Task Router Skill
Task Router
Notify the user before starting any long-running task and keep them updated. Use when a task will take noticeable time (>2-3 minutes). Send a start message, schedule a 5‑minute heartbeat update, and send a completion message immediately when done.
Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.
SkillHub CLI
skillhub install fogyoy/let-me-knowInspect the source and compatibility requirements, then follow its installation steps.
Give your agent the source link and ask it to inspect instructions and dependencies before explaining the installation steps.
Ensure the user is informed before long-running tasks start, gets periodic updates on a configurable interval (default 5 minutes), and receives an immediate completion/failure notice. Heartbeat messages must reflect real-time progress, not a repeated template.
Use this skill whenever a task will take noticeable time (>2–3 minutes) or involves long-running installs/builds/tests.
everyMs=300000). If the user specifies a different interval, use it.sleep <interval> → 读取进度 → message send 发一次动态进度。cron add 创建心跳 job 时,payload.deliver=false(避免“收到/启动”之类消息被转发给用户)。message send 主动推送进度。<task>-state.json),供清理使用。cron list,若已存在同名心跳 job,先 remove(去重)。进度:<最新步骤/阶段>(<关键指标>)。下一步:<next>。完成/失败会立刻通知你。
失败:<task> 发生错误(简述原因)。已停止心跳提醒。
These signals come from indexed source analysis and may lag behind changes. Check the current source files.
# Let Me Know ## Purpose Ensure the user is informed **before** long-running tasks start, gets periodic updates on a **configurable interval** (default 5 minutes), and receives an immediate completion/failure notice. Heartbeat messages must reflect **real-time progress**, not a repeated template. ## Trigger Use this skill whenever a task will take noticeable time (>2–3 minutes) or involves long-running installs/builds/tests. ## Workflow (required) 1) **Pre-flight message** (before starting): - Send a short message: what will run, estimated time, and explicitly state: - “完成或失败都会立刻通知你;期间我每 **X 分钟** 发一次进度心跳,您也可以修改心跳时间间隔。” 2) **Start a heartbeat (configurable interval, with pre-check)** - **Default interval = 5 minutes** (`everyMs=300000`). If the user specifies a different interval, use it. - Schedule repeating updates while the task runs. - **Before each heartbeat message**, read the latest progress (state file/logs) and send **current** progress (no repeated template): - Running → include latest step, progress metrics, and next step. - Failed → send failure notice **and stop the heartbeat**. - **优先推荐:同一条 agentTurn 内“原地心跳”**(不创建额外 cron): - 在长任务执行期间,用循环 `sleep <interval>` → 读取进度 → `message send` 发一次动态进度。 - 任务结束自然停止,不会遗留心跳任务。 - **只有在必须脱离当前执行流时才用 cron 心跳**,并且必须满足: - 通过 `cron add` 创建心跳 job 时,**payload.deliver=false**(避免“收到/启动”之类消息被转发给用户)。 - 心跳 job 内部用 `message send` 主动推送进度。 - 创建后把返回的 **heartbeatJobId** 写入状态文件(例如 `<task>-state.json`),供清理使用。 - 创建前先 `cron list`,若已存在同名心跳 job,先 remove(去重)。 - Content template (dynamic): - Running: `进度:<最新步骤/阶段>(<关键指标>)。下一步:<next>。完成/失败会立刻通知你。` - Failed: `失败:<task> 发生错误(简述原因)。已停止心跳提醒。` 3) **Run the task** - Execute the long-running command(s). 4) **Completi...
Task Router
Register, communicate, and earn on the x402hub AI agent marketplace. Use when an agent needs to register on x402hub, browse or claim bounties, submit deliverables, send messages to other agents via x402 Relay,...
Real-time event bus for AI agents. Publish, subscribe, and share live signals across a network of agents with Unix-style simplicity.
OpenClaw integration guidance for CAPTCHAS Agent API, including OpenResponses tool schemas and plugin tool registration.