Lark Okr logo

Lark Okr

OrganizationPopular
larksuite
lark-okr

飞书 OKR:管理目标与关键结果。查看和编辑 OKR 周期、目标、关键结果、对齐关系、量化指标和进展记录。当用户需要查看或创建 OKR、管理目标和关键结果、查看对齐关系时使用。不负责:待办任务管理(lark-task)、日程/会议安排(lark-calendar)、绩效评估

Overview

Publisherlarksuite
Repositorycli
Skill namelark-okr
Stars
17.3K
Forks
1.4K
Bundled files
25
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 25 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by larksuite on GitHub. Read the source before you install it.

Installation

Install the Lark Okr AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/larksuite/cli.git /tmp/cli
mkdir -p .claude/skills
cp -r /tmp/cli/skills/lark-okr .claude/skills/lark-okr
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lark Okr in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Lark Okr on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Lark Okr is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

okr (v2)

CRITICAL — 开始前 MUST 先用 Read 工具读取 ../lark-shared/SKILL.md,其中包含认证、权限处理

身份:OKR 操作默认使用 --as user(查看当前用户/上下级的 OKR 时)。也支持 --as bot 查看他人 OKR(需相应权限)。

快速决策

用户需求操作路径参考文档
查看自己/他人的 OKR获取用户 ID -> +cycle-list -> +cycle-detail -> 按需查指标/进展记录cycle-list, cycle-detail, indicators, progress-list
为自己写一组 OKR优先用 +batch-create 创建 Objective/KR 骨架batch-create, contentblock
只新增一条 O 或单条 KR+createcreate
编辑内容/备注/截止时间+patchpatch
修改 OKR 分数只有用户明确说“分数”“评分”“打分”“score”时才用 +patch --score;分数不是进度/完成度patch
调整顺序或权重+reorder / +weightreorder, weight
更新数字进度/完成度百分比或不带单位数字用 +indicator-update;需要改单位/目标值时查指标后用 indicators patchindicator-update, indicators
写文字进展+progress-create;如果文本和数字都有,百分比或默认单位可使用 --progress-percent 统一改,非百分比单位更新量化指标progress-create, progress-list, progress-update
对齐目标直接按对齐关系工作流处理alignments
查询/创建/修改/解决 OKR 评论获取周期下全部评论聚合用 +comment-detail,查询单个 O/KR/进展或仅查询周期全局评论用 +comment-listcomment, comment-create, comment-solve-reopen

分类只在用户明确要求分类,或创建 Objective 返回 invalid parameters 且怀疑租户强制开启分类时处理:用 lark-cli okr categories list --params '{"owner_type":"user","page_size":100}' --as user 查可用分类,选择语义合适且enabled=true 的分类 ID;分类可后续调整,不必停下等待用户确认。

获取当前用户用 contact +get-user;按姓名/邮箱查他人用 contact +search-user,拿到 open_id 后再查 OKR。

bash
lark-cli contact +search-user --query "张三" --has-chatted --as user

最常用 OKR 命令示例:

bash
# 查用户周期,再用周期 ID 查详情
lark-cli okr +cycle-list --user-id "ou_xxx" --as user
lark-cli okr +cycle-detail --cycle-id 7000000000000000001 --as user

# 批量创建 Objective/KR
lark-cli okr +batch-create \
  --cycle-id 7000000000000000001 \
  --input '[{"text":"提升产品用户体验","notes":"关注核心流程和用户反馈","krs":[{"text":"核心流程满意度达到 4.8 分"}]}]' \
  --as user

# 更新数字进度/完成度
lark-cli okr +indicator-update \
  --level key-result \
  --id 7000000000000000003 \
  --value 75 \
  --as user

分数和进度不要混用:用户说“进度”“完成度”“当前做到 75%”时,通常是在改量化指标或写进展记录,不是在改 score。只有明确要求修改 OKR 分数/评分/打分时,才使用 +patch --scorescore 取值是 0-1,最多一位小数。

进度判断规则:用户说“进度”“完成度”时,先判断是否是量化数字。数字进度通常对应量化指标;不可量化文本对应进展记录。需要修改指标单位时看 lark-okr-indicators.md

Shortcuts(推荐优先使用)

Shortcut 是对常用操作的高级封装(lark-cli okr +<verb> [flags])。有 Shortcut 的操作优先使用。

Shortcut说明
+cycle-list分页获取特定用户的 OKR 周期列表,可以用 --time-range 对当前页后置筛选
+cycle-detail获取特定 OKR 中所有目标和关键结果的内容
+create创建单个 Objective(可带备注),或向已有 Objective 新增 KR
+progress-list分页获取目标或关键结果的进展记录列表
+progress-get根据 ID 获取单条 OKR 进展记录
+progress-create为目标或关键结果创建进展记录
+progress-update更新指定 ID 的进展记录内容
+progress-delete删除指定 ID 的进展记录(不可恢复)
+upload-image上传图片用于 OKR 进展记录的富文本内容
+batch-create批量创建 Objective(可带备注)和 KR
+reorder调整 Objective 或 KR 的顺位
+weight调整 Objective 或 KR 的权重
+indicator-update更新 Objective 或 KR 的当前进度指标。更复杂的量化指标操作见 量化指标管理
+patch部分更新 Objective 或 KR(content、notes、score、deadline)
+comment-detail获取周期下 Cycle/Objective/KeyResult/Progress 的全部评论
+comment-list分页获取单个 OKR 实体下的评论
+comment-get获取单条评论详情
+comment-create创建新评论或回复已有评论(仅支持 --as user)
+comment-patch修改评论内容(仅支持 --as user)
+comment-delete永久删除单条评论(仅支持 --as user)
+comment-solve解决评论或划词评论串(仅支持 --as user)
+comment-reopen重新打开评论或划词评论串(仅支持 --as user)

创建场景选择

  • 单条创建优先用 +create:适合创建一个 Objective,或给已有 Objective 增加一个 KR。
  • 批量创建用 +batch-create:适合一次创建多个 Objective,并可同时附带多个 KR。
  • 如果你只需要修改已有 Objective / KR 的内容、备注、分数或截止时间,使用 +patch

格式说明

  • OKR 业务实体 获取 OKR 实体结构,定义和关系,帮助你更好的使用 OKR 功能
  • ContentBlock 富文本格式 — Objective/KeyResult/Progress 中 Content/Note 字段使用的富文本格式说明,以及简化的半纯文本(SemiPlainContent)格式的进一步说明。
  • 强烈建议 在操作 OKR 前,阅读OKR 业务实体以了解基础概念

API Resources

alignments

  • delete — 删除对齐关系
  • get — 获取对齐关系

操作指南: OKR 对齐关系管理 包含 list/create/delete 完整工作流

categories

  • list — 批量获取分类

cycles

  • list — 批量获取用户周期

cycle.objectives

  • list — 批量获取用户周期下的目标

indicators

  • patch — 更新量化指标

操作指南: OKR 量化指标管理 包含目标/KR 指标查询和 patch 更新完整工作流

key_results

  • delete — 删除关键结果
  • get — 获取关键结果
  • patch — 更新关键结果

key_result.indicators

  • list — 获取关键结果的量化指标

操作指南: OKR 量化指标管理

objectives

  • delete — 删除目标
  • get — 获取目标
  • key_results_position — 更新全部关键结果的位置
    • 请求中必须携带对应周期下全部关键结果的 ID,否则会参数校验失败。以传入的关键结果ID顺序重新排列关键结果。
  • key_results_weight — 更新全部关键结果的权重
    • 类似 objectives_weight, 请求中必须同时修改对应目标下全部关键结果的权重,且所有权重值的和必须等于 1 ,否则会参数校验失败。
  • patch — 更新目标

objective.alignments

  • create — 创建对齐关系
    • 对齐不允许对齐自己的目标,且发起对齐的目标和被对齐的目标所在周期时间上必须有重叠,否则会参数校验失败。
  • list — 批量获取目标下的对齐关系

objective.indicators

  • list — 获取目标的量化指标

objective.key_results

  • list — 批量获取目标下的关键结果

不在本 skill 范围

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Lark Okr AI skill do?

飞书 OKR:管理目标与关键结果。查看和编辑 OKR 周期、目标、关键结果、对齐关系、量化指标和进展记录。当用户需要查看或创建 OKR、管理目标和关键结果、查看对齐关系时使用。不负责:待办任务管理(lark-task)、日程/会议安排(lark-calendar)、绩效评估

Why use Lark Okr on TypingMind?

Because you install it once and use it with any model. Lark Okr is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Lark Okr in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/larksuite/cli/tree/main/skills/lark-okr. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Lark Okr?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Lark Okr?

As many as you like. As long as a model supports skills, you can use Lark Okr with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Lark Okr AI skill free?

Yes. It is published on GitHub by larksuite under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇