{
  "schemaVersion": "1.0",
  "item": {
    "slug": "migma",
    "name": "Migma",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/AdamSEY/migma",
    "canonicalUrl": "https://clawhub.ai/AdamSEY/migma",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/migma",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=migma",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/workflows.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": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-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/migma"
    },
    "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/migma",
    "agentPageUrl": "https://openagent3.xyz/skills/migma/agent",
    "manifestUrl": "https://openagent3.xyz/skills/migma/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/migma/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": "Migma",
        "body": "Create and send professional, on-brand emails with AI. Your agent can design emails from a prompt, send them instantly through a managed domain, and manage an entire audience — all from the terminal.\n\nAlways pass --json for structured output."
      },
      {
        "title": "First-time setup",
        "body": "If the user hasn't set up yet, run these steps once:\n\n# 1. Create an instant sending domain (no DNS needed)\nmigma domains managed create <companyname> --json\n# → Sends from: hello@<companyname>.migma.email\n\n# 2. Set a default project (brand)\nmigma projects list --json\nmigma projects use <projectId>"
      },
      {
        "title": "Create an email",
        "body": "When the user asks to create, design, or generate an email:\n\nmigma generate \"Welcome email for new subscribers\" --wait --json\n\nThe --wait flag blocks until the AI finishes. The JSON response includes conversationId, subject, and html.\n\nTo save the HTML locally, add --save ./email.html. To include a reference image (screenshot, design mockup), add --image <url>."
      },
      {
        "title": "Send an email",
        "body": "When the user asks to send an email to someone:\n\n# Send a generated email directly\nmigma send --to sarah@example.com --subject \"Welcome!\" \\\n  --from-conversation <conversationId> \\\n  --from hello@company.migma.email --from-name \"Company\" --json\n\n# Or send from a local HTML file\nmigma send --to sarah@example.com --subject \"Hello\" \\\n  --html ./email.html \\\n  --from hello@company.migma.email --from-name \"Company\" --json\n\n# Send to an entire segment or tag\nmigma send --segment <id> --subject \"Big News\" --html ./email.html \\\n  --from hello@company.migma.email --from-name \"Company\" --json\n\n# Personalize with template variables\nmigma send --to user@example.com --subject \"Hi {{name}}\" --html ./email.html \\\n  --from hello@company.migma.email --from-name \"Company\" \\\n  --var name=Sarah --var discount=20 --json\n\n--from-conversation auto-exports the HTML from a generated email — no separate export step."
      },
      {
        "title": "Validate an email",
        "body": "When the user wants to check an email before sending:\n\nmigma validate all --html ./email.html --json\nmigma validate all --conversation <conversationId> --json\n\nReturns an overall score plus individual checks: compatibility (30+ email clients), broken links, spelling/grammar, and deliverability/spam score. Individual checks: migma validate compatibility, links, spelling, deliverability."
      },
      {
        "title": "Export to platforms",
        "body": "When the user wants to export to an ESP or download a file:\n\nmigma export html <conversationId> --output ./email.html\nmigma export klaviyo <conversationId> --json\nmigma export mailchimp <conversationId> --json\nmigma export hubspot <conversationId> --json\nmigma export pdf <conversationId> --json\nmigma export mjml <conversationId> --json"
      },
      {
        "title": "Manage contacts",
        "body": "migma contacts add --email user@example.com --firstName John --json\nmigma contacts list --json\nmigma contacts import ./contacts.csv --json\nmigma contacts remove <id> --json"
      },
      {
        "title": "Manage tags and segments",
        "body": "migma tags create --name \"VIP\" --json\nmigma tags list --json\nmigma segments create --name \"Active Users\" --description \"...\" --json\nmigma segments list --json"
      },
      {
        "title": "Import a brand",
        "body": "When the user wants to set up a new brand from their website:\n\nmigma projects import https://yourbrand.com --wait --json\nmigma projects use <projectId>\n\nThis fetches logos, colors, fonts, and brand voice automatically."
      },
      {
        "title": "Error handling",
        "body": "On error, --json returns:\n\n{\"error\": {\"message\": \"Not found\", \"code\": \"not_found\", \"statusCode\": 404}}"
      }
    ],
    "body": "Migma\n\nCreate and send professional, on-brand emails with AI. Your agent can design emails from a prompt, send them instantly through a managed domain, and manage an entire audience — all from the terminal.\n\nAlways pass --json for structured output.\n\nFirst-time setup\n\nIf the user hasn't set up yet, run these steps once:\n\n# 1. Create an instant sending domain (no DNS needed)\nmigma domains managed create <companyname> --json\n# → Sends from: hello@<companyname>.migma.email\n\n# 2. Set a default project (brand)\nmigma projects list --json\nmigma projects use <projectId>\n\nCreate an email\n\nWhen the user asks to create, design, or generate an email:\n\nmigma generate \"Welcome email for new subscribers\" --wait --json\n\n\nThe --wait flag blocks until the AI finishes. The JSON response includes conversationId, subject, and html.\n\nTo save the HTML locally, add --save ./email.html. To include a reference image (screenshot, design mockup), add --image <url>.\n\nSend an email\n\nWhen the user asks to send an email to someone:\n\n# Send a generated email directly\nmigma send --to sarah@example.com --subject \"Welcome!\" \\\n  --from-conversation <conversationId> \\\n  --from hello@company.migma.email --from-name \"Company\" --json\n\n# Or send from a local HTML file\nmigma send --to sarah@example.com --subject \"Hello\" \\\n  --html ./email.html \\\n  --from hello@company.migma.email --from-name \"Company\" --json\n\n# Send to an entire segment or tag\nmigma send --segment <id> --subject \"Big News\" --html ./email.html \\\n  --from hello@company.migma.email --from-name \"Company\" --json\n\n# Personalize with template variables\nmigma send --to user@example.com --subject \"Hi {{name}}\" --html ./email.html \\\n  --from hello@company.migma.email --from-name \"Company\" \\\n  --var name=Sarah --var discount=20 --json\n\n\n--from-conversation auto-exports the HTML from a generated email — no separate export step.\n\nValidate an email\n\nWhen the user wants to check an email before sending:\n\nmigma validate all --html ./email.html --json\nmigma validate all --conversation <conversationId> --json\n\n\nReturns an overall score plus individual checks: compatibility (30+ email clients), broken links, spelling/grammar, and deliverability/spam score. Individual checks: migma validate compatibility, links, spelling, deliverability.\n\nExport to platforms\n\nWhen the user wants to export to an ESP or download a file:\n\nmigma export html <conversationId> --output ./email.html\nmigma export klaviyo <conversationId> --json\nmigma export mailchimp <conversationId> --json\nmigma export hubspot <conversationId> --json\nmigma export pdf <conversationId> --json\nmigma export mjml <conversationId> --json\n\nManage contacts\nmigma contacts add --email user@example.com --firstName John --json\nmigma contacts list --json\nmigma contacts import ./contacts.csv --json\nmigma contacts remove <id> --json\n\nManage tags and segments\nmigma tags create --name \"VIP\" --json\nmigma tags list --json\nmigma segments create --name \"Active Users\" --description \"...\" --json\nmigma segments list --json\n\nImport a brand\n\nWhen the user wants to set up a new brand from their website:\n\nmigma projects import https://yourbrand.com --wait --json\nmigma projects use <projectId>\n\n\nThis fetches logos, colors, fonts, and brand voice automatically.\n\nError handling\n\nOn error, --json returns:\n\n{\"error\": {\"message\": \"Not found\", \"code\": \"not_found\", \"statusCode\": 404}}"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/AdamSEY/migma",
    "publisherUrl": "https://clawhub.ai/AdamSEY/migma",
    "owner": "AdamSEY",
    "version": "1.3.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/migma",
    "downloadUrl": "https://openagent3.xyz/downloads/migma",
    "agentUrl": "https://openagent3.xyz/skills/migma/agent",
    "manifestUrl": "https://openagent3.xyz/skills/migma/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/migma/agent.md"
  }
}