Install
openclaw skills install feishu-parallel-dispatchUse in Feishu chats when the assistant should stay responsive while longer work continues in the background. Creates one spawned sub-agent task per substantial user prompt, keeps the foreground session short, and lets each child task report back independently when finished.
openclaw skills install feishu-parallel-dispatchUse this skill when working in Feishu and the user may send another prompt before the current task is done.
Pair it with feishu-progress-heartbeat or the equivalent heartbeat pattern so
long-running child tasks can send automatic progress updates about every 3
minutes while they are still active.
Keep the main Feishu chat responsive.
Do not let one long task occupy the foreground session when the work can be offloaded to a spawned sub-agent.
For any substantial Feishu request, prefer:
sessions_spawnFor substantial tasks, staying in the foreground without a spawned child is a failure mode, not an acceptable fallback.
This keeps the foreground session free so the next user prompt can create its own child task instead of waiting behind the previous one.
Spawn a child task when the request is likely to need any of these:
Do not spawn for tiny answers that can be completed immediately.
Treat each substantial user prompt as its own work item.
Pick the child agent with the clearest fit:
research: current facts, comparisons, source-backed analysisoffice: team planning, meeting outputs, shared project coordinationslides: personal planning, solo execution, personal review workfamily: family-shared tasks onlykittypuppy: couple-shared tasks onlycouncil: explicit multi-agent discussionUse short Feishu-friendly acknowledgement text, for example:
已接单,正在开一个独立任务处理,完成后我会直接回到这个会话。这个任务我先异步跑起来,你可以继续发下一个,我会分别回报。开始处理,这条我会交给独立子任务执行,做好后直接汇报结果。After this acknowledgement, spawn and stop. Do not stay in the foreground session doing the heavy work.
If the spawn fails, retry once immediately with a narrower label or a more obvious specialist. If it still fails, tell the user plainly that the background handoff failed and what fallback path you are taking.
Do not narrate the spawn mechanics, raw action payloads, or internal command objects to the user.
Each child task should report back independently when it finishes.
If the user asks:
还在吗哪些任务在跑第几个做完了这个是不是卡住了Then:
sessions_list with tree visibility to find active child sessionssession_status if neededDo not answer with a plan like "我先检查一下". Perform the status inspection first and reply only with the result.
If the inspection shows no active child but the last explicit request is still unfinished, immediately recreate a bounded continuation child for the missing next step before replying.
When spawning, use a short label so later status replies are readable.
Good labels:
行业调研项目周报旅行计划情侣清单PPT 生成If helpful, choose labels that make progress checks easier to read later.
Prefer short noun phrases over vague labels like 任务 or 处理中.