{
  "schemaVersion": "1.0",
  "item": {
    "slug": "todokan",
    "name": "Todokan",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/BANATEALAB/todokan",
    "canonicalUrl": "https://clawhub.ai/BANATEALAB/todokan",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/todokan",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=todokan",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.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/todokan"
    },
    "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/todokan",
    "agentPageUrl": "https://openagent3.xyz/skills/todokan/agent",
    "manifestUrl": "https://openagent3.xyz/skills/todokan/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/todokan/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": "Todokan — Kanban Task Management",
        "body": "Todokan is a kanban-style task manager. You can manage the user's tasks, boards, and projects through MCP tools."
      },
      {
        "title": "Prerequisites",
        "body": "A Todokan MCP server must be available (see README for setup)\nRequired env vars: TODOKAN_API_KEY, TODOKAN_MCP_URL (declared in skill metadata)"
      },
      {
        "title": "Trigger — When to Activate This Skill",
        "body": "Activate the Todokan skill when the user has one of the following intents:\n\nIntentExampleCreate / edit / delete a task\"Create a task: review PR\"Show boards or tasks\"Show me my tasks\", \"What's on the dev board?\"Change status\"Mark task X as done\"Save research results\"Save this as a task / document in Todokan\"Briefing / summary from tasks\"Give me a briefing of my open tasks\"Attach a document to a task\"Write a note on task X\"Search topics across boards\"What did I note about the investor meeting?\"Retrieve changes since last check\"What's new since this morning?\"\n\nDo not activate when the user is just talking about tasks in general without referencing Todokan."
      },
      {
        "title": "Tool Ordering",
        "body": "Follow this order to achieve consistent results:"
      },
      {
        "title": "Reading (always orient first)",
        "body": "1. list_habitats            → Which workspaces exist?\n2. list_boards              → Which boards exist? (note the IDs)\n3. list_tasks               → Tasks on a board (with filters)\n4. search_across_habitats   → Full-text search across boards/habitats\n5. get_events_since         → Retrieve changes since a timestamp\n6. list_board_labels        → Available labels + usage counts\n7. list_task_documents      → Documents attached to a task\n8. read_document            → Content of a document"
      },
      {
        "title": "Writing (only after orientation + confirmation)",
        "body": "9.  create_task / create_board / create_habitat\n10. update_task / update_task_by_title\n11. create_document / add_document_to_task\n12. delete_task              → Only after explicit confirmation"
      },
      {
        "title": "AI-Assisted (optional)",
        "body": "13. propose_task_variants    → Generate 2-3 variants\n14. confirm_task_fields      → Review fields before creation\n\nGolden rule: Never write blindly. Always call list_boards first to discover IDs — never guess UUIDs."
      },
      {
        "title": "Mandatory Checks",
        "body": "Before executing write actions, clarify the following:"
      },
      {
        "title": "Before create_task",
        "body": "Board: Which board? (If unclear → show list_boards, let the user choose)\n Title: Short, precise, imperative (max 80 characters)\n Priority: low / normal / high — default to normal if unclear\n Due date: Only set if mentioned by the user"
      },
      {
        "title": "Before update_task",
        "body": "Correct task? State the title + board for confirmation\n Which fields? Only change the fields the user requested"
      },
      {
        "title": "Before delete_task",
        "body": "Always ask for explicit confirmation — \"Should I permanently delete task '[Title]' on board '[Board]'? This cannot be undone.\""
      },
      {
        "title": "Before create_document",
        "body": "Clarify format: markdown, text, or html\n Link: Attach to which task (or standalone)?"
      },
      {
        "title": "No Hallucination",
        "body": "Use only real data from MCP tool responses. Never fabricate task IDs, board names, or content.\nIf a tool call fails or returns empty data: inform the user, do not improvise.\nWhen in doubt, show the actual results and ask."
      },
      {
        "title": "No Sensitive Data",
        "body": "Do not store passwords, API keys, tokens, or personal data in task titles or descriptions.\nIf the user mentions sensitive information, warn them: \"This may contain sensitive data — should I really store it in Todokan?\""
      },
      {
        "title": "Source Attribution",
        "body": "When storing content from external research (web, files, other tools) in Todokan, note the source in the task description or document:\nSource: [URL or filename]\nCreated by: Agent on [date]"
      },
      {
        "title": "Scope Awareness",
        "body": "Worker endpoint (/mcp-worker): Read-only + comments (add_comment). No task/board CUD, no document creation.\nPlanner endpoint (/mcp): Full access. Still ask before destructive actions.\nOn scope errors: explain to the user that the current endpoint does not have the required permissions."
      },
      {
        "title": "Idempotency",
        "body": "On network errors: do not blindly retry the same action. First check whether the action was already performed (list_tasks)."
      },
      {
        "title": "Briefing (summary of existing tasks)",
        "body": "## Briefing: [Board Name] — [Date]\n\n**Open (todo):** X tasks\n**In progress (doing):** Y tasks\n**Completed (done):** Z tasks\n\n### Urgent (high priority)\n- [ ] [Task Title] — due [Date]\n- [ ] [Task Title] — due [Date]\n\n### In Progress\n- [~] [Task Title] — since [Date]\n\n### Next Steps\n[1-2 sentences recommendation based on the data]"
      },
      {
        "title": "Draft (preview before task creation)",
        "body": "## Task Draft\n\n| Field       | Value                         |\n|-------------|-------------------------------|\n| Board       | [Board Name]                  |\n| Title       | [Title, max 80 chars]         |\n| Description | [Description, max 500 chars]  |\n| Status      | todo                          |\n| Priority    | [low / normal / high]         |\n| Due         | [YYYY-MM-DD or —]             |\n| Labels      | [label1, label2]              |\n\nShould I create this task?"
      },
      {
        "title": "Document Draft",
        "body": "## Document Draft\n\n**Title:** [Title]\n**Format:** markdown\n**Linked to:** [Task Title] on [Board Name]\n\n---\n[Document content]\n---\n\nShould I create this document?"
      },
      {
        "title": "Data Model",
        "body": "Habitat (workspace/project)\n  └── Board (kanban board, type: \"task\" or \"thought\")\n       └── Task (individual item with status, priority, labels, due date)\n            └── Document (attached notes/docs in markdown, text, or html)\n\nHabitats group boards. A user can have multiple habitats.\nBoards are kanban boards. Type task for actionable items, thought for ideas/notes.\nTasks live on a board and move through status columns.\nDocuments are rich text attached to tasks."
      },
      {
        "title": "Status Values",
        "body": "StatusMeaningtodoNot starteddoingIn progressdoneCompleted"
      },
      {
        "title": "Priority Values",
        "body": "PriorityMeaninglowLow prioritynormalDefault priorityhighHigh/urgent priority"
      },
      {
        "title": "Reading Data",
        "body": "list_habitats — List all workspaces\nlist_boards — List all boards (returns id, name, version)\nlist_tasks — List tasks with filters: boardId, status, label/labels, limit, cursor\nsearch_across_habitats — Full-text search over habitats/boards/tasks in one call\nget_events_since — Unified feed since timestamp (task events + comments + documents)\nlist_board_labels — Get unique labels on a board with usage counts\nlist_task_documents — Get documents attached to a task\nread_document — Read a document's content\nlist_task_comments — List comments on a task"
      },
      {
        "title": "Creating & Modifying (Planner endpoint only)",
        "body": "create_habitat — Create a new workspace (name)\ncreate_board — Create a new board (name, optional habitatId, boardType)\ncreate_task — Create a task (title, boardId or boardName, optional description, dueDate, priority, labels)\nupdate_task — Update a task by ID (taskId, plus fields to change)\nupdate_task_by_title — Update a task by exact title match (titleExact, boardId or boardName)\ndelete_task — Permanently delete a task (taskId)\ncreate_document — Create a document (optional relatedTaskId to attach)\nadd_document_to_task — Attach a new document to a task\nadd_comment — Add a comment to a task"
      },
      {
        "title": "AI-Assisted Creation",
        "body": "propose_task_variants — Generate 2-3 task variants (short/standard/detailed) from a rough description\nconfirm_task_fields — Preview a variant's fields before creating it"
      },
      {
        "title": "AI Visibility Gate",
        "body": "By default, the MCP server only returns tasks where aiEnabled: true. Tasks with aiEnabled: false are invisible to MCP agents — they will not appear in list_tasks, search_across_habitats, get_events_since, or get_task.\n\nUsers control this via a \"Send to AI\" button on each task card. When clicked, it sets aiEnabled: true, assignee: 'ai', and status: 'doing'.\n\nTo see only AI-assigned tasks: list_tasks { \"assignee\": \"ai\" }\nTo see all AI-enabled tasks: list_tasks {} (default — only AI-enabled tasks are returned)\nTo explicitly include non-AI tasks: list_tasks { \"aiEnabled\": false } (override, useful for reporting)"
      },
      {
        "title": "OAuth & Authentication",
        "body": "OAuth 2.1 with PKCE (RS256 JWT)\nToken lifetime: 30 days, no refresh token\nPlanner (/mcp): Full CRUD access — all scopes\nWorker (/mcp-worker): boards:read, tasks:read, labels:read, docs:read, comments:read, comments:write\nNo rate limiting — still be conservative with calls\nActivity logging: Every tool call is logged server-side"
      },
      {
        "title": "List all tasks on a board",
        "body": "list_boards to find the board ID\nlist_tasks with boardId to get tasks"
      },
      {
        "title": "Create a task",
        "body": "create_task { \"title\": \"Review PR #42\", \"boardName\": \"Development\", \"priority\": \"high\", \"dueDate\": \"2026-03-01\" }"
      },
      {
        "title": "Move a task to done",
        "body": "update_task { \"taskId\": \"<uuid>\", \"status\": \"done\" }"
      },
      {
        "title": "Add labels to a task",
        "body": "update_task { \"taskId\": \"<uuid>\", \"labels\": [\"bug\", \"frontend\"] }"
      },
      {
        "title": "Find tasks by label",
        "body": "list_tasks { \"boardId\": \"<uuid>\", \"labels\": [\"bug\"] }"
      },
      {
        "title": "Search across all habitats",
        "body": "search_across_habitats { \"query\": \"investor meeting\", \"limit\": 20 }"
      },
      {
        "title": "Poll event feed (agent loop)",
        "body": "get_events_since { \"since\": \"2026-02-24T08:00:00Z\", \"limit\": 200 }"
      },
      {
        "title": "Tips",
        "body": "Always call list_boards first to discover available board IDs — don't guess UUIDs.\nUse boardName instead of boardId when the user refers to boards by name.\nDue dates use YYYY-MM-DD format.\nTask titles are max 80 characters, descriptions max 500 characters.\nLabels are free-form strings (max 10 per task).\nThe update_task tool requires the task's UUID. Use list_tasks to find it, or update_task_by_title if you only know the title."
      }
    ],
    "body": "Todokan — Kanban Task Management\n\nTodokan is a kanban-style task manager. You can manage the user's tasks, boards, and projects through MCP tools.\n\nPrerequisites\nA Todokan MCP server must be available (see README for setup)\nRequired env vars: TODOKAN_API_KEY, TODOKAN_MCP_URL (declared in skill metadata)\nTrigger — When to Activate This Skill\n\nActivate the Todokan skill when the user has one of the following intents:\n\nIntent\tExample\nCreate / edit / delete a task\t\"Create a task: review PR\"\nShow boards or tasks\t\"Show me my tasks\", \"What's on the dev board?\"\nChange status\t\"Mark task X as done\"\nSave research results\t\"Save this as a task / document in Todokan\"\nBriefing / summary from tasks\t\"Give me a briefing of my open tasks\"\nAttach a document to a task\t\"Write a note on task X\"\nSearch topics across boards\t\"What did I note about the investor meeting?\"\nRetrieve changes since last check\t\"What's new since this morning?\"\n\nDo not activate when the user is just talking about tasks in general without referencing Todokan.\n\nTool Ordering\n\nFollow this order to achieve consistent results:\n\nReading (always orient first)\n1. list_habitats            → Which workspaces exist?\n2. list_boards              → Which boards exist? (note the IDs)\n3. list_tasks               → Tasks on a board (with filters)\n4. search_across_habitats   → Full-text search across boards/habitats\n5. get_events_since         → Retrieve changes since a timestamp\n6. list_board_labels        → Available labels + usage counts\n7. list_task_documents      → Documents attached to a task\n8. read_document            → Content of a document\n\nWriting (only after orientation + confirmation)\n9.  create_task / create_board / create_habitat\n10. update_task / update_task_by_title\n11. create_document / add_document_to_task\n12. delete_task              → Only after explicit confirmation\n\nAI-Assisted (optional)\n13. propose_task_variants    → Generate 2-3 variants\n14. confirm_task_fields      → Review fields before creation\n\n\nGolden rule: Never write blindly. Always call list_boards first to discover IDs — never guess UUIDs.\n\nMandatory Checks\n\nBefore executing write actions, clarify the following:\n\nBefore create_task\n Board: Which board? (If unclear → show list_boards, let the user choose)\n Title: Short, precise, imperative (max 80 characters)\n Priority: low / normal / high — default to normal if unclear\n Due date: Only set if mentioned by the user\nBefore update_task\n Correct task? State the title + board for confirmation\n Which fields? Only change the fields the user requested\nBefore delete_task\n Always ask for explicit confirmation — \"Should I permanently delete task '[Title]' on board '[Board]'? This cannot be undone.\"\nBefore create_document\n Clarify format: markdown, text, or html\n Link: Attach to which task (or standalone)?\nGuardrails\nNo Hallucination\nUse only real data from MCP tool responses. Never fabricate task IDs, board names, or content.\nIf a tool call fails or returns empty data: inform the user, do not improvise.\nWhen in doubt, show the actual results and ask.\nNo Sensitive Data\nDo not store passwords, API keys, tokens, or personal data in task titles or descriptions.\nIf the user mentions sensitive information, warn them: \"This may contain sensitive data — should I really store it in Todokan?\"\nSource Attribution\nWhen storing content from external research (web, files, other tools) in Todokan, note the source in the task description or document:\nSource: [URL or filename]\nCreated by: Agent on [date]\n\nScope Awareness\nWorker endpoint (/mcp-worker): Read-only + comments (add_comment). No task/board CUD, no document creation.\nPlanner endpoint (/mcp): Full access. Still ask before destructive actions.\nOn scope errors: explain to the user that the current endpoint does not have the required permissions.\nIdempotency\nOn network errors: do not blindly retry the same action. First check whether the action was already performed (list_tasks).\nOutput Format\nBriefing (summary of existing tasks)\n## Briefing: [Board Name] — [Date]\n\n**Open (todo):** X tasks\n**In progress (doing):** Y tasks\n**Completed (done):** Z tasks\n\n### Urgent (high priority)\n- [ ] [Task Title] — due [Date]\n- [ ] [Task Title] — due [Date]\n\n### In Progress\n- [~] [Task Title] — since [Date]\n\n### Next Steps\n[1-2 sentences recommendation based on the data]\n\nDraft (preview before task creation)\n## Task Draft\n\n| Field       | Value                         |\n|-------------|-------------------------------|\n| Board       | [Board Name]                  |\n| Title       | [Title, max 80 chars]         |\n| Description | [Description, max 500 chars]  |\n| Status      | todo                          |\n| Priority    | [low / normal / high]         |\n| Due         | [YYYY-MM-DD or —]             |\n| Labels      | [label1, label2]              |\n\nShould I create this task?\n\nDocument Draft\n## Document Draft\n\n**Title:** [Title]\n**Format:** markdown\n**Linked to:** [Task Title] on [Board Name]\n\n---\n[Document content]\n---\n\nShould I create this document?\n\nData Model\nHabitat (workspace/project)\n  └── Board (kanban board, type: \"task\" or \"thought\")\n       └── Task (individual item with status, priority, labels, due date)\n            └── Document (attached notes/docs in markdown, text, or html)\n\nHabitats group boards. A user can have multiple habitats.\nBoards are kanban boards. Type task for actionable items, thought for ideas/notes.\nTasks live on a board and move through status columns.\nDocuments are rich text attached to tasks.\nStatus Values\nStatus\tMeaning\ntodo\tNot started\ndoing\tIn progress\ndone\tCompleted\nPriority Values\nPriority\tMeaning\nlow\tLow priority\nnormal\tDefault priority\nhigh\tHigh/urgent priority\nAvailable MCP Tools\nReading Data\nlist_habitats — List all workspaces\nlist_boards — List all boards (returns id, name, version)\nlist_tasks — List tasks with filters: boardId, status, label/labels, limit, cursor\nsearch_across_habitats — Full-text search over habitats/boards/tasks in one call\nget_events_since — Unified feed since timestamp (task events + comments + documents)\nlist_board_labels — Get unique labels on a board with usage counts\nlist_task_documents — Get documents attached to a task\nread_document — Read a document's content\nlist_task_comments — List comments on a task\nCreating & Modifying (Planner endpoint only)\ncreate_habitat — Create a new workspace (name)\ncreate_board — Create a new board (name, optional habitatId, boardType)\ncreate_task — Create a task (title, boardId or boardName, optional description, dueDate, priority, labels)\nupdate_task — Update a task by ID (taskId, plus fields to change)\nupdate_task_by_title — Update a task by exact title match (titleExact, boardId or boardName)\ndelete_task — Permanently delete a task (taskId)\ncreate_document — Create a document (optional relatedTaskId to attach)\nadd_document_to_task — Attach a new document to a task\nadd_comment — Add a comment to a task\nAI-Assisted Creation\npropose_task_variants — Generate 2-3 task variants (short/standard/detailed) from a rough description\nconfirm_task_fields — Preview a variant's fields before creating it\nAI Visibility Gate\n\nBy default, the MCP server only returns tasks where aiEnabled: true. Tasks with aiEnabled: false are invisible to MCP agents — they will not appear in list_tasks, search_across_habitats, get_events_since, or get_task.\n\nUsers control this via a \"Send to AI\" button on each task card. When clicked, it sets aiEnabled: true, assignee: 'ai', and status: 'doing'.\n\nTo see only AI-assigned tasks: list_tasks { \"assignee\": \"ai\" }\nTo see all AI-enabled tasks: list_tasks {} (default — only AI-enabled tasks are returned)\nTo explicitly include non-AI tasks: list_tasks { \"aiEnabled\": false } (override, useful for reporting)\nOAuth & Authentication\nOAuth 2.1 with PKCE (RS256 JWT)\nToken lifetime: 30 days, no refresh token\nPlanner (/mcp): Full CRUD access — all scopes\nWorker (/mcp-worker): boards:read, tasks:read, labels:read, docs:read, comments:read, comments:write\nNo rate limiting — still be conservative with calls\nActivity logging: Every tool call is logged server-side\nCommon Workflows\nList all tasks on a board\nlist_boards to find the board ID\nlist_tasks with boardId to get tasks\nCreate a task\ncreate_task { \"title\": \"Review PR #42\", \"boardName\": \"Development\", \"priority\": \"high\", \"dueDate\": \"2026-03-01\" }\n\nMove a task to done\nupdate_task { \"taskId\": \"<uuid>\", \"status\": \"done\" }\n\nAdd labels to a task\nupdate_task { \"taskId\": \"<uuid>\", \"labels\": [\"bug\", \"frontend\"] }\n\nFind tasks by label\nlist_tasks { \"boardId\": \"<uuid>\", \"labels\": [\"bug\"] }\n\nSearch across all habitats\nsearch_across_habitats { \"query\": \"investor meeting\", \"limit\": 20 }\n\nPoll event feed (agent loop)\nget_events_since { \"since\": \"2026-02-24T08:00:00Z\", \"limit\": 200 }\n\nTips\nAlways call list_boards first to discover available board IDs — don't guess UUIDs.\nUse boardName instead of boardId when the user refers to boards by name.\nDue dates use YYYY-MM-DD format.\nTask titles are max 80 characters, descriptions max 500 characters.\nLabels are free-form strings (max 10 per task).\nThe update_task tool requires the task's UUID. Use list_tasks to find it, or update_task_by_title if you only know the title."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/BANATEALAB/todokan",
    "publisherUrl": "https://clawhub.ai/BANATEALAB/todokan",
    "owner": "BANATEALAB",
    "version": "1.3.2",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/todokan",
    "downloadUrl": "https://openagent3.xyz/downloads/todokan",
    "agentUrl": "https://openagent3.xyz/skills/todokan/agent",
    "manifestUrl": "https://openagent3.xyz/skills/todokan/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/todokan/agent.md"
  }
}