{ "schemaVersion": "1.0", "item": { "slug": "agents-manager", "name": "Agent manager", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/agentandbot-design/agents-manager", "canonicalUrl": "https://clawhub.ai/agentandbot-design/agents-manager", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/agents-manager", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agents-manager", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "references/agent-profile-schema.md", "references/agent-registry.md", "references/health-check-template.md", "references/task-routing-rules.md", "scripts/can_assign.js" ], "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": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/agents-manager" }, "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/agents-manager", "agentPageUrl": "https://openagent3.xyz/skills/agents-manager/agent", "manifestUrl": "https://openagent3.xyz/skills/agents-manager/agent.json", "briefUrl": "https://openagent3.xyz/skills/agents-manager/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": "Agents Manager", "body": "Manage all Clawdbot agents centrally: discover available agents, profile their capabilities, define routing hierarchy (who can assign to whom, who reports to whom), and intelligently route new tasks through the escalation chain." }, { "title": "System Prompt (Copy-Paste)", "body": "Give this prompt to any agent to teach them this skill:\n\n\"You have access to the agents-manager skill. Use it to discover peers (scan_agents), check permissions (can_assign.js), and route tasks. Always follow the Handshake Protocol: Check requires_approval before assigning. If true, ask me first.\"" }, { "title": "Core Rules", "body": "Discovery: Always check scan_agents.js before assuming an agent exists.\nPermission: Never assign a task without checking can_assign.js or agent-registry.md.\nprotocol:\n\nIF requires_approval is FALSE -> Assign directly.\nIF requires_approval is TRUE -> Ask supervisor (Human or Agent)." }, { "title": "Quick Start", "body": "GoalCommandSetupnode scripts/setup_wizard.js (Run this first!)Listnode scripts/scan_agents.jsHealthnode scripts/health_check.jsStatsnode scripts/log_analyzer.js" }, { "title": "1. Agent Discovery & Profiling", "body": "List and profile all agents to understand their capabilities and routing configuration.\n\n# List all agents\nnode {baseDir}/scripts/scan_agents.js\n\n# Profile specific agent\nnode {baseDir}/scripts/generate_card.js " }, { "title": "2. Validation & Health", "body": "Ensure your agent ecosystem is healthy and valid.\n\n# Validate registry integrity\nnode {baseDir}/scripts/validate_registry.js\n\n# Check permissions (Agent A -> Agent B)\nnode {baseDir}/scripts/can_assign.js \n\n# Visualize hierarchy\nnode {baseDir}/scripts/visualize_agents.js" }, { "title": "3. Task Routing & Escalation", "body": "Define how tasks flow between agents using references/task-routing-rules.md.\n\nDirect: Agent → Agent (if can_assign_to allows)\nHandshake: Request approval if requires_approval is true.\nEscalation: Helper → Supervisor → Human" }, { "title": "Resources", "body": "agent-profile-schema.md: Standard profile with routing & card fields.\nagent-registry.md: Live registry of all agents.\ntask-routing-rules.md: Decision matrix and handshake protocol." }, { "title": "Scripts", "body": "scan_agents.js: Discovery tool\nvalidate_registry.js: Schema validator\ncan_assign.js: Permission checker\ngenerate_card.js: Agent card generator\nvisualize_agents.js: Hierarchy visualizer\nscan_agents.js: Discovery tool\nvalidate_registry.js: Schema validator\ncan_assign.js: Permission checker\ngenerate_card.js: Agent card generator\nvisualize_agents.js: Hierarchy visualizer\nhealth_check.js: Status monitor (Healthy/Slow/Offline)\nlog_analyzer.js: Performance stats (Jobs/Success Rate)\nsetup_wizard.js: Interactive configuration tool" } ], "body": "Agents Manager\n\nManage all Clawdbot agents centrally: discover available agents, profile their capabilities, define routing hierarchy (who can assign to whom, who reports to whom), and intelligently route new tasks through the escalation chain.\n\n🤖 For Agents\nSystem Prompt (Copy-Paste)\n\nGive this prompt to any agent to teach them this skill:\n\n\"You have access to the agents-manager skill. Use it to discover peers (scan_agents), check permissions (can_assign.js), and route tasks. Always follow the Handshake Protocol: Check requires_approval before assigning. If true, ask me first.\"\n\nCore Rules\nDiscovery: Always check scan_agents.js before assuming an agent exists.\nPermission: Never assign a task without checking can_assign.js or agent-registry.md.\nprotocol:\nIF requires_approval is FALSE -> Assign directly.\nIF requires_approval is TRUE -> Ask supervisor (Human or Agent).\n👤 For Humans\nQuick Start\nGoal\tCommand\nSetup\tnode scripts/setup_wizard.js (Run this first!)\nList\tnode scripts/scan_agents.js\nHealth\tnode scripts/health_check.js\nStats\tnode scripts/log_analyzer.js\n1. Agent Discovery & Profiling\n\nList and profile all agents to understand their capabilities and routing configuration.\n\n# List all agents\nnode {baseDir}/scripts/scan_agents.js\n\n# Profile specific agent\nnode {baseDir}/scripts/generate_card.js \n\n2. Validation & Health\n\nEnsure your agent ecosystem is healthy and valid.\n\n# Validate registry integrity\nnode {baseDir}/scripts/validate_registry.js\n\n# Check permissions (Agent A -> Agent B)\nnode {baseDir}/scripts/can_assign.js \n\n# Visualize hierarchy\nnode {baseDir}/scripts/visualize_agents.js\n\n3. Task Routing & Escalation\n\nDefine how tasks flow between agents using references/task-routing-rules.md.\n\nDirect: Agent → Agent (if can_assign_to allows)\nHandshake: Request approval if requires_approval is true.\nEscalation: Helper → Supervisor → Human\nResources\nagent-profile-schema.md: Standard profile with routing & card fields.\nagent-registry.md: Live registry of all agents.\ntask-routing-rules.md: Decision matrix and handshake protocol.\nScripts\nscan_agents.js: Discovery tool\nvalidate_registry.js: Schema validator\ncan_assign.js: Permission checker\ngenerate_card.js: Agent card generator\nvisualize_agents.js: Hierarchy visualizer\nscan_agents.js: Discovery tool\nvalidate_registry.js: Schema validator\ncan_assign.js: Permission checker\ngenerate_card.js: Agent card generator\nvisualize_agents.js: Hierarchy visualizer\nhealth_check.js: Status monitor (Healthy/Slow/Offline)\nlog_analyzer.js: Performance stats (Jobs/Success Rate)\nsetup_wizard.js: Interactive configuration tool" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/agentandbot-design/agents-manager", "publisherUrl": "https://clawhub.ai/agentandbot-design/agents-manager", "owner": "agentandbot-design", "version": "1.0.2", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/agents-manager", "downloadUrl": "https://openagent3.xyz/downloads/agents-manager", "agentUrl": "https://openagent3.xyz/skills/agents-manager/agent", "manifestUrl": "https://openagent3.xyz/skills/agents-manager/agent.json", "briefUrl": "https://openagent3.xyz/skills/agents-manager/agent.md" } }