npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

live-ops-todo-dispatch

v2.0.2

Published

直播运营每日代办分发 CLI v2:读取钉钉群聊/私聊,AI 语义筛选每日代办,结合固定模板自动创建钉钉待办、发送汇总消息,并生成云端定时(早批次+轮询)任务

Readme

live-ops-todo-dispatch (lotd) v2

直播运营每日代办分发 CLI —— 读取钉钉群聊/私聊,AI 语义筛选每日代办,结合固定模板自动创建钉钉待办、私信汇总,并生成云端定时任务(早批次 + 每 30 分钟轮询)

v1 只能按写死的固定清单发代办;v2 以聊天内容为准,固定清单降级为辅助模板,并新增通用代办模板,举一反三识别聊天里的任意任务。

能力总览

| 能力 | 说明 | |---|---| | 聊天采集 | dws 按时间窗拉监控群/私聊消息,支持图片下载(品牌时刻图) | | AI 语义筛选 | T1 每日清单 / T2 分工指派 / T3 通用任务 / T4 分工表(更新负责人)/ T5 停播改期取消(拦截);N1-N4 噪音自动忽略;拿不准的进异常清单只发操作者 | | 固定模板 | 保留 v1:sameDay / advance1 / advance2,自然日倒推、24:00 归属直播当天、一事一待办 | | 通用模板 | 挂链接、抽奖时段、信息收集等任意聊天任务,自动解析负责人与时间 | | 混合节奏 | 早批次(如 9:00/10:00,可配)+ 8:00–23:30 每 30 分钟轮询;夜间消息并入早批次 | | 全自动 | 建待办 → 回读验证 → 按人私信汇总 → 操作者收运行报告;异常不打扰执行人 | | 幂等可回滚 | 消息/待办双账本去重;lotd rollback --run <id> 按批次删除误建待办 | | 周期提醒 | 每周数据拉取/复盘等用钉钉循环待办,时间因人而异 |

安装

npm i -g live-ops-todo-dispatch
lotd verify          # dws 必需;qwenwork 仅云端定时需要
dws auth login       # 未登录时先登录钉钉

快速开始

# 1. 交互式首配(账号预设、监控群勾选、执行人 userId 反查、别名、周期提醒)
lotd setup
#    非交互环境可用 lotd init 生成模板手动编辑

lotd check           # 校验配置

# 2. 日常由云端定时自动跑;手动全流程演示:
lotd collect --mode batch --download
lotd extract --mode batch
#   → AI 阅读 lotd-bundle/batch-all.md,按 skill 分类规则产出 decisions JSON
lotd plan --decisions lotd-bundle/decisions.json     # 预览(不创建)
lotd dispatch --decisions lotd-bundle/decisions.json # 正式分发

# 3. 云端定时(每账号早批次 + 每30分钟轮询)
lotd scheduler --out tasks.json     # 生成任务定义
lotd scheduler --apply              # 安装 qwenwork 后直接创建

# 4. 把 AI skill 安装到 Agent 技能目录
lotd skill-install --target qoderwork   # 钉钉千问工作台;也支持 qoder/claude/cursor/codex/agents/. 等

命令一览

| 命令 | 作用 | |---|---| | setup [路径] | 交互式首配 | | init [目录] | 生成 v2 配置模板 | | check / verify | 校验配置 / 检查 dws、qwenwork | | collect --mode batch\|poll | 拉取监控会话增量消息(batch 回看 24h,poll 看上次之后) | | extract --mode ... | 采集并生成 AI 上下文包(.json + .md,含分类样本与决策 schema) | | plan | 合并预览固定模板 + 聊天决策(dry-run) | | dispatch | 正式执行:建待办、私信、报告、记账本 | | rollback --run <id> | 回滚某次运行 | | calendar --month YYYY-MM | 固定模板整月日历 | | reminders | 幂等创建周期循环待办 | | scheduler [--out|--apply] | 生成/创建云端定时任务 | | skill-install --target | 安装随包 skill 到 Agent 目录 |

配置结构(accounts.json)

  • operator:当前使用者(收运行报告/异常清单;复盘类任务跟随此人,换人重跑 setup)
  • accounts[]:账号、排期(weekly:2,3,4 / dates:...)、推送时间、固定模板开关、执行人、事项、品牌时刻、监控 sources
  • globalSources[]:跨账号监控会话
  • aliases[]:昵称别名(小明=张三…),决策中的负责人先过别名表
  • reminders[]:周期提醒(weekday 1-7、time、receivers,operator 表示操作者本人)
  • config.polling:轮询时段与频率(默认 8:00–23:30 / 30 分钟)

AI 决策(decisions JSON)

AI 读取上下文包后输出五类数组:todos(建待办)、ownershipUpdates(T4 长期分工)、suppressions(T5 拦截)、ignored(N1-N4 噪音)、anomalies(只发操作者)。完整字段见包内 templates/decisions.schema.json,分类样本见 templates/samples.md(随 skill 发布为 references/classification.md)。

灰度建议

  1. collect + extract + plan 只分析不创建,连续几天核对分类准确率;
  2. 单账号灰度 3–7 天,用 rollback 兜底;
  3. 稳定后扩到全部账号并启用 scheduler --apply

二期规划

飞书(lark CLI)、大象 app(电脑操控 GUI)消息源接入。

开发

node test/run.js      # 离线测试(规则/迁移/合并/拦截/去重)
npm pack              # 本地打包验证
npm publish           # 发布(需 npm login)

License

MIT