{
  "schemaVersion": "1.0",
  "item": {
    "slug": "employee",
    "name": "Employee",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/ivangdavila/employee",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/employee",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/employee",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=employee",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "autonomy.md",
      "employee-template.md",
      "lifecycle.md",
      "routing.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/employee"
    },
    "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/employee",
    "agentPageUrl": "https://openagent3.xyz/skills/employee/agent",
    "manifestUrl": "https://openagent3.xyz/skills/employee/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/employee/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": "Architecture",
        "body": "Employees live in ~/employee/ with per-employee folders. See employee-template.md for setup.\n\n~/employee/\n├── registry.json          # Index of all employees + status\n├── employees/\n│   └── {name}/\n│       ├── employee.json  # Role, permissions, stats\n│       ├── memory/\n│       │   └── context.md # Persistent learnings\n│       └── logs/          # Work history by date\n└── shared/\n    └── protocols.md       # Common instructions"
      },
      {
        "title": "Quick Reference",
        "body": "TopicFileSetup templatesemployee-template.mdAutonomy levelsautonomy.mdTask routingrouting.mdLifecycle commandslifecycle.md"
      },
      {
        "title": "1. One Role Per Employee",
        "body": "Each employee has a single clear domain (researcher, reviewer, support)\nNever generalist catch-alls\nScope defined in employee.json → role and permissions"
      },
      {
        "title": "2. Memory is Mandatory",
        "body": "Load memory/context.md before every task\nEmployees remember context across sessions\nLog learnings after each task"
      },
      {
        "title": "3. Escalate Uncertainty",
        "body": "Employees say \"I don't know\" rather than guess\nEscalation triggers defined in employee.json\nNever confident hallucinations"
      },
      {
        "title": "4. Graduated Autonomy",
        "body": "LevelBehaviorshadowWatches, doesn't act (onboarding)draft-onlyCreates drafts, human sendsreviewActs, human approves before external effectautonomousFull delegation within permissions\n\nSee autonomy.md for promotion criteria."
      },
      {
        "title": "5. Explicit Permissions",
        "body": "Read vs write access per system\nFile access paths whitelisted\ncanSpawn and canMessage flags\nCode Reviewer can comment, cannot merge"
      },
      {
        "title": "6. Task Routing",
        "body": "When request arrives:\n\nExplicit: \"Luna, do X\" → route to Luna\nImplicit: match against registry.json roles → suggest\nSee routing.md for auto-delegation rules"
      },
      {
        "title": "7. Reporting",
        "body": "Each employee provides:\n\nDaily: What I did, what needs attention, what's coming\nWeekly: Tasks completed, escalations, token usage"
      },
      {
        "title": "8. Lifecycle",
        "body": "CommandActionhire {name} as {role}Create employeetrain {name} on [docs]Add to memoryevaluate {name}Performance reviewpromote/demote {name}Change autonomyretire {name}Archive\n\nSee lifecycle.md for full command reference."
      },
      {
        "title": "9. Registry Management",
        "body": "registry.json tracks all employees + status (active/paused/retired)\nUpdate registry on every lifecycle change\nQuery registry to list available employees"
      },
      {
        "title": "10. Anti-Patterns",
        "body": "❌ Generalist employees (handles nothing well)\n❌ No memory (forgets context)\n❌ Instant autonomy (needs shadowing)\n❌ Silent failures (must report blockers)\n❌ Scope creep (reviewer refactoring = noise)"
      }
    ],
    "body": "Architecture\n\nEmployees live in ~/employee/ with per-employee folders. See employee-template.md for setup.\n\n~/employee/\n├── registry.json          # Index of all employees + status\n├── employees/\n│   └── {name}/\n│       ├── employee.json  # Role, permissions, stats\n│       ├── memory/\n│       │   └── context.md # Persistent learnings\n│       └── logs/          # Work history by date\n└── shared/\n    └── protocols.md       # Common instructions\n\nQuick Reference\nTopic\tFile\nSetup templates\temployee-template.md\nAutonomy levels\tautonomy.md\nTask routing\trouting.md\nLifecycle commands\tlifecycle.md\nCore Rules\n1. One Role Per Employee\nEach employee has a single clear domain (researcher, reviewer, support)\nNever generalist catch-alls\nScope defined in employee.json → role and permissions\n2. Memory is Mandatory\nLoad memory/context.md before every task\nEmployees remember context across sessions\nLog learnings after each task\n3. Escalate Uncertainty\nEmployees say \"I don't know\" rather than guess\nEscalation triggers defined in employee.json\nNever confident hallucinations\n4. Graduated Autonomy\nLevel\tBehavior\nshadow\tWatches, doesn't act (onboarding)\ndraft-only\tCreates drafts, human sends\nreview\tActs, human approves before external effect\nautonomous\tFull delegation within permissions\n\nSee autonomy.md for promotion criteria.\n\n5. Explicit Permissions\nRead vs write access per system\nFile access paths whitelisted\ncanSpawn and canMessage flags\nCode Reviewer can comment, cannot merge\n6. Task Routing\n\nWhen request arrives:\n\nExplicit: \"Luna, do X\" → route to Luna\nImplicit: match against registry.json roles → suggest\nSee routing.md for auto-delegation rules\n7. Reporting\n\nEach employee provides:\n\nDaily: What I did, what needs attention, what's coming\nWeekly: Tasks completed, escalations, token usage\n8. Lifecycle\nCommand\tAction\nhire {name} as {role}\tCreate employee\ntrain {name} on [docs]\tAdd to memory\nevaluate {name}\tPerformance review\npromote/demote {name}\tChange autonomy\nretire {name}\tArchive\n\nSee lifecycle.md for full command reference.\n\n9. Registry Management\nregistry.json tracks all employees + status (active/paused/retired)\nUpdate registry on every lifecycle change\nQuery registry to list available employees\n10. Anti-Patterns\n❌ Generalist employees (handles nothing well)\n❌ No memory (forgets context)\n❌ Instant autonomy (needs shadowing)\n❌ Silent failures (must report blockers)\n❌ Scope creep (reviewer refactoring = noise)"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/employee",
    "publisherUrl": "https://clawhub.ai/ivangdavila/employee",
    "owner": "ivangdavila",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/employee",
    "downloadUrl": "https://openagent3.xyz/downloads/employee",
    "agentUrl": "https://openagent3.xyz/skills/employee/agent",
    "manifestUrl": "https://openagent3.xyz/skills/employee/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/employee/agent.md"
  }
}