{
  "schemaVersion": "1.0",
  "item": {
    "slug": "workflow",
    "name": "Workflow",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/ivangdavila/workflow",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/workflow",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/workflow",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=workflow",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "components.md",
      "data-flow.md",
      "errors.md",
      "lifecycle.md",
      "state.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": "workflow",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-11T03:57:25.735Z",
      "expiresAt": "2026-05-18T03:57:25.735Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=workflow",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=workflow",
        "contentDisposition": "attachment; filename=\"workflow-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "workflow"
      },
      "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/workflow"
    },
    "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/workflow",
    "agentPageUrl": "https://openagent3.xyz/skills/workflow/agent",
    "manifestUrl": "https://openagent3.xyz/skills/workflow/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/workflow/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": "Workflows live in workflows/ with components and flows:\n\nworkflows/\n├── index.md                 # Inventory with tags\n├── components/\n│   ├── connections/         # Auth configs\n│   ├── nodes/               # Reusable operations\n│   └── triggers/            # Event sources\n└── flows/{name}/\n    ├── flow.md              # Definition\n    ├── config.yaml          # Parameters\n    ├── run.sh               # Executable\n    ├── state/               # Persistent between runs\n    └── logs/"
      },
      {
        "title": "Quick Reference",
        "body": "TopicFileDirectory layout, naming, formatsstructure.mdData passing between nodesdata-flow.mdCursor, seen set, checkpointstate.mdRetry, rollback, idempotencyerrors.mdConnections, nodes, triggerscomponents.mdCreate, test, update, archivelifecycle.md"
      },
      {
        "title": "Requirements",
        "body": "jq — JSON processing\nyq — YAML config parsing\ncurl — HTTP requests\nflock — Lock files to prevent concurrent runs\nSecrets in macOS Keychain (security find-generic-password)"
      },
      {
        "title": "Data Storage",
        "body": "Location: workflows/ in workspace root\nState: flows/{name}/state/ — cursor.json, seen.json, checkpoint.json\nLogs: flows/{name}/logs/ — JSONL per run\nData: flows/{name}/data/ — intermediate files between nodes"
      },
      {
        "title": "1. Data Flow Pattern",
        "body": "Each node writes output to data/{NN}-{name}.json. Next node reads it.\n\ncurl ... > data/01-fetch.json\njq '...' data/01-fetch.json > data/02-filter.json\n\nBreaking this pattern = nodes can't communicate."
      },
      {
        "title": "2. Error Declaration",
        "body": "Every node in flow.md MUST declare:\n\nOn error: retry(N) | fail | continue | alert\nOn empty: skip | continue | fail\n\nUndefined behavior = unpredictable workflow."
      },
      {
        "title": "3. Lock Files",
        "body": "Prevent concurrent runs:\n\nLOCKFILE=\"/tmp/workflow-${NAME}.lock\"\nexec 200>\"$LOCKFILE\"\nflock -n 200 || exit 0"
      },
      {
        "title": "4. State Files",
        "body": "FilePurposecursor.json\"Where did I leave off?\"seen.json\"What have I processed?\"checkpoint.json\"Multi-step recovery\""
      },
      {
        "title": "5. Component Reuse",
        "body": "Before creating new connections/nodes/triggers:\n\nls workflows/components/connections/\nls workflows/components/nodes/\n\nUse existing. Update \"Workflows Using This\" when adding.\n\nRelated: For LLM-driven multi-phase processes, see the cycle skill."
      }
    ],
    "body": "Architecture\n\nWorkflows live in workflows/ with components and flows:\n\nworkflows/\n├── index.md                 # Inventory with tags\n├── components/\n│   ├── connections/         # Auth configs\n│   ├── nodes/               # Reusable operations\n│   └── triggers/            # Event sources\n└── flows/{name}/\n    ├── flow.md              # Definition\n    ├── config.yaml          # Parameters\n    ├── run.sh               # Executable\n    ├── state/               # Persistent between runs\n    └── logs/\n\nQuick Reference\nTopic\tFile\nDirectory layout, naming, formats\tstructure.md\nData passing between nodes\tdata-flow.md\nCursor, seen set, checkpoint\tstate.md\nRetry, rollback, idempotency\terrors.md\nConnections, nodes, triggers\tcomponents.md\nCreate, test, update, archive\tlifecycle.md\nRequirements\njq — JSON processing\nyq — YAML config parsing\ncurl — HTTP requests\nflock — Lock files to prevent concurrent runs\nSecrets in macOS Keychain (security find-generic-password)\nData Storage\nLocation: workflows/ in workspace root\nState: flows/{name}/state/ — cursor.json, seen.json, checkpoint.json\nLogs: flows/{name}/logs/ — JSONL per run\nData: flows/{name}/data/ — intermediate files between nodes\nCore Rules\n1. Data Flow Pattern\n\nEach node writes output to data/{NN}-{name}.json. Next node reads it.\n\ncurl ... > data/01-fetch.json\njq '...' data/01-fetch.json > data/02-filter.json\n\n\nBreaking this pattern = nodes can't communicate.\n\n2. Error Declaration\n\nEvery node in flow.md MUST declare:\n\nOn error: retry(N) | fail | continue | alert\nOn empty: skip | continue | fail\n\nUndefined behavior = unpredictable workflow.\n\n3. Lock Files\n\nPrevent concurrent runs:\n\nLOCKFILE=\"/tmp/workflow-${NAME}.lock\"\nexec 200>\"$LOCKFILE\"\nflock -n 200 || exit 0\n\n4. State Files\nFile\tPurpose\ncursor.json\t\"Where did I leave off?\"\nseen.json\t\"What have I processed?\"\ncheckpoint.json\t\"Multi-step recovery\"\n5. Component Reuse\n\nBefore creating new connections/nodes/triggers:\n\nls workflows/components/connections/\nls workflows/components/nodes/\n\n\nUse existing. Update \"Workflows Using This\" when adding.\n\nRelated: For LLM-driven multi-phase processes, see the cycle skill."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/workflow",
    "publisherUrl": "https://clawhub.ai/ivangdavila/workflow",
    "owner": "ivangdavila",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/workflow",
    "downloadUrl": "https://openagent3.xyz/downloads/workflow",
    "agentUrl": "https://openagent3.xyz/skills/workflow/agent",
    "manifestUrl": "https://openagent3.xyz/skills/workflow/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/workflow/agent.md"
  }
}