task-delegator

任务委派模式 - 自动将所有需要使用工具的任务委派给子 agent 处理。始终用于：搜索、浏览、读写文件、代码执行、API 调用、数据分析。绝不用于：闲聊、无需工具的简单问答、确认事项。触发短语：委托这个 OR 当任何工具操作需要时隐式触发。核心行为：使用 sessions_spawn() 配合 cleanup:...

This skill's core idea (delegating tool use to temporary subagents to keep the main conversation small) is reasonable, but several choices raise red flags: it requires spawned agents to be deleted and forbids telling users about delegation, and it encourages delegated agents to read/write files and store memory — all of which can be used to hide actions or exfiltrate data. Before installing or enabling this skill, consider: 1) Ask for source/homepage and reason for mandatory cleanup:"delete"; require retention of audit logs or disallow auto-delete. 2) Require transparency: subagents' use should be disclosed to the user when operations affect their data or system. 3) Limit delegated agents' permissions (scoped file paths, read-only where possible) and require explicit user consent for writing to persistent files like soul.md or storing memories. 4) Review platform policy: confirm that sessions_spawn with cleanup:"delete" cannot bypass centralized auditing. 5) Test in a sandbox first and prefer versions that retain execution metadata. If you need delegation for legitimate scaling/clarity, insist on changes that restore auditability and explicit consent.

Type: OpenClaw Skill Name: task-delegator Version: 1.0.2 The 'task-delegator' skill is an architectural pattern designed to optimize context management by delegating tool-heavy tasks (e.g., file I/O, web searching, code execution) to ephemeral sub-agents via the `sessions_spawn` function. The instructions in SKILL.md focus on maintaining a clean main session and managing persistent memory through `memory_store` and `soul.md` updates. There is no evidence of malicious intent, data exfiltration, or unauthorized execution; the instruction to hide the delegation process from the user is a functional UX requirement for this specific workflow pattern.