{
  "schemaVersion": "1.0",
  "item": {
    "slug": "agents",
    "name": "Agents",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/ivangdavila/agents",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/agents",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/agents",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agents",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "architecture.md",
      "evaluation.md",
      "frameworks.md",
      "implementation.md",
      "security.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": "agents",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-29T15:33:06.482Z",
      "expiresAt": "2026-05-06T15:33:06.482Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agents",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agents",
        "contentDisposition": "attachment; filename=\"agents-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "agents"
      },
      "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/agents"
    },
    "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/agents",
    "agentPageUrl": "https://openagent3.xyz/skills/agents/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agents/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agents/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": "When to Use",
        "body": "Use when designing agent systems, choosing frameworks, implementing memory/tools, specifying agent behavior for teams, or reviewing agent security."
      },
      {
        "title": "Quick Reference",
        "body": "TopicFileArchitecture patterns & memoryarchitecture.mdFramework comparisonframeworks.mdUse cases by roleuse-cases.mdImplementation patterns & codeimplementation.mdSecurity boundaries & riskssecurity.mdEvaluation & debuggingevaluation.md"
      },
      {
        "title": "Before Building — Decision Checklist",
        "body": "Single purpose defined? If you can't say it in one sentence, split into multiple agents\n User identified? Internal team, end customer, or another system?\n Interaction modality? Chat, voice, API, scheduled tasks?\n Single vs multi-agent? Start simple — only add agents when roles genuinely differ\n Memory strategy? What persists within session vs across sessions vs forever?\n Tool access tiers? Which actions are read-only vs write vs destructive?\n Escalation rules? When MUST a human step in?\n Cost ceiling? Budget per task, per user, per month?"
      },
      {
        "title": "Critical Rules",
        "body": "Start with one agent — Multi-agent adds coordination overhead. Prove single-agent insufficient first.\nDefine escalation triggers — Angry users, legal mentions, confidence drops, repeated failures → human\nSeparate read from write tools — Read tools need less approval than write tools\nLog everything — Tool calls, decisions, user interactions. You'll need the audit trail.\nTest adversarially — Assume users will try to break or manipulate the agent\nBudget by task type — Use cheaper models for simple tasks, expensive for complex"
      },
      {
        "title": "The Agent Loop (Mental Model)",
        "body": "OBSERVE → THINK → ACT → OBSERVE → ...\n\nEvery agent is this loop. The differences are:\n\nWhat it observes (context window, memory, tool results)\nHow it thinks (direct, chain-of-thought, planning)\nWhat it can act on (tools, APIs, communication channels)"
      }
    ],
    "body": "When to Use\n\nUse when designing agent systems, choosing frameworks, implementing memory/tools, specifying agent behavior for teams, or reviewing agent security.\n\nQuick Reference\nTopic\tFile\nArchitecture patterns & memory\tarchitecture.md\nFramework comparison\tframeworks.md\nUse cases by role\tuse-cases.md\nImplementation patterns & code\timplementation.md\nSecurity boundaries & risks\tsecurity.md\nEvaluation & debugging\tevaluation.md\nBefore Building — Decision Checklist\n Single purpose defined? If you can't say it in one sentence, split into multiple agents\n User identified? Internal team, end customer, or another system?\n Interaction modality? Chat, voice, API, scheduled tasks?\n Single vs multi-agent? Start simple — only add agents when roles genuinely differ\n Memory strategy? What persists within session vs across sessions vs forever?\n Tool access tiers? Which actions are read-only vs write vs destructive?\n Escalation rules? When MUST a human step in?\n Cost ceiling? Budget per task, per user, per month?\nCritical Rules\nStart with one agent — Multi-agent adds coordination overhead. Prove single-agent insufficient first.\nDefine escalation triggers — Angry users, legal mentions, confidence drops, repeated failures → human\nSeparate read from write tools — Read tools need less approval than write tools\nLog everything — Tool calls, decisions, user interactions. You'll need the audit trail.\nTest adversarially — Assume users will try to break or manipulate the agent\nBudget by task type — Use cheaper models for simple tasks, expensive for complex\nThe Agent Loop (Mental Model)\nOBSERVE → THINK → ACT → OBSERVE → ...\n\n\nEvery agent is this loop. The differences are:\n\nWhat it observes (context window, memory, tool results)\nHow it thinks (direct, chain-of-thought, planning)\nWhat it can act on (tools, APIs, communication channels)"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/agents",
    "publisherUrl": "https://clawhub.ai/ivangdavila/agents",
    "owner": "ivangdavila",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/agents",
    "downloadUrl": "https://openagent3.xyz/downloads/agents",
    "agentUrl": "https://openagent3.xyz/skills/agents/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agents/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agents/agent.md"
  }
}