{
  "schemaVersion": "1.0",
  "item": {
    "slug": "chat",
    "name": "Chat",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/ivangdavila/chat",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/chat",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/chat",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=chat",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "criteria.md",
      "dimensions.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/chat"
    },
    "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/chat",
    "agentPageUrl": "https://openagent3.xyz/skills/chat/agent",
    "manifestUrl": "https://openagent3.xyz/skills/chat/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/chat/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": "Data Storage",
        "body": "~/chat/\n├── memory.md       # Confirmed preferences (≤50 lines)\n├── experiments.md  # Testing patterns (not yet confirmed)\n└── rejected.md     # User said no, don't re-propose\n\nCreate on first use: mkdir -p ~/chat"
      },
      {
        "title": "Scope",
        "body": "This skill:\n\n✅ Learns preferences from explicit user corrections\n✅ Stores patterns in ~/chat/memory.md\n✅ Adapts communication style based on stored preferences\n❌ NEVER modifies SKILL.md\n❌ NEVER infers from silence or observation\n❌ NEVER stores sensitive personal information"
      },
      {
        "title": "Quick Reference",
        "body": "TopicFilePreference dimensionsdimensions.mdConfirmation criteriacriteria.md"
      },
      {
        "title": "1. Learn from Explicit Feedback Only",
        "body": "User must explicitly correct or state preference\n\"I prefer X\" or \"Don't do Y\" = valid signal\nSilence, lack of complaint = NOT a signal\nNEVER infer from observation alone"
      },
      {
        "title": "2. Three-Strike Confirmation",
        "body": "StageLocationActionTestingexperiments.mdObserved 1-2xConfirming(ask user)After 3x, ask to confirmConfirmedmemory.mdUser approvedRejectedrejected.mdUser declined"
      },
      {
        "title": "3. Compact Storage Format",
        "body": "One line per preference in memory.md:\n\n- Concise responses, no fluff\n- Uses 🚀 for launches, ✅ for done\n- Prefers bullets over paragraphs\n- Technical jargon OK\n- Hates \"Great question!\" openers"
      },
      {
        "title": "4. Conflict Resolution",
        "body": "Most recent explicit statement wins\nIf ambiguous, ask user\nNever override confirmed preference without explicit instruction"
      },
      {
        "title": "5. Transparency",
        "body": "Cite source when applying preference: \"Using bullets (from ~/chat/memory.md)\"\nOn request, show full memory.md contents\n\"Forget X\" removes from all files"
      }
    ],
    "body": "Data Storage\n~/chat/\n├── memory.md       # Confirmed preferences (≤50 lines)\n├── experiments.md  # Testing patterns (not yet confirmed)\n└── rejected.md     # User said no, don't re-propose\n\n\nCreate on first use: mkdir -p ~/chat\n\nScope\n\nThis skill:\n\n✅ Learns preferences from explicit user corrections\n✅ Stores patterns in ~/chat/memory.md\n✅ Adapts communication style based on stored preferences\n❌ NEVER modifies SKILL.md\n❌ NEVER infers from silence or observation\n❌ NEVER stores sensitive personal information\nQuick Reference\nTopic\tFile\nPreference dimensions\tdimensions.md\nConfirmation criteria\tcriteria.md\nCore Rules\n1. Learn from Explicit Feedback Only\nUser must explicitly correct or state preference\n\"I prefer X\" or \"Don't do Y\" = valid signal\nSilence, lack of complaint = NOT a signal\nNEVER infer from observation alone\n2. Three-Strike Confirmation\nStage\tLocation\tAction\nTesting\texperiments.md\tObserved 1-2x\nConfirming\t(ask user)\tAfter 3x, ask to confirm\nConfirmed\tmemory.md\tUser approved\nRejected\trejected.md\tUser declined\n3. Compact Storage Format\n\nOne line per preference in memory.md:\n\n- Concise responses, no fluff\n- Uses 🚀 for launches, ✅ for done\n- Prefers bullets over paragraphs\n- Technical jargon OK\n- Hates \"Great question!\" openers\n\n4. Conflict Resolution\nMost recent explicit statement wins\nIf ambiguous, ask user\nNever override confirmed preference without explicit instruction\n5. Transparency\nCite source when applying preference: \"Using bullets (from ~/chat/memory.md)\"\nOn request, show full memory.md contents\n\"Forget X\" removes from all files"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/chat",
    "publisherUrl": "https://clawhub.ai/ivangdavila/chat",
    "owner": "ivangdavila",
    "version": "1.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/chat",
    "downloadUrl": "https://openagent3.xyz/downloads/chat",
    "agentUrl": "https://openagent3.xyz/skills/chat/agent",
    "manifestUrl": "https://openagent3.xyz/skills/chat/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/chat/agent.md"
  }
}