Menu

Not in the top 1,000 by GitHub stars

autumnseasonism/lark-todo

AI Agent Skill - 扫描飞书全平台待办事项，智能排序，直接处理或创建任务

Engineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 1b225a138866

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 1b225a13886686a9ff160c7c4324b980e7076669

137GitHub stars
0stars in 7 days
1skill in this repository
0commits in 30 days

Heat

0.3
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Oct 25, 2026137

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

lark-todo

When your agent uses it

飞书全平台待办扫描：IM 消息、会议纪要、日程、文档评论、待办审批、我发起的审批、邮件、已有任务八源并行采集，按优先级排序后支持直接处理或建任务。多企业账号自动发现并并行扫描，跨企业合并。用户说'有啥待办'、'@我的消息'、'扫一圈'、'收工检查'、'今天还差啥'、'morning standup'、'daily review' 时触发，连随口'忙不忙'、'有人找我吗'也应触发。同时覆盖多企业 profile 管理（添加/查看/删除）。依赖 lark-cli。

What it loads into context

Frontmatter

170 tokens

Always available to the agent

SKILL.md

10,313 tokens

When the skill is activated

Reference documents

13,087 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Step 0: 依赖自检与自动装配（必须在 Step A 之前）
  2. 启动检查
  3. 执行模式选择（Hybrid）
  4. 管理企业账号（Profile）
  5. 认证与权限
  6. 核心思路
  7. 前置条件
  8. 扫描模式
  9. 准备：获取当前用户信息
  10. 8 个数据源并行扫描
  11. 优先级判断
  12. 日程关联
  13. 去重与合并
  14. 输出格式
  15. Profile 路由
  16. 行动决策
  17. 可直接处理的事项类型
  18. 不能直接处理 → 创建任务
  19. 异常处理
  20. 权限总表
  21. 参考

Scripts executed separately

  • evals/run_full_tests.sh
  • evals/run_tests.sh
  • evals/test_scan.py
  • scripts/bootstrap.sh
  • scripts/lark_cli_json.py
  • scripts/scan.py

Files

  • .gitignoreasset112 bytes
  • LICENSEasset1,066 bytes
  • README.mddoc15,138 bytes
  • README_EN.mddoc13,236 bytes
  • SKILL.mdcore37,174 bytes
  • SKILL.mdcore37,174 bytes
  • SKILL.mdcore37,174 bytes
  • SKILL.mdcore37,174 bytes
  • SKILL.mdcore37,174 bytes
  • SKILL.mdcore37,174 bytes
  • SKILL.mdcore37,174 bytes
  • SKILL.mdcore37,174 bytes
  • SKILL.mdcore37,174 bytes
  • SKILL.mdcore37,174 bytes
  • SKILL.mdcore37,174 bytes
  • SKILL.mdcore37,174 bytes
  • SKILL.mdcore37,174 bytes
  • SKILL.mdcore37,174 bytes
  • evals/evals.jsonasset9,223 bytes
  • evals/run_full_tests.shruns12,140 bytes
  • evals/run_tests.shruns3,735 bytes
  • evals/skill-prompts.jsonasset2,451 bytes
  • evals/test_scan.pyruns10,149 bytes
  • references/action-dispatch.mddoc5,749 bytes
  • references/data-sources.mddoc12,341 bytes
  • scripts/bootstrap.shruns2,520 bytes
  • scripts/lark_cli_json.pyruns4,034 bytes
  • scripts/scan.pyruns9,949 bytes
Read SKILL.md

# 待办行动扫描器

## Step 0: 依赖自检与自动装配（必须在 Step A 之前）

**目的**：确保 `lark-cli` 在 PATH 中可用。本 skill 除 Python 标准库（可选加速器）外，唯一外部依赖就是 `lark-cli`（官方 `@larksuite/cli` npm 包）——已装则跳过，缺失则自动补齐，装不上则给出清晰指引。

**首选路径**（`<SKILL_DIR>` 即本 SKILL.md 所在目录）：

```bash
bash "<SKILL_DIR>/scripts/bootstrap.sh"
```

脚本按"幂等探测 → 需要才安装 → 失败分类提示"的顺序工作，**退出码就是分支**：
View the complete source on GitHub

Skills included

  • lark-todo

Repository facts

License
MIT
Created
Apr 15, 2026
Last pushed
Apr 21, 2026
Forks
16
Open issues
0
Project activity
Slowing

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 6, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 13 notes
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 52 signals by file

README.md

  • Network accessline 6
    </p>   <p align="center">     <img src="https://img.shields.io/badge/version-4.2.0-blue" alt="version">
  • Network accessline 7
    <p align="center">     <img src="https://img.shields.io/badge/version-4.2.0-blue" alt="version">     <img src="https://img.shields.io/badge/license-MIT-green" alt="license">
  • Network accessline 8
    <img src="https://img.shields.io/badge/version-4.2.0-blue" alt="version">
  • Network accessline 9
    <img src="https://img.shields.io/badge/license-MIT-green" alt="license">
  • Network accessline 10
    <img src="https://img.shields.io/badge/lark--cli-%3E%3D1.0.9-orange" alt="lark-cli">
  • Network accessline 11
    <img src="https://img.shields.io/badge/mode-hybrid%20%7C%20SKILL.md%20%2B%20optional%20Python-blueviolet" alt="hybrid mode">
  • Network accessline 12
    <img src="https://img.shields.io/badge/python-stdlib%20only-informational" alt="python stdlib only">
  • Network accessline 13
    <img src="https://img.shields.io/badge/multi--org-✓-brightgreen" alt="multi-org">
  • Network accessline 180
    - 支持 SKILL.md 规范的 Agent 应用（[Claude Code](https://claude.com/claude-code) / [Trae](https://www.trae.cn/) / [Cline](https://cline.bot/) 等）
  • Network accessline 191
    请帮我安装这个 skill： https://github.com/autumnseasonism/lark-todo-skill.git
  • Network accessline 192
    https://github.com/autumnseasonism/lark-todo-skill.git
  • Network accessline 200
    # 放在当前项目目录，或放到 Agent 的 skills 扫描路径下 git clone https://github.com/autumnseasonism/lark-todo-skill.git
  • Network accessline 201
    git clone https://github.com/autumnseasonism/lark-todo-skill.git
  • Network accessline 329
    本项目依赖 [lark-cli](https://github.com/larksuite/cli)（MIT License）作为底层 CLI 工具。lark-todo 不包含 lark-cli 的任何代码，仅通过命令行调用其功能。

README_EN.md

  • Network accessline 6
    </p>   <p align="center">     <img src="https://img.shields.io/badge/version-4.2.0-blue" alt="version">
  • Network accessline 7
    <p align="center">     <img src="https://img.shields.io/badge/version-4.2.0-blue" alt="version">     <img src="https://img.shields.io/badge/license-MIT-green" alt="license">
  • Network accessline 8
    <img src="https://img.shields.io/badge/version-4.2.0-blue" alt="version">
  • Network accessline 9
    <img src="https://img.shields.io/badge/license-MIT-green" alt="license">
  • Network accessline 10
    <img src="https://img.shields.io/badge/lark--cli-%3E%3D1.0.9-orange" alt="lark-cli">
  • Network accessline 11
    <img src="https://img.shields.io/badge/zero%20code-pure%20SKILL.md-blueviolet" alt="zero code">
  • Network accessline 12
    <img src="https://img.shields.io/badge/multi--org-✓-brightgreen" alt="multi-org">
  • Network accessline 177
    - An AI agent supporting the SKILL.md spec ([Claude Code](https://claude.com/claude-code) / [Trae](https://www.trae.cn/) / [Cline](https://cline.bot/))
  • Network accessline 188
    Please install this skill: https://github.com/autumnseasonism/lark-todo-skill.git
  • Network accessline 189
    https://github.com/autumnseasonism/lark-todo-skill.git
  • Network accessline 197
    # Put it in the current project directory, or in your agent's skill scan path git clone https://github.com/autumnseasonism/lark-todo-skill.git
  • Network accessline 198
    git clone https://github.com/autumnseasonism/lark-todo-skill.git
  • Network accessline 285
    This project depends on [lark-cli](https://github.com/larksuite/cli) (MIT License) as the underlying CLI tool. lark-todo contains no lark-cli source code — it only invokes lark-cli through shell commands.

evals/run_full_tests.sh

  • Executable scriptline 1
    #!/bin/bash
  • Dangerous shell operationline 19
    output=$(eval "$cmd" 2>&1)
  • Dangerous shell operationline 37
    output=$(eval "$cmd" 2>&1)
  • Dangerous shell operationline 54
    output=$(eval "$cmd" 2>&1)

evals/run_tests.sh

  • Executable scriptline 1
    #!/bin/bash
  • Dangerous shell operationline 18
    output=$(eval "$cmd" 2>&1)

evals/test_scan.py

  • Executable scriptline 1
    Executable file
  • Access to secretsline 179
    [Credential-related source omitted]
  • Access to secretsline 216
    [Credential-related source omitted]
  • Access to secretsline 237
    [Credential-related source omitted]
  • Access to secretsline 251
    [Credential-related source omitted]
  • Access to secretsline 269
    [Credential-related source omitted]
  • Access to secretsline 283
    [Credential-related source omitted]

scripts/bootstrap.sh

  • Executable scriptline 1
    #!/usr/bin/env bash
  • Network accessline 29
    if [ "${#missing[@]}" -gt 0 ]; then   log "未检测到：${missing[*]}。lark-cli 依赖 npm 全局安装。"   log "请先安装 Node.js（建议 >= 18）：https://nodejs.org/"
  • Network accessline 30
    log "未检测到：${missing[*]}。lark-cli 依赖 npm 全局安装。"   log "请先安装 Node.js（建议 >= 18）：https://nodejs.org/"   log "安装完成并重开 shell 后，可再次执行本脚本或手动："
  • Network accessline 31
    log "请先安装 Node.js（建议 >= 18）：https://nodejs.org/"
  • Dangerous shell operationline 54
    log "  · 权限问题（macOS/Linux）：尝试 'sudo npm install -g @larksuite/cli'"
  • Network accessline 54
    log "  · 权限问题（macOS/Linux）：尝试 'sudo npm install -g @larksuite/cli'" log "      或配置 npm 用户级 prefix（npm config set prefix ~/.npm-global）后重试" log "  · 网络问题：换镜像 'npm install -g @larksuite/cli --registry=https://registry.npmmirror.com'"
  • Network accessline 55
    log "      或配置 npm 用户级 prefix（npm config set prefix ~/.npm-global）后重试" log "  · 网络问题：换镜像 'npm install -g @larksuite/cli --registry=https://registry.npmmirror.com'" log "  · 企业代理：先设 HTTP(S)_PROXY 再重试"
  • Network accessline 56
    log "  · 网络问题：换镜像 'npm install -g @larksuite/cli --registry=https://registry.npmmirror.com'"

scripts/lark_cli_json.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Access to secretsline 66
    [Credential-related source omitted]
  • Access to secretsline 69
    [Credential-related source omitted]

scripts/scan.py

  • Executable scriptline 1
    #!/usr/bin/env python3

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Declared and executed: 2 facts
  • Contacts nodejs.org, which SKILL.md, the README and the plugin manifest do not mentionscripts/bootstrap.sh:31High confidence
  • Contacts registry.npmmirror.com, which SKILL.md, the README and the plugin manifest do not mentionscripts/bootstrap.sh:56High confidence
Signal confidence: 52 facts

and 2 more

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

mattpocock/skills

Skills for Real Engineers. Straight from my .agents directory.

317kGitHub stars

obra/superpowers

An agentic skills framework & software development methodology that works.

313.8kGitHub stars

NousResearch/hermes-agent

The agent that grows with you

261.3kGitHub stars

multica-ai/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions,…

230.4kGitHub stars

anthropics/skills

Public repository for Agent Skills

188.3kGitHub stars

DietrichGebert/ponytail

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

186kGitHub stars