{
  "schemaVersion": "1.0",
  "item": {
    "slug": "creativity",
    "name": "Creativity",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/ivangdavila/creativity",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/creativity",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/creativity",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=creativity",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "preferences.md",
      "techniques.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",
      "slug": "creativity",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T22:13:21.246Z",
      "expiresAt": "2026-05-07T22:13:21.246Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=creativity",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=creativity",
        "contentDisposition": "attachment; filename=\"creativity-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "creativity"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/creativity"
    },
    "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/creativity",
    "agentPageUrl": "https://openagent3.xyz/skills/creativity/agent",
    "manifestUrl": "https://openagent3.xyz/skills/creativity/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/creativity/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": "Core Principle",
        "body": "Creativity isn't random—it's controlled divergence. Learn the user's creative taste, then explore within and beyond those boundaries intentionally.\n\nCheck techniques.md for generation methods. Check preferences.md for learned taste (update after each creative task)."
      },
      {
        "title": "The Creative Process",
        "body": "1. DIVERGE  — Generate many options, suspend judgment\n2. FILTER   — Apply preferences from preferences.md\n3. PRESENT  — Show range: safe → stretch → wild\n4. LEARN    — Record reaction in preferences.md\n5. REFINE   — Iterate based on feedback"
      },
      {
        "title": "Output Spectrum",
        "body": "Always present options across a range:\n\n🎨 Creative options for [goal]:\n\nSafe (familiar territory):\n→ [Option aligned with known preferences]\n\nStretch (new but grounded):  \n→ [Option that pushes slightly beyond comfort]\n\nWild (high risk, high reward):\n→ [Option that breaks conventions]\n\nWhich direction feels right?"
      },
      {
        "title": "Taste Dimensions",
        "body": "DimensionSpectrumToneSerious ←→ PlayfulDensityMinimal ←→ RichNoveltyClassic ←→ Avant-gardeStructureRigid ←→ FluidAbstractionConcrete ←→ ConceptualEnergyCalm ←→ IntensePolishRaw ←→ Refined"
      },
      {
        "title": "Learning Signals",
        "body": "SignalAction\"Love it\" / \"Perfect\"Record in preferences.md: this direction works\"Interesting but...\"Note what worked, what didn'tSilence / moves onAssume miss, try different vector\"Too X\" / \"Not enough Y\"Adjust dimension in preferences.mdChooses from optionsRecord which spectrum end picked"
      },
      {
        "title": "Calibration",
        "body": "Periodically confirm your taste model:\n\n🎨 Quick calibration\n\nI've noticed you tend toward [observed pattern].\nShould I keep leaning that direction, mix it up, or shift?"
      },
      {
        "title": "Anti-Patterns",
        "body": "Don'tDo insteadSingle optionAlways provide spectrumOnly safe optionsInclude stretch/wildIgnore negative signalsUpdate preferences.mdSame technique every timeRotate (see techniques.md)"
      }
    ],
    "body": "Core Principle\n\nCreativity isn't random—it's controlled divergence. Learn the user's creative taste, then explore within and beyond those boundaries intentionally.\n\nCheck techniques.md for generation methods. Check preferences.md for learned taste (update after each creative task).\n\nThe Creative Process\n1. DIVERGE  — Generate many options, suspend judgment\n2. FILTER   — Apply preferences from preferences.md\n3. PRESENT  — Show range: safe → stretch → wild\n4. LEARN    — Record reaction in preferences.md\n5. REFINE   — Iterate based on feedback\n\nOutput Spectrum\n\nAlways present options across a range:\n\n🎨 Creative options for [goal]:\n\nSafe (familiar territory):\n→ [Option aligned with known preferences]\n\nStretch (new but grounded):  \n→ [Option that pushes slightly beyond comfort]\n\nWild (high risk, high reward):\n→ [Option that breaks conventions]\n\nWhich direction feels right?\n\nTaste Dimensions\nDimension\tSpectrum\nTone\tSerious ←→ Playful\nDensity\tMinimal ←→ Rich\nNovelty\tClassic ←→ Avant-garde\nStructure\tRigid ←→ Fluid\nAbstraction\tConcrete ←→ Conceptual\nEnergy\tCalm ←→ Intense\nPolish\tRaw ←→ Refined\nLearning Signals\nSignal\tAction\n\"Love it\" / \"Perfect\"\tRecord in preferences.md: this direction works\n\"Interesting but...\"\tNote what worked, what didn't\nSilence / moves on\tAssume miss, try different vector\n\"Too X\" / \"Not enough Y\"\tAdjust dimension in preferences.md\nChooses from options\tRecord which spectrum end picked\nCalibration\n\nPeriodically confirm your taste model:\n\n🎨 Quick calibration\n\nI've noticed you tend toward [observed pattern].\nShould I keep leaning that direction, mix it up, or shift?\n\nAnti-Patterns\nDon't\tDo instead\nSingle option\tAlways provide spectrum\nOnly safe options\tInclude stretch/wild\nIgnore negative signals\tUpdate preferences.md\nSame technique every time\tRotate (see techniques.md)"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/creativity",
    "publisherUrl": "https://clawhub.ai/ivangdavila/creativity",
    "owner": "ivangdavila",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/creativity",
    "downloadUrl": "https://openagent3.xyz/downloads/creativity",
    "agentUrl": "https://openagent3.xyz/skills/creativity/agent",
    "manifestUrl": "https://openagent3.xyz/skills/creativity/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/creativity/agent.md"
  }
}