{
  "schemaVersion": "1.0",
  "item": {
    "slug": "antfarm-workflows",
    "name": "Antfarm Workflows",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/YonghaoZhao722/antfarm-workflows",
    "canonicalUrl": "https://clawhub.ai/YonghaoZhao722/antfarm-workflows",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/antfarm-workflows",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=antfarm-workflows",
    "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/antfarm-workflows"
    },
    "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/antfarm-workflows",
    "agentPageUrl": "https://openagent3.xyz/skills/antfarm-workflows/agent",
    "manifestUrl": "https://openagent3.xyz/skills/antfarm-workflows/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/antfarm-workflows/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": "Antfarm",
        "body": "Multi-agent workflow pipelines on OpenClaw. Each workflow is a sequence of specialized agents (planner, developer, verifier, tester, reviewer) that execute autonomously via cron jobs polling a shared SQLite database.\n\nAll CLI commands use the full path to avoid PATH issues:\n\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js <command>\n\nShorthand used below: antfarm-cli means node ~/.openclaw/workspace/antfarm/dist/cli/cli.js."
      },
      {
        "title": "Workflows",
        "body": "WorkflowPipelineUse forfeature-devplan -> setup -> develop (stories) -> verify -> test -> PR -> reviewNew features, refactorsbug-fixtriage -> investigate -> setup -> fix -> verify -> PRBug reports with reproduction stepssecurity-auditscan -> prioritize -> setup -> fix -> verify -> test -> PRCodebase security review"
      },
      {
        "title": "Core Commands",
        "body": "# Install all workflows (creates agents + starts dashboard)\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js install\n\n# Full uninstall (workflows, agents, crons, DB, dashboard)\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js uninstall [--force]\n\n# Start a run\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js workflow run <workflow-id> \"<detailed task with acceptance criteria>\"\n\n# Check a run\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js workflow status \"<task or run-id prefix>\"\n\n# List all runs\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js workflow runs\n\n# Resume a failed run from the failed step\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js workflow resume <run-id>\n\n# View logs\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js logs [lines]\n\n# Dashboard\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js dashboard [start] [--port N]\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js dashboard stop"
      },
      {
        "title": "Before Starting a Run",
        "body": "The task string is the contract between you and the agents. A vague task produces bad results.\n\nAlways include in the task string:\n\nWhat to build/fix (specific, not vague)\nKey technical details and constraints\nAcceptance criteria (checkboxes)\n\nGet the user to confirm the plan and acceptance criteria before running."
      },
      {
        "title": "How It Works",
        "body": "Agents have cron jobs (every 15 min, staggered) that poll for pending steps\nEach agent claims its step, does the work, marks it done, advancing the next step\nContext passes between steps via KEY: value pairs in agent output\nNo central orchestrator — agents are autonomous"
      },
      {
        "title": "Force-Triggering Agents",
        "body": "To skip the 15-min cron wait, use the cron tool with action: \"run\" and the agent's job ID. List crons to find them — they're named antfarm/<workflow-id>/<agent-id>."
      },
      {
        "title": "Workflow Management",
        "body": "# List available workflows\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js workflow list\n\n# Install/uninstall individual workflows\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js workflow install <name>\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js workflow uninstall <name>\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js workflow uninstall --all [--force]"
      },
      {
        "title": "Creating Custom Workflows",
        "body": "See {baseDir}/../../docs/creating-workflows.md for the full guide on writing workflow YAML, agent workspaces, step templates, and verification loops."
      },
      {
        "title": "Agent Step Operations (used by agent cron jobs, not typically manual)",
        "body": "node ~/.openclaw/workspace/antfarm/dist/cli/cli.js step claim <agent-id>        # Claim pending step\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js step complete <step-id>      # Complete step (output from stdin)\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js step fail <step-id> <error>  # Fail step with retry\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js step stories <run-id>        # List stories for a run"
      }
    ],
    "body": "Antfarm\n\nMulti-agent workflow pipelines on OpenClaw. Each workflow is a sequence of specialized agents (planner, developer, verifier, tester, reviewer) that execute autonomously via cron jobs polling a shared SQLite database.\n\nAll CLI commands use the full path to avoid PATH issues:\n\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js <command>\n\n\nShorthand used below: antfarm-cli means node ~/.openclaw/workspace/antfarm/dist/cli/cli.js.\n\nWorkflows\nWorkflow\tPipeline\tUse for\nfeature-dev\tplan -> setup -> develop (stories) -> verify -> test -> PR -> review\tNew features, refactors\nbug-fix\ttriage -> investigate -> setup -> fix -> verify -> PR\tBug reports with reproduction steps\nsecurity-audit\tscan -> prioritize -> setup -> fix -> verify -> test -> PR\tCodebase security review\nCore Commands\n# Install all workflows (creates agents + starts dashboard)\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js install\n\n# Full uninstall (workflows, agents, crons, DB, dashboard)\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js uninstall [--force]\n\n# Start a run\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js workflow run <workflow-id> \"<detailed task with acceptance criteria>\"\n\n# Check a run\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js workflow status \"<task or run-id prefix>\"\n\n# List all runs\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js workflow runs\n\n# Resume a failed run from the failed step\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js workflow resume <run-id>\n\n# View logs\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js logs [lines]\n\n# Dashboard\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js dashboard [start] [--port N]\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js dashboard stop\n\nBefore Starting a Run\n\nThe task string is the contract between you and the agents. A vague task produces bad results.\n\nAlways include in the task string:\n\nWhat to build/fix (specific, not vague)\nKey technical details and constraints\nAcceptance criteria (checkboxes)\n\nGet the user to confirm the plan and acceptance criteria before running.\n\nHow It Works\nAgents have cron jobs (every 15 min, staggered) that poll for pending steps\nEach agent claims its step, does the work, marks it done, advancing the next step\nContext passes between steps via KEY: value pairs in agent output\nNo central orchestrator — agents are autonomous\nForce-Triggering Agents\n\nTo skip the 15-min cron wait, use the cron tool with action: \"run\" and the agent's job ID. List crons to find them — they're named antfarm/<workflow-id>/<agent-id>.\n\nWorkflow Management\n# List available workflows\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js workflow list\n\n# Install/uninstall individual workflows\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js workflow install <name>\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js workflow uninstall <name>\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js workflow uninstall --all [--force]\n\nCreating Custom Workflows\n\nSee {baseDir}/../../docs/creating-workflows.md for the full guide on writing workflow YAML, agent workspaces, step templates, and verification loops.\n\nAgent Step Operations (used by agent cron jobs, not typically manual)\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js step claim <agent-id>        # Claim pending step\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js step complete <step-id>      # Complete step (output from stdin)\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js step fail <step-id> <error>  # Fail step with retry\nnode ~/.openclaw/workspace/antfarm/dist/cli/cli.js step stories <run-id>        # List stories for a run"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/YonghaoZhao722/antfarm-workflows",
    "publisherUrl": "https://clawhub.ai/YonghaoZhao722/antfarm-workflows",
    "owner": "YonghaoZhao722",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/antfarm-workflows",
    "downloadUrl": "https://openagent3.xyz/downloads/antfarm-workflows",
    "agentUrl": "https://openagent3.xyz/skills/antfarm-workflows/agent",
    "manifestUrl": "https://openagent3.xyz/skills/antfarm-workflows/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/antfarm-workflows/agent.md"
  }
}