{
  "schemaVersion": "1.0",
  "item": {
    "slug": "amplifier-openclaw",
    "name": "Amplifier",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/bkrabach/amplifier-openclaw",
    "canonicalUrl": "https://clawhub.ai/bkrabach/amplifier-openclaw",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/amplifier-openclaw",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=amplifier-openclaw",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.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/amplifier-openclaw"
    },
    "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/amplifier-openclaw",
    "agentPageUrl": "https://openagent3.xyz/skills/amplifier-openclaw/agent",
    "manifestUrl": "https://openagent3.xyz/skills/amplifier-openclaw/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/amplifier-openclaw/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": "Amplifier — Multi-Agent Delegation",
        "body": "Amplifier is a multi-agent AI framework. Delegate tasks that benefit from specialist agents, structured workflows, or parallel investigation."
      },
      {
        "title": "When to Delegate",
        "body": "High confidence → delegate immediately:\n\n\"Research X and compare approaches\"\n\"Build a Python tool that does X\"\n\"Review this code for security and design\"\nUser says \"amplifier\", \"deep dive\", \"thorough\", \"comprehensive\"\nTask has clear subtasks benefiting from parallel agents\n\nMedium confidence → offer the choice:\n\n\"I can do a quick analysis, or delegate to Amplifier for a thorough multi-agent review.\"\n\nLow confidence → handle yourself:\n\nSimple Q&A, quick code edits, casual conversation, anything needing immediate response"
      },
      {
        "title": "Basic Delegation",
        "body": "exec command:\"amplifier-openclaw run 'Research the top 3 Python web frameworks' --bundle foundation\" background:true timeout:600"
      },
      {
        "title": "With Model Selection",
        "body": "Pass --model to override the default model:\n\nexec command:\"amplifier-openclaw run --model your-preferred-model 'Deep code review' --bundle foundation\" background:true timeout:600\n\nTip: Pass --model matching the model from your OpenClaw Runtime line so Amplifier uses the same one."
      },
      {
        "title": "Bundles",
        "body": "amplifier-openclaw bundles list\n\nBundleBest ForfoundationGeneral: research, analysis, planning (default)superpowersMulti-agent brainstorm, deep investigationcoderCode generation, refactoring, debugging"
      },
      {
        "title": "Session Persistence",
        "body": "# Start a named session\nexec command:\"amplifier-openclaw run --session-name my-project 'Start building the auth module' --bundle foundation\" background:true\n\n# Resume later\nexec command:\"amplifier-openclaw run --resume --session-name my-project 'Now add unit tests'\" background:true"
      },
      {
        "title": "Modes",
        "body": "Amplifier supports slash-command modes in prompts. Modes do not carry over between runs — include the mode at the start of each prompt:\n\n# Brainstorm mode (uses all agents)\nexec command:\"amplifier-openclaw run --bundle superpowers '/brainstorm How should we architect the new API?'\" background:true\n\n# Research mode\nexec command:\"amplifier-openclaw run --bundle foundation '/research Latest advances in RAG'\" background:true"
      },
      {
        "title": "JSON Output",
        "body": "{\n  \"response\": \"The analysis found...\",\n  \"usage\": {\n    \"input_tokens\": 28566,\n    \"output_tokens\": 1800,\n    \"estimated_cost\": 0.12,\n    \"tool_invocations\": 3\n  },\n  \"status\": \"completed\"\n}"
      },
      {
        "title": "Cost Tracking",
        "body": "exec command:\"amplifier-openclaw cost --period week\"\n\nReport costs only when asked or when notable (>$1)."
      },
      {
        "title": "Interpreting Results",
        "body": "response: Present to the user (the main output)\nerror: Report in plain language, don't dump raw JSON\nusage.estimated_cost: May be 0.0 — don't alarm about zero\nstatus: \"completed\", \"cancelled\", or error state"
      },
      {
        "title": "During Active Delegation",
        "body": "\"stop\"/\"cancel\" → kill the background process\nUnrelated questions → answer yourself, don't interrupt Amplifier\nFollow-up → tell user you'll pass it along when current task finishes"
      },
      {
        "title": "Install",
        "body": "If not already installed:\n\nuv tool install \"amplifier-app-openclaw @ git+https://github.com/microsoft/amplifier-app-openclaw@v1.0.5\""
      }
    ],
    "body": "Amplifier — Multi-Agent Delegation\n\nAmplifier is a multi-agent AI framework. Delegate tasks that benefit from specialist agents, structured workflows, or parallel investigation.\n\nWhen to Delegate\n\nHigh confidence → delegate immediately:\n\n\"Research X and compare approaches\"\n\"Build a Python tool that does X\"\n\"Review this code for security and design\"\nUser says \"amplifier\", \"deep dive\", \"thorough\", \"comprehensive\"\nTask has clear subtasks benefiting from parallel agents\n\nMedium confidence → offer the choice:\n\n\"I can do a quick analysis, or delegate to Amplifier for a thorough multi-agent review.\"\n\nLow confidence → handle yourself:\n\nSimple Q&A, quick code edits, casual conversation, anything needing immediate response\nUsage\nBasic Delegation\nexec command:\"amplifier-openclaw run 'Research the top 3 Python web frameworks' --bundle foundation\" background:true timeout:600\n\nWith Model Selection\n\nPass --model to override the default model:\n\nexec command:\"amplifier-openclaw run --model your-preferred-model 'Deep code review' --bundle foundation\" background:true timeout:600\n\n\nTip: Pass --model matching the model from your OpenClaw Runtime line so Amplifier uses the same one.\n\nBundles\namplifier-openclaw bundles list\n\nBundle\tBest For\nfoundation\tGeneral: research, analysis, planning (default)\nsuperpowers\tMulti-agent brainstorm, deep investigation\ncoder\tCode generation, refactoring, debugging\nSession Persistence\n# Start a named session\nexec command:\"amplifier-openclaw run --session-name my-project 'Start building the auth module' --bundle foundation\" background:true\n\n# Resume later\nexec command:\"amplifier-openclaw run --resume --session-name my-project 'Now add unit tests'\" background:true\n\nModes\n\nAmplifier supports slash-command modes in prompts. Modes do not carry over between runs — include the mode at the start of each prompt:\n\n# Brainstorm mode (uses all agents)\nexec command:\"amplifier-openclaw run --bundle superpowers '/brainstorm How should we architect the new API?'\" background:true\n\n# Research mode\nexec command:\"amplifier-openclaw run --bundle foundation '/research Latest advances in RAG'\" background:true\n\nJSON Output\n{\n  \"response\": \"The analysis found...\",\n  \"usage\": {\n    \"input_tokens\": 28566,\n    \"output_tokens\": 1800,\n    \"estimated_cost\": 0.12,\n    \"tool_invocations\": 3\n  },\n  \"status\": \"completed\"\n}\n\nCost Tracking\nexec command:\"amplifier-openclaw cost --period week\"\n\n\nReport costs only when asked or when notable (>$1).\n\nInterpreting Results\nresponse: Present to the user (the main output)\nerror: Report in plain language, don't dump raw JSON\nusage.estimated_cost: May be 0.0 — don't alarm about zero\nstatus: \"completed\", \"cancelled\", or error state\nDuring Active Delegation\n\"stop\"/\"cancel\" → kill the background process\nUnrelated questions → answer yourself, don't interrupt Amplifier\nFollow-up → tell user you'll pass it along when current task finishes\nInstall\n\nIf not already installed:\n\nuv tool install \"amplifier-app-openclaw @ git+https://github.com/microsoft/amplifier-app-openclaw@v1.0.5\""
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/bkrabach/amplifier-openclaw",
    "publisherUrl": "https://clawhub.ai/bkrabach/amplifier-openclaw",
    "owner": "bkrabach",
    "version": "1.1.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/amplifier-openclaw",
    "downloadUrl": "https://openagent3.xyz/downloads/amplifier-openclaw",
    "agentUrl": "https://openagent3.xyz/skills/amplifier-openclaw/agent",
    "manifestUrl": "https://openagent3.xyz/skills/amplifier-openclaw/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/amplifier-openclaw/agent.md"
  }
}