From sundial-org-awesome-openclaw-skills-4
Manages Clawdbot agents: discover available agents, profile capabilities, define routing hierarchies, check permissions, and assign tasks via Node.js CLI scripts.
npx claudepluginhub joshuarweaver/cascade-ai-ml-agents-misc-2 --plugin sundial-org-awesome-openclaw-skills-4This skill uses the workspace's default tool permissions.
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.
README.mdreferences/agent-profile-schema.mdreferences/agent-registry.mdreferences/health-check-template.mdreferences/task-routing-rules.mdscripts/can_assign.jsscripts/generate_card.jsscripts/health_check.jsscripts/log_analyzer.jsscripts/scan_agents.jsscripts/setup_wizard.jsscripts/validate_registry.jsscripts/visualize_agents.jsGuides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).
Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.
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.
Give this prompt to any agent to teach them this skill:
"You have access to the
agents-managerskill. Use it to discover peers (scan_agents), check permissions (can_assign.js), and route tasks. Always follow the Handshake Protocol: Checkrequires_approvalbefore assigning. If true, ask me first."
scan_agents.js before assuming an agent exists.can_assign.js or agent-registry.md.requires_approval is FALSE -> Assign directly.requires_approval is TRUE -> Ask supervisor (Human or Agent).| Goal | Command |
|---|---|
| Setup | node scripts/setup_wizard.js (Run this first!) |
| List | node scripts/scan_agents.js |
| Health | node scripts/health_check.js |
| Stats | node scripts/log_analyzer.js |
List and profile all agents to understand their capabilities and routing configuration.
# List all agents
node {baseDir}/scripts/scan_agents.js
# Profile specific agent
node {baseDir}/scripts/generate_card.js <agent_id>
Ensure your agent ecosystem is healthy and valid.
# Validate registry integrity
node {baseDir}/scripts/validate_registry.js
# Check permissions (Agent A -> Agent B)
node {baseDir}/scripts/can_assign.js <source_id> <target_id>
# Visualize hierarchy
node {baseDir}/scripts/visualize_agents.js
Define how tasks flow between agents using references/task-routing-rules.md.
can_assign_to allows)requires_approval is true.scan_agents.js: Discovery toolvalidate_registry.js: Schema validatorcan_assign.js: Permission checkergenerate_card.js: Agent card generatorvisualize_agents.js: Hierarchy visualizerscan_agents.js: Discovery toolvalidate_registry.js: Schema validatorcan_assign.js: Permission checkergenerate_card.js: Agent card generatorvisualize_agents.js: Hierarchy visualizerhealth_check.js: Status monitor (Healthy/Slow/Offline)log_analyzer.js: Performance stats (Jobs/Success Rate)setup_wizard.js: Interactive configuration tool