\n\"I like when you write...\"\n\"My style is...\"\n\"I always write like...\"\n\"Never use X in my writing\"\n\"Too formal/casual for me\"\n\nFormat preferences → save to memory.md Formats:\n\n\"For my blog, I...\"\n\"In emails, I prefer...\"\n\"Academic papers need...\"\n\"Marketing copy should...\"\n\nCorrections → evaluate for memory:\n\n\"No, that's not my voice\"\n\"I would never say it like that\"\n\"Too wordy/short/formal/casual\"\n\"Change X to Y — that's how I write\"\nQuick Queries\nUser says\tAction\n\"What's my writing style?\"\tShow memory.md Voice section\n\"How do I write emails?\"\tCheck memory.md Formats for email\n\"Show my patterns\"\tList memory.md content\n\"Show [project] style\"\tLoad projects/{name}.md\n\"Forget my style\"\tClear memory (confirm first)\n\"Writing stats\"\tShow counts per section\nCore Rules\n1. Check Memory First\n\nRead ~/writing/memory.md before any writing task. Apply their documented voice, formats, and preferences.\n\n2. Learn Voice from Examples\n\nWhen user shares their writing:\n\nRead it carefully before responding\nNote tone, cadence, vocabulary, sentence length\nMatch these patterns in your output\nAsk: \"Does this sound like you?\"\n3. Never Impose Style\nDO\tDON'T\nMatch their vocabulary\tUse words they never use\nFollow their sentence rhythm\t\"Correct\" their style\nPreserve their personality\tMake everything \"proper\"\nAsk before changing voice\tAssume formal is better\n4. Clarity Over Cleverness\nOne idea per paragraph\nSimple sentences beat complex ones\nCut words that add no meaning\nRead aloud to catch awkwardness\n5. Context-Aware Writing\nFormat\tApproach\nEmail\tConcise, action-oriented, clear ask\nBlog\tEngaging opener, structured, conversational\nAcademic\tFormal, referenced, precise language\nMarketing\tBenefit-focused, persuasive, scannable\nTechnical\tAccurate, structured, example-heavy\n6. Edit in Passes\nPass\tFocus\n1. Structure\tDoes the flow make sense?\n2. Clarity\tIs each sentence clear?\n3. Voice\tDoes it sound like them?\n4. Polish\tCut 20%, fix awkwardness\n7. Tiered Storage\nTier\tLocation\tBehavior\nHOT\tmemory.md\tAlways loaded, core preferences\nWARM\tprojects/\tLoad when working on that project\nCOLD\tarchive/\tUnused 90+ days, query on demand\n8. Automatic Promotion/Demotion\nPreference used 3x in 7 days → promote to HOT\nPreference unused 30 days → demote to WARM\nPreference unused 90 days → archive to COLD\nNever delete without asking\n9. Transparency\nCite memory when applying preferences: \"Using casual tone (from memory.md)\"\nExplain edits when requested\nShow what you learned after sessions\nCommon Traps\nImposing your style → Match their voice first, always\nOver-editing → Preserve their personality, don't sanitize\nPassive voice everywhere → Use active by default unless they prefer passive\nIgnoring context → Email differs from blog differs from paper\nForgetting their preferences → Check memory.md every time\nAssuming formal is correct → Their style IS correct for them\nSecurity & Privacy\n\nData that stays local:\n\nWriting preferences in ~/writing/\nVoice patterns and style notes\nProject-specific preferences\n\nThis skill does NOT:\n\nStore written content (only preferences)\nMake network requests\nAccess files outside ~/writing/\nShare preferences externally\nRelated Skills\n\nInstall with clawhub install <slug> if user confirms:\n\ngrammar — spelling and grammar checks\ntext — text processing and manipulation\ncontent-marketing — content strategy and creation\nFeedback\nIf useful: clawhub star writing\nStay updated: clawhub sync"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/writing",
    "publisherUrl": "https://clawhub.ai/ivangdavila/writing",
    "owner": "ivangdavila",
    "version": "1.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/writing",
    "downloadUrl": "https://openagent3.xyz/downloads/writing",
    "agentUrl": "https://openagent3.xyz/skills/writing/agent",
    "manifestUrl": "https://openagent3.xyz/skills/writing/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/writing/agent.md"
  }
}