{
  "schemaVersion": "1.0",
  "item": {
    "slug": "mcp-workflow",
    "name": "MCP Workflow",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/slemo54/mcp-workflow",
    "canonicalUrl": "https://clawhub.ai/slemo54/mcp-workflow",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/mcp-workflow",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=mcp-workflow",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/jason-zhou-insights.md",
      "references/mcp-spec.md",
      "references/workflow-patterns.md",
      "scripts/mcp-server.js",
      "scripts/templates/code-review.json"
    ],
    "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": "mcp-workflow",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-05T04:46:23.305Z",
      "expiresAt": "2026-05-12T04:46:23.305Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=mcp-workflow",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=mcp-workflow",
        "contentDisposition": "attachment; filename=\"mcp-workflow-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "mcp-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/mcp-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/mcp-workflow",
    "agentPageUrl": "https://openagent3.xyz/skills/mcp-workflow/agent",
    "manifestUrl": "https://openagent3.xyz/skills/mcp-workflow/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/mcp-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": "Quick Reference",
        "body": "# Start MCP Server\nnode scripts/mcp-server.js\n\n# Run a workflow\n./scripts/workflow-engine.sh run <workflow-name> [--input <json>]\n\n# List available workflows\n./scripts/workflow-engine.sh list\n\n# Create new workflow from template\n./scripts/workflow-engine.sh create <name> --from <template>\n\n# Validate workflow\n./scripts/workflow-engine.sh validate <workflow-file>"
      },
      {
        "title": "Overview",
        "body": "This skill implements workflow automation using the Model Context Protocol (MCP), enabling:\n\nPrompt Chains: Multi-step prompt sequences\nDynamic Workflows: Context-aware adaptation\nResource Integration: File/data embedding\nCross-Server Coordination: Multi-MCP orchestration"
      },
      {
        "title": "1. Prompt Chain Pattern",
        "body": "plan → generate → execute → validate"
      },
      {
        "title": "2. Dynamic Prompt Pattern",
        "body": "context → adapt → generate → output"
      },
      {
        "title": "3. Resource Embedding Pattern",
        "body": "resource://{type}/{id} → load → embed → process"
      },
      {
        "title": "4. External Trigger Pattern",
        "body": "trigger → validate → dispatch → execute"
      },
      {
        "title": "Built-in Templates",
        "body": "TemplateDescriptionUse Casemeal-plannerWeekly meal planningNutrition, shopping listscode-reviewAutomated code reviewPR analysis, quality checksweekly-reportStatus report generationTeam updates, metricsdocumentation-generatorDoc generationAPI docs, changelogs"
      },
      {
        "title": "Resources",
        "body": "file://{path} - File system access\nmemory://{key} - Memory storage\nconfig://{section} - Configuration values"
      },
      {
        "title": "Tools",
        "body": "workflow.run - Execute workflow\nworkflow.list - List workflows\nworkflow.validate - Validate workflow JSON\nprompt.render - Render prompt template"
      },
      {
        "title": "Prompts",
        "body": "chain:plan - Planning prompt\nchain:generate - Generation prompt\nchain:review - Review prompt"
      },
      {
        "title": "Meal Planner Workflow",
        "body": "./scripts/workflow-engine.sh run meal-planner \\\n  --input '{\"diet\":\"vegetarian\",\"days\":7,\"budget\":50}'"
      },
      {
        "title": "Code Review Workflow",
        "body": "./scripts/workflow-engine.sh run code-review \\\n  --input '{\"repo\":\"myapp\",\"pr\":123}'"
      },
      {
        "title": "Weekly Report",
        "body": "./scripts/workflow-engine.sh run weekly-report \\\n  --input '{\"project\":\"dashboard\",\"week\":\"2024-W01\"}'"
      },
      {
        "title": "1. Workflow Design",
        "body": "Keep steps atomic and focused\nUse clear input/output contracts\nImplement error handling at each step\nVersion your workflows"
      },
      {
        "title": "2. Prompt Engineering",
        "body": "Use system prompts for context\nProvide examples in few-shot prompts\nChain prompts for complex tasks\nValidate outputs before next step"
      },
      {
        "title": "3. Resource Management",
        "body": "Use URI patterns consistently\nCache frequently accessed resources\nClean up temporary resources\nDocument resource schemas"
      },
      {
        "title": "4. Cross-Server Coordination",
        "body": "Define clear interfaces between servers\nUse standardized message formats\nImplement health checks\nHandle timeouts gracefully"
      },
      {
        "title": "Configuration",
        "body": "Create ~/.openclaw/mcp-workflow.json:\n\n{\n  \"servers\": [\n    {\n      \"name\": \"local\",\n      \"command\": \"node scripts/mcp-server.js\",\n      \"env\": {}\n    }\n  ],\n  \"workflowsDir\": \"./workflows\",\n  \"templatesDir\": \"./scripts/templates\",\n  \"defaultTimeout\": 30000\n}"
      },
      {
        "title": "Integration with OpenClaw",
        "body": "Use in your OpenClaw session:\n\n# Load the skill\nopenclaw skill load mcp-workflow\n\n# Run workflow\nopenclaw workflow run meal-planner --input '{\"days\":5}'"
      },
      {
        "title": "References",
        "body": "MCP Specification\nWorkflow Patterns\nJason Zhou Insights"
      }
    ],
    "body": "MCP Workflow Skill\nQuick Reference\n# Start MCP Server\nnode scripts/mcp-server.js\n\n# Run a workflow\n./scripts/workflow-engine.sh run <workflow-name> [--input <json>]\n\n# List available workflows\n./scripts/workflow-engine.sh list\n\n# Create new workflow from template\n./scripts/workflow-engine.sh create <name> --from <template>\n\n# Validate workflow\n./scripts/workflow-engine.sh validate <workflow-file>\n\nOverview\n\nThis skill implements workflow automation using the Model Context Protocol (MCP), enabling:\n\nPrompt Chains: Multi-step prompt sequences\nDynamic Workflows: Context-aware adaptation\nResource Integration: File/data embedding\nCross-Server Coordination: Multi-MCP orchestration\nWorkflow Patterns\n1. Prompt Chain Pattern\nplan → generate → execute → validate\n\n2. Dynamic Prompt Pattern\ncontext → adapt → generate → output\n\n3. Resource Embedding Pattern\nresource://{type}/{id} → load → embed → process\n\n4. External Trigger Pattern\ntrigger → validate → dispatch → execute\n\nBuilt-in Templates\nTemplate\tDescription\tUse Case\nmeal-planner\tWeekly meal planning\tNutrition, shopping lists\ncode-review\tAutomated code review\tPR analysis, quality checks\nweekly-report\tStatus report generation\tTeam updates, metrics\ndocumentation-generator\tDoc generation\tAPI docs, changelogs\nMCP Server Features\nResources\nfile://{path} - File system access\nmemory://{key} - Memory storage\nconfig://{section} - Configuration values\nTools\nworkflow.run - Execute workflow\nworkflow.list - List workflows\nworkflow.validate - Validate workflow JSON\nprompt.render - Render prompt template\nPrompts\nchain:plan - Planning prompt\nchain:generate - Generation prompt\nchain:review - Review prompt\nExample Usage\nMeal Planner Workflow\n./scripts/workflow-engine.sh run meal-planner \\\n  --input '{\"diet\":\"vegetarian\",\"days\":7,\"budget\":50}'\n\nCode Review Workflow\n./scripts/workflow-engine.sh run code-review \\\n  --input '{\"repo\":\"myapp\",\"pr\":123}'\n\nWeekly Report\n./scripts/workflow-engine.sh run weekly-report \\\n  --input '{\"project\":\"dashboard\",\"week\":\"2024-W01\"}'\n\nBest Practices\n1. Workflow Design\nKeep steps atomic and focused\nUse clear input/output contracts\nImplement error handling at each step\nVersion your workflows\n2. Prompt Engineering\nUse system prompts for context\nProvide examples in few-shot prompts\nChain prompts for complex tasks\nValidate outputs before next step\n3. Resource Management\nUse URI patterns consistently\nCache frequently accessed resources\nClean up temporary resources\nDocument resource schemas\n4. Cross-Server Coordination\nDefine clear interfaces between servers\nUse standardized message formats\nImplement health checks\nHandle timeouts gracefully\nConfiguration\n\nCreate ~/.openclaw/mcp-workflow.json:\n\n{\n  \"servers\": [\n    {\n      \"name\": \"local\",\n      \"command\": \"node scripts/mcp-server.js\",\n      \"env\": {}\n    }\n  ],\n  \"workflowsDir\": \"./workflows\",\n  \"templatesDir\": \"./scripts/templates\",\n  \"defaultTimeout\": 30000\n}\n\nIntegration with OpenClaw\n\nUse in your OpenClaw session:\n\n# Load the skill\nopenclaw skill load mcp-workflow\n\n# Run workflow\nopenclaw workflow run meal-planner --input '{\"days\":5}'\n\nReferences\nMCP Specification\nWorkflow Patterns\nJason Zhou Insights"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/slemo54/mcp-workflow",
    "publisherUrl": "https://clawhub.ai/slemo54/mcp-workflow",
    "owner": "slemo54",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/mcp-workflow",
    "downloadUrl": "https://openagent3.xyz/downloads/mcp-workflow",
    "agentUrl": "https://openagent3.xyz/skills/mcp-workflow/agent",
    "manifestUrl": "https://openagent3.xyz/skills/mcp-workflow/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/mcp-workflow/agent.md"
  }
}