← 返回 Skills 市场
siaslfs

Live Task Pulse

作者 siaslfs · GitHub ↗ · v1.1.0
cross-platform ⚠ suspicious
309
总下载
0
收藏
2
当前安装
2
版本数
在 OpenClaw 中安装
/install live-task-pulse
功能描述
Real-time task progress tracking with live push notifications. MANDATORY for ALL multi-step tasks (>30s or >2 tool calls). Activate automatically — do not wa...
使用说明 (SKILL.md)

Live Task Pulse

Real-time task execution tracking with live push notifications.

Why This Exists

Other trackers write to files — users can't see progress until they ask. Live Task Pulse pushes every step change to the user's chat instantly via OpenClaw's message tool, while persisting state to JSON for crash recovery.

Architecture

┌─────────────┐    ┌──────────────┐    ┌─────────────┐
│ task_pulse.py│───>│ JSON on disk │    │ User's chat │
│  (CLI tool)  │    │ (persistence)│    │ (Telegram/  │
└──────┬───────┘    └──────────────┘    │  Discord/..)│
       │                                └──────▲──────┘
       │         ┌──────────────┐              │
       └────────>│ message tool │──────────────┘
                 │ (real-time)  │
                 └──────────────┘

Dual-layer = no other skill does both.

Quick Reference

Create task → push start notification

TASK_ID=$(python3 scripts/task_pulse.py create "任务名" "步骤1" "步骤2" "步骤3")

Then immediately call message tool:

message(action="send", message="🚀 开始【任务名】\
📋 步骤1 → 步骤2 → 步骤3\
🔄 当前: 步骤1")

Advance to next step → push progress

python3 scripts/task_pulse.py next "$TASK_ID" "抓取了25条数据"

Then push: message(action="send", message="✅ [1/3] 步骤1完成(抓取了25条数据)\ 🔄 → 步骤2")

Heartbeat (long step, >1min)

python3 scripts/task_pulse.py heartbeat "$TASK_ID" "已处理60%"

Push only if meaningful progress (avoid spam).

Complete

python3 scripts/task_pulse.py done "$TASK_ID" "发布成功 https://..."

Push: message(action="send", message="🎉 【任务名】完成!\ 结果: https://...")

Fail

python3 scripts/task_pulse.py error "$TASK_ID" "登录过期"

Push: message(action="send", message="❌ 【任务名】失败\ 错误: 登录过期")

Query status

python3 scripts/task_pulse.py status

Cleanup (>7 days completed)

python3 scripts/task_pulse.py cleanup

Mandatory Rules

  1. Always push after file update — file update alone is invisible to users
  2. Push format: emoji + [done/total] + current step + one-line info (≤3 lines)
  3. Push frequency: every step transition; long steps max once per 30s
  4. Stall = running + no update for 3 minutes — detected on status query
  5. On stall detection: push ⚠️ 【任务名】可能卡住了(3分钟无更新)
  6. Cleanup: run in heartbeat, keep completed tasks 7 days

Status Icons

Status Icon Meaning
running 🔄 Executing
done ✅/🎉 Completed
error Failed
stalled ⚠️ No update >3min
pending Step not started

Integration

  • Cron jobs: Wrap cron task payload with create/next/done calls
  • Sub-agents: Parent agent creates task, sub-agent updates via file, parent pushes
  • Heartbeat cleanup: Add python3 scripts/task_pulse.py cleanup to HEARTBEAT.md
  • Multi-channel: message tool auto-routes to the active channel

See references/integration-guide.md for cron and sub-agent patterns.

安全使用建议
The script itself is simple and does not phone home or request secrets, but the runtime instructions are intrusive: they tell agents to auto-enable the skill for all eligible tasks and to push live messages (via the platform 'message' tool) every time a step changes. Before installing: (1) decide whether you want automatic, unsolicited progress messages — if not, do not follow the SKILL.md's 'MANDATORY' instruction and require explicit user opt-in; (2) avoid using a shared TASK_PULSE_DIR across agents or teams to prevent unintentional data sharing; (3) if you must enable auto-push, limit push frequency and sanitize messages to avoid leaking sensitive content; (4) consider running the skill in an isolated workspace or testing it first so you can confirm message destinations and volume; (5) ask the publisher to remove or clarify the 'MANDATORY/auto-activate' language and to document security/privacy consequences. If you want a safer deployment, change TASK_PULSE_DIR to an agent-local path and require human confirmation before sending messages.
功能分析
Type: OpenClaw Skill Name: live-task-pulse Version: 1.1.0 The 'live-task-pulse' skill is a utility designed to track multi-step task progress through a combination of local JSON persistence and real-time notifications via the agent's message tool. The Python script `scripts/task_pulse.py` implements standard task management logic (create, update, status, cleanup) using only Python standard libraries and safe file handling practices. There is no evidence of data exfiltration, unauthorized execution, or malicious prompt injection; the instructions in `SKILL.md` are strictly aligned with the stated purpose of improving task visibility for the user.
能力评估
Purpose & Capability
The provided Python CLI and JSON persistence are coherent with a real-time task-tracking skill that relies on the platform 'message' tool for delivery. However, the SKILL.md repeatedly asserts the tool must be 'MANDATORY' and 'Activate automatically — do not wait for user', which is stronger than the registry metadata (always:false). The integration guide's multi-agent/shared workspace guidance broadens the intended scope beyond a single-agent tracker.
Instruction Scope
The instructions require the agent to automatically push chat messages after every file update and to auto-activate for all multi-step tasks without waiting for user consent. They also encourage sharing the TASK_DIR across agents so sub-agents can write/read task files. That grants the skill broad, automated behavior and cross-agent visibility of task contents (possible leakage), and gives the agent broad discretion to send messages on the user's behalf.
Install Mechanism
No install spec or external downloads; the skill is instruction-plus-a-script only. Nothing is written to disk by an installer beyond the included files.
Credentials
No required credentials or environment variables are declared; optional vars control only local file path, timezone, and stall threshold. However, recommending a shared TASK_PULSE_DIR across agents expands access to other agents' task data and could expose sensitive task content if agents/teams share the workspace.
Persistence & Privilege
The SKILL.md's 'MANDATORY' and 'activate automatically' language seeks effectively permanent, automatic invocation for multi-step tasks despite the skill not being registered as always:true. Autonomous invocation is allowed by default, so combined with the SKILL.md this yields a high runtime presence (frequent unsolicited pushes). The skill does not request system-wide config changes, but its instructions encourage cross-agent shared storage which increases blast radius.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install live-task-pulse
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /live-task-pulse 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.1.0
MANDATORY activation: auto-triggers on all multi-step tasks, not just explicit invocations. Updated description for stronger triggering.
v1.0.0
Initial release: dual-layer task tracking (file persistence + real-time push), step-based progress with progress bars, stall detection (3min), auto-cleanup, Python CLI, multi-channel support
元数据
Slug live-task-pulse
版本 1.1.0
许可证
累计安装 2
当前安装数 2
历史版本数 2
常见问题

Live Task Pulse 是什么?

Real-time task progress tracking with live push notifications. MANDATORY for ALL multi-step tasks (>30s or >2 tool calls). Activate automatically — do not wa... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 309 次。

如何安装 Live Task Pulse?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install live-task-pulse」即可一键安装,无需额外配置。

Live Task Pulse 是免费的吗?

是的,Live Task Pulse 完全免费(开源免费),可自由下载、安装和使用。

Live Task Pulse 支持哪些平台?

Live Task Pulse 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Live Task Pulse?

由 siaslfs(@siaslfs)开发并维护,当前版本 v1.1.0。

💬 留言讨论