{
  "schemaVersion": "1.0",
  "item": {
    "slug": "eywa",
    "name": "Eywa",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/a-sumo/eywa",
    "canonicalUrl": "https://clawhub.ai/a-sumo/eywa",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/eywa",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=eywa",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "eywa-call.sh"
    ],
    "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/eywa"
    },
    "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/eywa",
    "agentPageUrl": "https://openagent3.xyz/skills/eywa/agent",
    "manifestUrl": "https://openagent3.xyz/skills/eywa/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/eywa/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": "Eywa: Multi-Agent Coordination Layer",
        "body": "You are now connected to Eywa, a coordination layer for agent swarms. Eywa gives you shared spatial memory, task management, conflict detection, and destination navigation across multiple concurrent agents."
      },
      {
        "title": "Setup",
        "body": "Your Eywa connection is configured via environment variables:\n\nEYWA_ROOM — the room slug (e.g. demo, my-project)\nEYWA_AGENT — your agent identity prefix (e.g. openclaw). The server appends a unique suffix like /jade-dusk.\nEYWA_URL — MCP endpoint (default: https://eywa-mcp.armandsumo.workers.dev)\n\nThe helper script at {baseDir}/eywa-call.sh handles all MCP communication."
      },
      {
        "title": "How to call Eywa tools",
        "body": "Use the exec tool to run the helper script:\n\nbash {baseDir}/eywa-call.sh <tool_name> '<json_arguments>'\n\nExamples:\n\n# Start a session (always do this first)\nbash {baseDir}/eywa-call.sh eywa_start '{\"task_description\":\"Implementing user auth\"}'\n\n# Log an operation with semantic tags\nbash {baseDir}/eywa-call.sh eywa_log '{\"role\":\"assistant\",\"content\":\"Added JWT middleware\",\"system\":\"api\",\"action\":\"create\",\"scope\":\"auth service\",\"outcome\":\"success\"}'\n\n# Check what other agents are doing\nbash {baseDir}/eywa-call.sh eywa_status '{}'\n\n# View the task queue\nbash {baseDir}/eywa-call.sh eywa_tasks '{}'\n\n# Claim a task\nbash {baseDir}/eywa-call.sh eywa_pick_task '{\"task_id\":\"<uuid>\"}'\n\n# Update task progress\nbash {baseDir}/eywa-call.sh eywa_update_task '{\"task_id\":\"<uuid>\",\"status\":\"in_progress\",\"notes\":\"Working on it\"}'\n\n# Store knowledge that persists across sessions\nbash {baseDir}/eywa-call.sh eywa_learn '{\"content\":\"Auth uses JWT with RS256, tokens expire in 1h\",\"tags\":[\"auth\",\"api\"],\"title\":\"JWT auth pattern\"}'\n\n# Set the team destination\nbash {baseDir}/eywa-call.sh eywa_destination '{\"action\":\"set\",\"destination\":\"Ship v1.0 with auth, billing, and dashboard\",\"milestones\":[\"Auth system\",\"Billing integration\",\"Dashboard MVP\"]}'\n\n# Mark session complete\nbash {baseDir}/eywa-call.sh eywa_done '{\"summary\":\"Implemented JWT auth middleware\",\"status\":\"completed\",\"artifacts\":[\"src/middleware/auth.ts\"],\"tags\":[\"auth\",\"feature\"]}'"
      },
      {
        "title": "Session lifecycle",
        "body": "eywa_start — Start a session. Returns a room snapshot with active agents, recent activity, tasks, destination, and relevant knowledge. Always call this first.\n\ntask_description (required): what you're working on\ncontinue_from (optional): agent name to load context from (baton handoff)\n\n\n\neywa_done — Mark session complete with structured summary.\n\nsummary, status (completed/blocked/failed/partial), artifacts[], tags[], next_steps\n\n\n\neywa_stop — Quick session end with summary."
      },
      {
        "title": "Memory and logging",
        "body": "eywa_log — Log an operation with semantic tags. Other agents and humans see what you're doing.\n\nrole, content, system (git/api/deploy/filesystem/etc.), action (read/write/create/deploy/test/etc.), scope, outcome (success/failure/blocked)\n\n\n\neywa_learn — Store persistent knowledge (survives sessions).\n\ncontent, tags[], title\n\n\n\neywa_knowledge — Retrieve the knowledge base.\n\ntag, search, limit\n\n\n\neywa_search — Search all messages by content."
      },
      {
        "title": "Tasks",
        "body": "eywa_tasks — List tasks sorted by priority. Filter by status, assignee, milestone.\neywa_task — Create a new task.\neywa_pick_task — Claim an open task (sets status to claimed, creates work claim for conflict detection).\neywa_update_task — Update status, add notes, reassign.\neywa_subtask — Break a task into subtasks."
      },
      {
        "title": "Collaboration",
        "body": "eywa_status — See all agents, their work, systems, curvature scores.\neywa_claim — Declare your work scope and files. Triggers conflict detection.\neywa_context — Get shared context from all agents.\neywa_msg — Send a message to a specific agent or all."
      },
      {
        "title": "Navigation",
        "body": "eywa_destination — Set, update, or view the team destination with milestones and progress tracking."
      },
      {
        "title": "Workflow",
        "body": "Start: Call eywa_start with what you're working on. Read the snapshot.\nClaim: If picking up a task, call eywa_pick_task. Otherwise call eywa_claim with your scope.\nWork: Do your work. Log significant operations with eywa_log (tag with system/action/outcome).\nLearn: Store any knowledge worth keeping with eywa_learn.\nDone: Call eywa_done with summary, status, artifacts, and next steps."
      },
      {
        "title": "When to log",
        "body": "EventsystemactionoutcomeRead a filefilesystemreadsuccessWrite/edit a filefilesystemwritesuccessCreate new filefilesystemcreatesuccessRun testscitestsuccess/failureGit commitgitwritesuccessGit pushgitdeploysuccess/failureDeploy to staging/proddeploydeploysuccess/failureAPI callapiread/writesuccess/failureDatabase migrationdatabasewritesuccess/failureHit a blocker(relevant)(relevant)blocked\n\nLog enough that another agent could understand what you did and continue your work."
      },
      {
        "title": "Key principles",
        "body": "Coordinate, don't duplicate: Check eywa_status and eywa_tasks before starting work. If another agent is already on it, pick something else.\nLog operations: Every significant action should be tagged. Invisible agents have zero curvature.\nStore knowledge: If you discover something useful (a pattern, a gotcha, a convention), call eywa_learn. Future sessions benefit.\nWork toward the destination: Check eywa_destination to understand the goal. Your work should converge toward it."
      }
    ],
    "body": "Eywa: Multi-Agent Coordination Layer\n\nYou are now connected to Eywa, a coordination layer for agent swarms. Eywa gives you shared spatial memory, task management, conflict detection, and destination navigation across multiple concurrent agents.\n\nSetup\n\nYour Eywa connection is configured via environment variables:\n\nEYWA_ROOM — the room slug (e.g. demo, my-project)\nEYWA_AGENT — your agent identity prefix (e.g. openclaw). The server appends a unique suffix like /jade-dusk.\nEYWA_URL — MCP endpoint (default: https://eywa-mcp.armandsumo.workers.dev)\n\nThe helper script at {baseDir}/eywa-call.sh handles all MCP communication.\n\nHow to call Eywa tools\n\nUse the exec tool to run the helper script:\n\nbash {baseDir}/eywa-call.sh <tool_name> '<json_arguments>'\n\n\nExamples:\n\n# Start a session (always do this first)\nbash {baseDir}/eywa-call.sh eywa_start '{\"task_description\":\"Implementing user auth\"}'\n\n# Log an operation with semantic tags\nbash {baseDir}/eywa-call.sh eywa_log '{\"role\":\"assistant\",\"content\":\"Added JWT middleware\",\"system\":\"api\",\"action\":\"create\",\"scope\":\"auth service\",\"outcome\":\"success\"}'\n\n# Check what other agents are doing\nbash {baseDir}/eywa-call.sh eywa_status '{}'\n\n# View the task queue\nbash {baseDir}/eywa-call.sh eywa_tasks '{}'\n\n# Claim a task\nbash {baseDir}/eywa-call.sh eywa_pick_task '{\"task_id\":\"<uuid>\"}'\n\n# Update task progress\nbash {baseDir}/eywa-call.sh eywa_update_task '{\"task_id\":\"<uuid>\",\"status\":\"in_progress\",\"notes\":\"Working on it\"}'\n\n# Store knowledge that persists across sessions\nbash {baseDir}/eywa-call.sh eywa_learn '{\"content\":\"Auth uses JWT with RS256, tokens expire in 1h\",\"tags\":[\"auth\",\"api\"],\"title\":\"JWT auth pattern\"}'\n\n# Set the team destination\nbash {baseDir}/eywa-call.sh eywa_destination '{\"action\":\"set\",\"destination\":\"Ship v1.0 with auth, billing, and dashboard\",\"milestones\":[\"Auth system\",\"Billing integration\",\"Dashboard MVP\"]}'\n\n# Mark session complete\nbash {baseDir}/eywa-call.sh eywa_done '{\"summary\":\"Implemented JWT auth middleware\",\"status\":\"completed\",\"artifacts\":[\"src/middleware/auth.ts\"],\"tags\":[\"auth\",\"feature\"]}'\n\nAvailable tools\nSession lifecycle\n\neywa_start — Start a session. Returns a room snapshot with active agents, recent activity, tasks, destination, and relevant knowledge. Always call this first.\n\ntask_description (required): what you're working on\ncontinue_from (optional): agent name to load context from (baton handoff)\n\neywa_done — Mark session complete with structured summary.\n\nsummary, status (completed/blocked/failed/partial), artifacts[], tags[], next_steps\n\neywa_stop — Quick session end with summary.\n\nMemory and logging\n\neywa_log — Log an operation with semantic tags. Other agents and humans see what you're doing.\n\nrole, content, system (git/api/deploy/filesystem/etc.), action (read/write/create/deploy/test/etc.), scope, outcome (success/failure/blocked)\n\neywa_learn — Store persistent knowledge (survives sessions).\n\ncontent, tags[], title\n\neywa_knowledge — Retrieve the knowledge base.\n\ntag, search, limit\n\neywa_search — Search all messages by content.\n\nTasks\neywa_tasks — List tasks sorted by priority. Filter by status, assignee, milestone.\neywa_task — Create a new task.\neywa_pick_task — Claim an open task (sets status to claimed, creates work claim for conflict detection).\neywa_update_task — Update status, add notes, reassign.\neywa_subtask — Break a task into subtasks.\nCollaboration\neywa_status — See all agents, their work, systems, curvature scores.\neywa_claim — Declare your work scope and files. Triggers conflict detection.\neywa_context — Get shared context from all agents.\neywa_msg — Send a message to a specific agent or all.\nNavigation\neywa_destination — Set, update, or view the team destination with milestones and progress tracking.\nWorkflow\nStart: Call eywa_start with what you're working on. Read the snapshot.\nClaim: If picking up a task, call eywa_pick_task. Otherwise call eywa_claim with your scope.\nWork: Do your work. Log significant operations with eywa_log (tag with system/action/outcome).\nLearn: Store any knowledge worth keeping with eywa_learn.\nDone: Call eywa_done with summary, status, artifacts, and next steps.\nWhen to log\nEvent\tsystem\taction\toutcome\nRead a file\tfilesystem\tread\tsuccess\nWrite/edit a file\tfilesystem\twrite\tsuccess\nCreate new file\tfilesystem\tcreate\tsuccess\nRun tests\tci\ttest\tsuccess/failure\nGit commit\tgit\twrite\tsuccess\nGit push\tgit\tdeploy\tsuccess/failure\nDeploy to staging/prod\tdeploy\tdeploy\tsuccess/failure\nAPI call\tapi\tread/write\tsuccess/failure\nDatabase migration\tdatabase\twrite\tsuccess/failure\nHit a blocker\t(relevant)\t(relevant)\tblocked\n\nLog enough that another agent could understand what you did and continue your work.\n\nKey principles\nCoordinate, don't duplicate: Check eywa_status and eywa_tasks before starting work. If another agent is already on it, pick something else.\nLog operations: Every significant action should be tagged. Invisible agents have zero curvature.\nStore knowledge: If you discover something useful (a pattern, a gotcha, a convention), call eywa_learn. Future sessions benefit.\nWork toward the destination: Check eywa_destination to understand the goal. Your work should converge toward it."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/a-sumo/eywa",
    "publisherUrl": "https://clawhub.ai/a-sumo/eywa",
    "owner": "a-sumo",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/eywa",
    "downloadUrl": "https://openagent3.xyz/downloads/eywa",
    "agentUrl": "https://openagent3.xyz/skills/eywa/agent",
    "manifestUrl": "https://openagent3.xyz/skills/eywa/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/eywa/agent.md"
  }
}