Task Dispatcher

智能任务分发与子代理协调中枢。当用户提交任何任务时，执行需求分析、任务拆解、分发策略制定，分发给合适的 subagent 执行，监控进度并阶段汇报，最终汇总结果。失败时自动兜底处理。适用于：（1）用户直接下达的任务（2）cron/heartbeat 触发的任务（3）任何需要多步骤处理的工作。

Before installing or enabling this skill: 1) Confirm whether your runtime provides a 'subagents' tool and what that tool is allowed to do. 2) Ask the author to clarify/patch cleanup.yaml: set require_confirmation:true, disable cleanup_on_start, and remove any rules that delete arbitrary host files. 3) Remove or parameterize hard-coded absolute paths (e.g., /Users/xiaotiac/...) to avoid accidental access to user directories. 4) Verify that the skill will not read or act on host filesystem paths, environment variables, or webhooks unless you explicitly configure them; if Slack/email/webhook placeholders are used, ensure no secrets are auto-read. 5) Test the skill in a restricted sandbox or non-production account with monitoring/logging enabled to observe behavior (especially any file system or network actions). 6) If you plan to allow autonomous runs, require explicit confirmation for HIGH/CRITICAL actions and audit logs for any auto-abort/auto-delete actions. These checks will reduce the risk that the dispatcher executes destructive cleanup or accesses unintended files.

Type: OpenClaw Skill Name: task-dispatcher Version: 1.0.0 The bundle is a sophisticated task orchestration system designed to manage sub-agents through structured pipelines. It includes robust safety and operational guardrails, such as 'Deadloop Prevention' in budget.yaml and a detailed cleanup policy in cleanup.yaml that explicitly blacklists sensitive files and directories (e.g., .env, .aws, SSH keys, and secrets) to prevent accidental data loss or exposure. The instructions in SKILL.md and SUPPLEMENTARY_DESIGN.md are consistent with the stated purpose of a multi-agent coordinator and show no signs of malicious intent, exfiltration, or unauthorized command execution.