{
  "schemaVersion": "1.0",
  "item": {
    "slug": "comanda",
    "name": "Comanda",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/kris-hansen/comanda",
    "canonicalUrl": "https://clawhub.ai/kris-hansen/comanda",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/comanda",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=comanda",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/WORKFLOW-SPEC.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": "comanda",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-01T23:39:14.193Z",
      "expiresAt": "2026-05-08T23:39:14.193Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=comanda",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=comanda",
        "contentDisposition": "attachment; filename=\"comanda-1.0.2.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "comanda"
      },
      "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/comanda"
    },
    "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/comanda",
    "agentPageUrl": "https://openagent3.xyz/skills/comanda/agent",
    "manifestUrl": "https://openagent3.xyz/skills/comanda/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/comanda/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": "Comanda - Declarative AI Pipelines",
        "body": "🌐 Website: comanda.sh | 📦 GitHub: kris-hansen/comanda\n\nComanda defines LLM workflows in YAML and runs them from the command line. Workflows can chain multiple AI models, run steps in parallel, and pipe data through processing stages."
      },
      {
        "title": "Installation",
        "body": "# macOS\nbrew install kris-hansen/comanda/comanda\n\n# Or via Go\ngo install github.com/kris-hansen/comanda@latest\n\nThen configure API keys:\n\ncomanda configure"
      },
      {
        "title": "Generate a Workflow",
        "body": "Create a workflow YAML from natural language:\n\ncomanda generate <output.yaml> \"<prompt>\"\n\n# Examples\ncomanda generate summarize.yaml \"Create a workflow that summarizes text input\"\ncomanda generate review.yaml \"Analyze code for bugs, then suggest fixes\" -m claude-sonnet-4-20250514"
      },
      {
        "title": "Visualize a Workflow",
        "body": "Display ASCII chart of workflow structure:\n\ncomanda chart <workflow.yaml>\ncomanda chart workflow.yaml --verbose\n\nShows step relationships, models used, input/output chains, and validity."
      },
      {
        "title": "Process/Execute a Workflow",
        "body": "Run a workflow file:\n\ncomanda process <workflow.yaml>\n\n# With input\ncat file.txt | comanda process analyze.yaml\necho \"Design a REST API\" | comanda process multi-agent.yaml\n\n# Multiple workflows\ncomanda process step1.yaml step2.yaml step3.yaml"
      },
      {
        "title": "View/Edit Workflows",
        "body": "Workflow files are YAML. Read them directly to understand or modify:\n\ncat workflow.yaml"
      },
      {
        "title": "Basic Step",
        "body": "step_name:\n  input: STDIN | NA | filename | $VARIABLE\n  model: gpt-4o | claude-sonnet-4-20250514 | gemini-pro | ollama/llama2 | claude-code | gemini-cli\n  action: \"Instruction for the model\"\n  output: STDOUT | filename | $VARIABLE"
      },
      {
        "title": "Parallel Execution",
        "body": "parallel-process:\n  analysis-one:\n    input: STDIN\n    model: claude-sonnet-4-20250514\n    action: \"Analyze for security issues\"\n    output: $SECURITY\n\n  analysis-two:\n    input: STDIN\n    model: gpt-4o\n    action: \"Analyze for performance\"\n    output: $PERF"
      },
      {
        "title": "Chained Steps",
        "body": "extract:\n  input: document.pdf\n  model: gpt-4o\n  action: \"Extract key points\"\n  output: $POINTS\n\nsummarize:\n  input: $POINTS\n  model: claude-sonnet-4-20250514\n  action: \"Create executive summary\"\n  output: STDOUT"
      },
      {
        "title": "Generate + Process (Meta-workflows)",
        "body": "create_workflow:\n  input: NA\n  generate:\n    model: gpt-4o\n    action: \"Create a workflow that analyzes sentiment\"\n    output: generated.yaml\n\nrun_it:\n  input: NA\n  process:\n    workflow_file: generated.yaml"
      },
      {
        "title": "Available Models",
        "body": "Run comanda configure to set up API keys. Common models:\n\nProviderModelsOpenAIgpt-4o, gpt-4o-mini, o1, o1-miniAnthropicclaude-sonnet-4-20250514, claude-opus-4-20250514Googlegemini-pro, gemini-flashOllamaollama/llama2, ollama/mistral, etc.Agenticclaude-code, gemini-cli, openai-codex"
      },
      {
        "title": "Examples Location",
        "body": "See ~/clawd/comanda/examples/ for workflow samples:\n\nagentic-loop/ - Autonomous agent patterns\nclaude-code/ - Claude Code integration\ngemini-cli/ - Gemini CLI workflows\ndocument-processing/ - PDF, text extraction\ndatabase-connections/ - DB query workflows"
      },
      {
        "title": "Troubleshooting",
        "body": "\"model not configured\": Run comanda configure to add API keys\nWorkflow validation errors: Use comanda chart workflow.yaml to visualize and check validity\nDebug mode: Add --debug flag for verbose logging"
      }
    ],
    "body": "Comanda - Declarative AI Pipelines\n\n🌐 Website: comanda.sh | 📦 GitHub: kris-hansen/comanda\n\nComanda defines LLM workflows in YAML and runs them from the command line. Workflows can chain multiple AI models, run steps in parallel, and pipe data through processing stages.\n\nInstallation\n# macOS\nbrew install kris-hansen/comanda/comanda\n\n# Or via Go\ngo install github.com/kris-hansen/comanda@latest\n\n\nThen configure API keys:\n\ncomanda configure\n\nCommands\nGenerate a Workflow\n\nCreate a workflow YAML from natural language:\n\ncomanda generate <output.yaml> \"<prompt>\"\n\n# Examples\ncomanda generate summarize.yaml \"Create a workflow that summarizes text input\"\ncomanda generate review.yaml \"Analyze code for bugs, then suggest fixes\" -m claude-sonnet-4-20250514\n\nVisualize a Workflow\n\nDisplay ASCII chart of workflow structure:\n\ncomanda chart <workflow.yaml>\ncomanda chart workflow.yaml --verbose\n\n\nShows step relationships, models used, input/output chains, and validity.\n\nProcess/Execute a Workflow\n\nRun a workflow file:\n\ncomanda process <workflow.yaml>\n\n# With input\ncat file.txt | comanda process analyze.yaml\necho \"Design a REST API\" | comanda process multi-agent.yaml\n\n# Multiple workflows\ncomanda process step1.yaml step2.yaml step3.yaml\n\nView/Edit Workflows\n\nWorkflow files are YAML. Read them directly to understand or modify:\n\ncat workflow.yaml\n\nWorkflow YAML Format\nBasic Step\nstep_name:\n  input: STDIN | NA | filename | $VARIABLE\n  model: gpt-4o | claude-sonnet-4-20250514 | gemini-pro | ollama/llama2 | claude-code | gemini-cli\n  action: \"Instruction for the model\"\n  output: STDOUT | filename | $VARIABLE\n\nParallel Execution\nparallel-process:\n  analysis-one:\n    input: STDIN\n    model: claude-sonnet-4-20250514\n    action: \"Analyze for security issues\"\n    output: $SECURITY\n\n  analysis-two:\n    input: STDIN\n    model: gpt-4o\n    action: \"Analyze for performance\"\n    output: $PERF\n\nChained Steps\nextract:\n  input: document.pdf\n  model: gpt-4o\n  action: \"Extract key points\"\n  output: $POINTS\n\nsummarize:\n  input: $POINTS\n  model: claude-sonnet-4-20250514\n  action: \"Create executive summary\"\n  output: STDOUT\n\nGenerate + Process (Meta-workflows)\ncreate_workflow:\n  input: NA\n  generate:\n    model: gpt-4o\n    action: \"Create a workflow that analyzes sentiment\"\n    output: generated.yaml\n\nrun_it:\n  input: NA\n  process:\n    workflow_file: generated.yaml\n\nAvailable Models\n\nRun comanda configure to set up API keys. Common models:\n\nProvider\tModels\nOpenAI\tgpt-4o, gpt-4o-mini, o1, o1-mini\nAnthropic\tclaude-sonnet-4-20250514, claude-opus-4-20250514\nGoogle\tgemini-pro, gemini-flash\nOllama\tollama/llama2, ollama/mistral, etc.\nAgentic\tclaude-code, gemini-cli, openai-codex\nExamples Location\n\nSee ~/clawd/comanda/examples/ for workflow samples:\n\nagentic-loop/ - Autonomous agent patterns\nclaude-code/ - Claude Code integration\ngemini-cli/ - Gemini CLI workflows\ndocument-processing/ - PDF, text extraction\ndatabase-connections/ - DB query workflows\nTroubleshooting\n\"model not configured\": Run comanda configure to add API keys\nWorkflow validation errors: Use comanda chart workflow.yaml to visualize and check validity\nDebug mode: Add --debug flag for verbose logging"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/kris-hansen/comanda",
    "publisherUrl": "https://clawhub.ai/kris-hansen/comanda",
    "owner": "kris-hansen",
    "version": "1.0.2",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/comanda",
    "downloadUrl": "https://openagent3.xyz/downloads/comanda",
    "agentUrl": "https://openagent3.xyz/skills/comanda/agent",
    "manifestUrl": "https://openagent3.xyz/skills/comanda/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/comanda/agent.md"
  }
}