{
  "schemaVersion": "1.0",
  "item": {
    "slug": "soulflow",
    "name": "SoulFlow — Agent Teams Workflow Skill",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/0xtommythomas-dev/soulflow",
    "canonicalUrl": "https://clawhub.ai/0xtommythomas-dev/soulflow",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/soulflow",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=soulflow",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "CHANGELOG.md",
      "soulflow.js",
      "README.md",
      "PUBLICATION_CHECKLIST.md",
      "package.json",
      "CONTRIBUTING.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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/soulflow"
    },
    "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/soulflow",
    "agentPageUrl": "https://openagent3.xyz/skills/soulflow/agent",
    "manifestUrl": "https://openagent3.xyz/skills/soulflow/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/soulflow/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "SoulFlow — Workflow Framework for OpenClaw",
        "body": "A framework for building custom AI workflows. Each workflow is a series of steps that execute in isolated agent sessions with full tool access. Define your workflow in JSON, invoke it naturally, and let the agents handle the execution.\n\nWhat you can build:\n\nDevelopment pipelines (security audits, bug fixes, feature development)\nContent workflows (research → draft → edit → publish)\nOperations automation (deploy → verify → rollback-on-fail)\nResearch pipelines (gather → analyze → synthesize → report)\nAny multi-step task that benefits from isolated, focused agent sessions\n\nShips with 3 example dev workflows to show you how it works. Build your own for anything."
      },
      {
        "title": "Quick Start",
        "body": "Natural language (easiest):\nJust tell your agent what you need:\n\n\"Run a security audit on my project at ~/myapp\"\n\"Fix this bug: users can't login with Google OAuth in ~/webapp\"\n\"Build a referral system for ~/webapp\"\n\nYour agent reads this SKILL.md and invokes SoulFlow automatically.\n\nCommand line:\n\ncd ~/.openclaw/workspace/soulflow\n\n# Run a security audit\nnode soulflow.js run security-audit \"Audit the codebase at ~/project for vulnerabilities\"\n\n# Fix a bug\nnode soulflow.js run bug-fix \"Login returns 500 when email has uppercase letters in ~/myapp\"\n\n# Build a feature\nnode soulflow.js run feature-dev \"Add dark mode toggle to the settings page in ~/myapp\""
      },
      {
        "title": "How It Works",
        "body": "SoulFlow connects to your local OpenClaw gateway via WebSocket and runs each workflow step as an isolated agent session. A dedicated soulflow-worker agent is auto-created with minimal context — no memory bleed from your main agent.\n\nEach step:\n\nGets a fresh session (no context bloat)\nReceives the task + output from previous steps\nHas full tool access (read, write, edit, exec, browser)\nMust complete its work and report results\n\nAuto-notifications (v1.1.0+): When workflows complete, SoulFlow automatically notifies the main agent session with results. No need to manually check status."
      },
      {
        "title": "Example Workflows (Included)",
        "body": "These are examples to show what's possible. Build your own for any domain."
      },
      {
        "title": "security-audit",
        "body": "Scan → Prioritize → Fix → Verify\nDevelopment example: Reads your source files, identifies vulnerabilities by severity, applies fixes, then verifies them."
      },
      {
        "title": "bug-fix",
        "body": "Triage → Fix → Verify\nDevelopment example: Investigates the root cause by reading code, applies the fix, then verifies it didn't introduce regressions."
      },
      {
        "title": "feature-dev",
        "body": "Plan → Implement → Review\nDevelopment example: Architects the implementation plan, writes the code, then reviews for quality and correctness.\n\nWant content workflows? Research pipelines? Deploy automation? Create your own .workflow.json — see Custom Workflows below."
      },
      {
        "title": "Commands",
        "body": "node soulflow.js run <workflow> \"<task>\"    # Run a workflow\nnode soulflow.js list                       # List available workflows\nnode soulflow.js runs                       # List past runs\nnode soulflow.js status [run-id]            # Check run status\nnode soulflow.js test                       # Test gateway connection"
      },
      {
        "title": "Natural Language (via your agent)",
        "body": "The agent knows how to invoke SoulFlow for you. Just describe what you want:\n\nSecurity audits:\n\n\"Audit my app for security issues\"\n\"Check ~/myapp for vulnerabilities\"\n\"Scan the codebase for security problems\"\n\nBug fixes:\n\n\"Fix this bug: login fails when...\"\n\"There's a problem with the payment flow\"\n\"Users are seeing 500 errors when they...\"\n\nFeatures:\n\n\"Build a referral system\"\n\"Add dark mode to the settings page\"\n\"Implement OAuth login with Google\"\n\nHow it works:\n\nYou tell your agent what you need\nYour agent reads this SKILL.md\nAgent invokes node soulflow.js run <workflow> \"<task>\"\nSoulFlow runs the workflow and reports back\n\nPattern matching: The agent matches your message to workflows:\n\nSecurity audit → keywords: \"audit\", \"security\", \"scan\", \"vulnerabilit\"\nBug fix → keywords: \"fix\", \"bug\", \"broken\", \"not working\", \"error\"\nFeature dev → keywords: \"build\", \"add\", \"implement\", \"create\", \"feature\"\n\nNo workflow matches? Agent will ask which workflow you want or suggest creating a custom one."
      },
      {
        "title": "Custom Workflows",
        "body": "You can create workflows for ANY task. Define them in JSON and place in the workflows/ directory."
      },
      {
        "title": "Creating via Chat",
        "body": "Tell your agent:\n\n\"Create a SoulFlow workflow for [your use case]\"\n\nExamples:\n\n\"Create a workflow for content publishing: research topic → draft article → edit → publish to blog\"\n\"Create a workflow for deployment: run tests → build → deploy → verify health checks → rollback if failed\"\n\"Create a workflow for weekly reports: gather metrics → analyze trends → generate summary → send email\"\n\nYour agent will:\n\nDesign the workflow steps\nWrite the .workflow.json file to workflows/\nShow you how to run it"
      },
      {
        "title": "Manual Creation",
        "body": "Create a .workflow.json file in the workflows/ directory:\n\n{\n  \"id\": \"my-workflow\",\n  \"name\": \"My Custom Workflow\",\n  \"version\": 1,\n  \"description\": \"What this workflow does\",\n  \"steps\": [\n    {\n      \"id\": \"step1\",\n      \"name\": \"First Step\",\n      \"input\": \"Do this thing: {{task}}\",\n      \"expects\": \"STATUS: done\",\n      \"maxRetries\": 1\n    },\n    {\n      \"id\": \"step2\",\n      \"name\": \"Second Step\",\n      \"input\": \"Now do this based on step 1:\\n\\n{{step1_output}}\\n\\nOriginal task: {{task}}\",\n      \"expects\": \"STATUS: done\",\n      \"maxRetries\": 1\n    }\n  ]\n}"
      },
      {
        "title": "Variables",
        "body": "{{task}} — The user's original task description\n{{stepid_output}} — Full output from a previous step (e.g. {{scan_output}})\nAny KEY: value lines in step output become variables (e.g. ROOT_CAUSE: ... → {{root_cause}})"
      },
      {
        "title": "Prompt Tips",
        "body": "For best results, write prompts that:\n\nExplicitly tell the agent to use tools: \"Use read to examine the file\", \"Use edit to apply the fix\"\nSay \"Do NOT just describe — actually do it\"\nEnd with \"When done, end with: STATUS: done\""
      },
      {
        "title": "Architecture",
        "body": "Zero dependencies — Pure Node.js 22 (native WebSocket)\nGateway-native — Connects via WebSocket with challenge-response auth\nSession isolation — Each step in a fresh session\nDedicated worker — Auto-creates soulflow-worker agent with minimal brain files\nJSON state — Run history saved to ~/.openclaw/workspace/.soulflow/runs/\n10-minute timeout per step (configurable)"
      },
      {
        "title": "Requirements",
        "body": "OpenClaw 2026.2.x or later\nNode.js 22+ (for native WebSocket)\nGateway with token auth configured"
      },
      {
        "title": "Security & Permissions",
        "body": "What SoulFlow does to your OpenClaw instance:\n\nReads your gateway config (~/.openclaw/openclaw.json) to obtain the authentication token needed to connect via WebSocket\nModifies your gateway config (~/.openclaw/openclaw.json) via config.patch to register the soulflow-worker agent\nCreates a dedicated worker agent (soulflow-worker) with minimal brain files (SOUL.md only, no memory/history)\nCopies authProfiles from existing agents — Worker inherits credentials for external services (GitHub, cloud providers, etc.) that your other agents use\nGrants the worker full tool access (read, write, edit, exec, browser) — this is required for workflows to actually perform tasks\nWrites run state to ~/.openclaw/workspace/.soulflow/runs/ as JSON files\n\nWhy these permissions are needed:\n\nConfig read/write: Required to authenticate with the gateway and register the worker agent (same as openclaw CLI tool)\nAgent creation: Each workflow step runs in an isolated session to prevent context bleed\nauthProfiles inheritance: Allows workflows to interact with external services (e.g., git push, cloud API calls) using your existing credentials\nFull tools: Workflows need real capabilities (e.g., security-audit reads files, bug-fix edits code, deploy-pipeline pushes to git)\nFilesystem write: Stores workflow history and allows workflows to create/modify files\n\nSecurity considerations:\n\nWorker agent has NO access to your main agent's memory or history\nWorker DOES inherit your external service credentials (authProfiles) — can access GitHub, cloud APIs, etc.\nWorkflows run with YOUR permissions (same as running commands yourself)\nMalicious workflows could read/modify files, run commands, or access external services\nOnly install SoulFlow if you trust the skill author (review code on GitHub first)\nOnly run workflows you trust — custom workflows from untrusted sources could exfiltrate data or misuse credentials\nRun SoulFlow in isolated/sandboxed environments if processing untrusted workflows\n\nRecommended practices:\n\nReview built-in workflows before first use (especially security-audit and bug-fix)\nInspect custom .workflow.json files before running\nReview GitHub repo (https://github.com/0xtommythomas-dev/soulflow) before installation\nRun on non-production OpenClaw instances when testing new workflows\nBack up important files before running workflows that modify code\nUse BYOK (bring your own keys) mode if you want isolated credentials per workflow\nMonitor ~/.openclaw/workspace/.soulflow/runs/ for workflow execution logs"
      },
      {
        "title": "For Agents: How to Invoke SoulFlow",
        "body": "When the user requests a workflow (security audit, bug fix, feature build, etc.), you should:\n\nIdentify the workflow by matching keywords:\n\nSecurity audit: \"audit\", \"security\", \"scan\", \"vulnerabilit\"\nBug fix: \"fix\", \"bug\", \"broken\", \"not working\", \"error\"\nFeature dev: \"build\", \"add\", \"implement\", \"create\", \"feature\"\nCustom: check workflows/*.workflow.json for other options\n\n\n\nExtract the task description — the user's description of what they want done\n\n\nInvoke SoulFlow using exec:\ncd /root/.openclaw/workspace/soulflow && node soulflow.js run <workflow> \"<task>\"\n\n\n\nMonitor the run — SoulFlow will output the run ID, then show progress as each step completes\n\n\nReport results — When complete, relay the final status to the user\n\nExample:\n\nUser: \"Run a security audit on ~/myapp\"\nYou: [exec] cd /root/.openclaw/workspace/soulflow && node soulflow.js run security-audit \"Audit ~/myapp for vulnerabilities\"\n\nCreating workflows for users:\nIf the user asks you to create a custom workflow:\n\nDesign the workflow steps based on their requirements\nWrite a .workflow.json file to /root/.openclaw/workspace/soulflow/workflows/\nShow them how to run it\n\nSee CONTRIBUTING.md for workflow design best practices."
      }
    ],
    "body": "SoulFlow — Workflow Framework for OpenClaw\n\nA framework for building custom AI workflows. Each workflow is a series of steps that execute in isolated agent sessions with full tool access. Define your workflow in JSON, invoke it naturally, and let the agents handle the execution.\n\nWhat you can build:\n\nDevelopment pipelines (security audits, bug fixes, feature development)\nContent workflows (research → draft → edit → publish)\nOperations automation (deploy → verify → rollback-on-fail)\nResearch pipelines (gather → analyze → synthesize → report)\nAny multi-step task that benefits from isolated, focused agent sessions\n\nShips with 3 example dev workflows to show you how it works. Build your own for anything.\n\nQuick Start\n\nNatural language (easiest): Just tell your agent what you need:\n\n\"Run a security audit on my project at ~/myapp\"\n\"Fix this bug: users can't login with Google OAuth in ~/webapp\"\n\"Build a referral system for ~/webapp\"\n\nYour agent reads this SKILL.md and invokes SoulFlow automatically.\n\nCommand line:\n\ncd ~/.openclaw/workspace/soulflow\n\n# Run a security audit\nnode soulflow.js run security-audit \"Audit the codebase at ~/project for vulnerabilities\"\n\n# Fix a bug\nnode soulflow.js run bug-fix \"Login returns 500 when email has uppercase letters in ~/myapp\"\n\n# Build a feature\nnode soulflow.js run feature-dev \"Add dark mode toggle to the settings page in ~/myapp\"\n\nHow It Works\n\nSoulFlow connects to your local OpenClaw gateway via WebSocket and runs each workflow step as an isolated agent session. A dedicated soulflow-worker agent is auto-created with minimal context — no memory bleed from your main agent.\n\nEach step:\n\nGets a fresh session (no context bloat)\nReceives the task + output from previous steps\nHas full tool access (read, write, edit, exec, browser)\nMust complete its work and report results\n\nAuto-notifications (v1.1.0+): When workflows complete, SoulFlow automatically notifies the main agent session with results. No need to manually check status.\n\nExample Workflows (Included)\n\nThese are examples to show what's possible. Build your own for any domain.\n\nsecurity-audit\n\nScan → Prioritize → Fix → Verify Development example: Reads your source files, identifies vulnerabilities by severity, applies fixes, then verifies them.\n\nbug-fix\n\nTriage → Fix → Verify Development example: Investigates the root cause by reading code, applies the fix, then verifies it didn't introduce regressions.\n\nfeature-dev\n\nPlan → Implement → Review Development example: Architects the implementation plan, writes the code, then reviews for quality and correctness.\n\nWant content workflows? Research pipelines? Deploy automation? Create your own .workflow.json — see Custom Workflows below.\n\nCommands\nnode soulflow.js run <workflow> \"<task>\"    # Run a workflow\nnode soulflow.js list                       # List available workflows\nnode soulflow.js runs                       # List past runs\nnode soulflow.js status [run-id]            # Check run status\nnode soulflow.js test                       # Test gateway connection\n\nNatural Language (via your agent)\n\nThe agent knows how to invoke SoulFlow for you. Just describe what you want:\n\nSecurity audits:\n\n\"Audit my app for security issues\"\n\"Check ~/myapp for vulnerabilities\"\n\"Scan the codebase for security problems\"\n\nBug fixes:\n\n\"Fix this bug: login fails when...\"\n\"There's a problem with the payment flow\"\n\"Users are seeing 500 errors when they...\"\n\nFeatures:\n\n\"Build a referral system\"\n\"Add dark mode to the settings page\"\n\"Implement OAuth login with Google\"\n\nHow it works:\n\nYou tell your agent what you need\nYour agent reads this SKILL.md\nAgent invokes node soulflow.js run <workflow> \"<task>\"\nSoulFlow runs the workflow and reports back\n\nPattern matching: The agent matches your message to workflows:\n\nSecurity audit → keywords: \"audit\", \"security\", \"scan\", \"vulnerabilit\"\nBug fix → keywords: \"fix\", \"bug\", \"broken\", \"not working\", \"error\"\nFeature dev → keywords: \"build\", \"add\", \"implement\", \"create\", \"feature\"\n\nNo workflow matches? Agent will ask which workflow you want or suggest creating a custom one.\n\nCustom Workflows\n\nYou can create workflows for ANY task. Define them in JSON and place in the workflows/ directory.\n\nCreating via Chat\n\nTell your agent:\n\n\"Create a SoulFlow workflow for [your use case]\"\n\nExamples:\n\n\"Create a workflow for content publishing: research topic → draft article → edit → publish to blog\"\n\"Create a workflow for deployment: run tests → build → deploy → verify health checks → rollback if failed\"\n\"Create a workflow for weekly reports: gather metrics → analyze trends → generate summary → send email\"\n\nYour agent will:\n\nDesign the workflow steps\nWrite the .workflow.json file to workflows/\nShow you how to run it\nManual Creation\n\nCreate a .workflow.json file in the workflows/ directory:\n\n{\n  \"id\": \"my-workflow\",\n  \"name\": \"My Custom Workflow\",\n  \"version\": 1,\n  \"description\": \"What this workflow does\",\n  \"steps\": [\n    {\n      \"id\": \"step1\",\n      \"name\": \"First Step\",\n      \"input\": \"Do this thing: {{task}}\",\n      \"expects\": \"STATUS: done\",\n      \"maxRetries\": 1\n    },\n    {\n      \"id\": \"step2\",\n      \"name\": \"Second Step\",\n      \"input\": \"Now do this based on step 1:\\n\\n{{step1_output}}\\n\\nOriginal task: {{task}}\",\n      \"expects\": \"STATUS: done\",\n      \"maxRetries\": 1\n    }\n  ]\n}\n\nVariables\n{{task}} — The user's original task description\n{{stepid_output}} — Full output from a previous step (e.g. {{scan_output}})\nAny KEY: value lines in step output become variables (e.g. ROOT_CAUSE: ... → {{root_cause}})\nPrompt Tips\n\nFor best results, write prompts that:\n\nExplicitly tell the agent to use tools: \"Use read to examine the file\", \"Use edit to apply the fix\"\nSay \"Do NOT just describe — actually do it\"\nEnd with \"When done, end with: STATUS: done\"\nArchitecture\nZero dependencies — Pure Node.js 22 (native WebSocket)\nGateway-native — Connects via WebSocket with challenge-response auth\nSession isolation — Each step in a fresh session\nDedicated worker — Auto-creates soulflow-worker agent with minimal brain files\nJSON state — Run history saved to ~/.openclaw/workspace/.soulflow/runs/\n10-minute timeout per step (configurable)\nRequirements\nOpenClaw 2026.2.x or later\nNode.js 22+ (for native WebSocket)\nGateway with token auth configured\nSecurity & Permissions\n\nWhat SoulFlow does to your OpenClaw instance:\n\nReads your gateway config (~/.openclaw/openclaw.json) to obtain the authentication token needed to connect via WebSocket\nModifies your gateway config (~/.openclaw/openclaw.json) via config.patch to register the soulflow-worker agent\nCreates a dedicated worker agent (soulflow-worker) with minimal brain files (SOUL.md only, no memory/history)\nCopies authProfiles from existing agents — Worker inherits credentials for external services (GitHub, cloud providers, etc.) that your other agents use\nGrants the worker full tool access (read, write, edit, exec, browser) — this is required for workflows to actually perform tasks\nWrites run state to ~/.openclaw/workspace/.soulflow/runs/ as JSON files\n\nWhy these permissions are needed:\n\nConfig read/write: Required to authenticate with the gateway and register the worker agent (same as openclaw CLI tool)\nAgent creation: Each workflow step runs in an isolated session to prevent context bleed\nauthProfiles inheritance: Allows workflows to interact with external services (e.g., git push, cloud API calls) using your existing credentials\nFull tools: Workflows need real capabilities (e.g., security-audit reads files, bug-fix edits code, deploy-pipeline pushes to git)\nFilesystem write: Stores workflow history and allows workflows to create/modify files\n\nSecurity considerations:\n\nWorker agent has NO access to your main agent's memory or history\nWorker DOES inherit your external service credentials (authProfiles) — can access GitHub, cloud APIs, etc.\nWorkflows run with YOUR permissions (same as running commands yourself)\nMalicious workflows could read/modify files, run commands, or access external services\nOnly install SoulFlow if you trust the skill author (review code on GitHub first)\nOnly run workflows you trust — custom workflows from untrusted sources could exfiltrate data or misuse credentials\nRun SoulFlow in isolated/sandboxed environments if processing untrusted workflows\n\nRecommended practices:\n\nReview built-in workflows before first use (especially security-audit and bug-fix)\nInspect custom .workflow.json files before running\nReview GitHub repo (https://github.com/0xtommythomas-dev/soulflow) before installation\nRun on non-production OpenClaw instances when testing new workflows\nBack up important files before running workflows that modify code\nUse BYOK (bring your own keys) mode if you want isolated credentials per workflow\nMonitor ~/.openclaw/workspace/.soulflow/runs/ for workflow execution logs\nFor Agents: How to Invoke SoulFlow\n\nWhen the user requests a workflow (security audit, bug fix, feature build, etc.), you should:\n\nIdentify the workflow by matching keywords:\n\nSecurity audit: \"audit\", \"security\", \"scan\", \"vulnerabilit\"\nBug fix: \"fix\", \"bug\", \"broken\", \"not working\", \"error\"\nFeature dev: \"build\", \"add\", \"implement\", \"create\", \"feature\"\nCustom: check workflows/*.workflow.json for other options\n\nExtract the task description — the user's description of what they want done\n\nInvoke SoulFlow using exec:\n\ncd /root/.openclaw/workspace/soulflow && node soulflow.js run <workflow> \"<task>\"\n\n\nMonitor the run — SoulFlow will output the run ID, then show progress as each step completes\n\nReport results — When complete, relay the final status to the user\n\nExample:\n\nUser: \"Run a security audit on ~/myapp\"\nYou: [exec] cd /root/.openclaw/workspace/soulflow && node soulflow.js run security-audit \"Audit ~/myapp for vulnerabilities\"\n\n\nCreating workflows for users: If the user asks you to create a custom workflow:\n\nDesign the workflow steps based on their requirements\nWrite a .workflow.json file to /root/.openclaw/workspace/soulflow/workflows/\nShow them how to run it\n\nSee CONTRIBUTING.md for workflow design best practices."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/0xtommythomas-dev/soulflow",
    "publisherUrl": "https://clawhub.ai/0xtommythomas-dev/soulflow",
    "owner": "0xtommythomas-dev",
    "version": "1.1.2",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/soulflow",
    "downloadUrl": "https://openagent3.xyz/downloads/soulflow",
    "agentUrl": "https://openagent3.xyz/skills/soulflow/agent",
    "manifestUrl": "https://openagent3.xyz/skills/soulflow/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/soulflow/agent.md"
  }
}