Communication / AGENT SKILL

lark-contact

open.feishu.cn

719.7K installs

Find Lark contacts and resolve names, emails, IDs, profile details, and visible bots or agents.
飞书 / Lark 通讯录:按姓名 / 邮箱解析成 open_id,或按 open_id 反查姓名 / 部门 / 邮箱 / 联系方式 / 个人状态 / 签名,以及按关键词搜索当前用户可见的机器人 / 智能体(agent)。当用户提到一个名字要下一步发消息 / 排日程,或拿到 open_id 想查具体信息时使用。不负责部门树遍历、按部门列员工、组织架构图,这类需求走原生 OpenAPI。

One new superpower.

Run this command in your project to choose an agent and install the skill.

npx skillycli add https://open.feishu.cn/ --skill lark-contactView original source

BEFORE YOU INSTALL

Understand the trade-offs.

SECURITY REVIEW

Review incomplete

The available checks do not support a complete conclusion. Review the scope before relying on this result.

No reported risk0 reported findingsIncomplete evidence

Scope & how to read this review

Static inspection of the supplied skill source. “Complete” means the selected source and checks completed; it does not cover every downloaded package, external service, or runtime action.

Source coverage: partial
Reviewed: 2026-10-07
Reviewed version: sha256:e4639
Latest catalog version: sha256:e4639

The reported findings score starts at 100 and subtracts 35 for each critical finding, 20 for high, 9 for medium, and 3 for low, with a floor of 0. It is shown only for complete, current reviews with all finding details. A score of 100 means no findings were reported in the reviewed source.

Severity describes potential impact, not the probability of harm. Review the conditions and evidence for each finding. A scan is not a safety guarantee.

SKILL QUALITY

Limited evidence for a verdict

45/100Provisional source score

The supplied instructions provide useful routing for Lark contact and bot lookups, including identity restrictions and ambiguous matches. Reliable end-to-end use remains insufficiently documented because command references, authentication prerequisites, response examples, and verification checks are unavailable.

low confidenceStatic reviewIntegration skill

The reviewer had limited evidence. These scores describe what was available, not a verified measure of reliability.

What works well

Clearly distinguishes user and bot identities and defines supported lookup tasks.
Provides concrete CLI examples for employee search, bot search, and profile queries.
Addresses ambiguous matches, permission failures, cross-tenant empty fields, and ID types.

Before you rely on it

Supply the linked command references and shared identity/authentication guidance.
Document setup, identity selection, zero-result handling, and actionable permission-error recovery.
Add representative responses and explicit checks for successful and unsuccessful lookups.

Clear instructionsCan your agent understand the task and expected outcome?3/4

Task boundaries and identity-based command selection are clear, but determining the current identity and interpreting lookup results require additional guidance.

EVIDENCE

SKILL.md: "**user 身份和 bot 身份是两条完全独立的路径**。先确定当前身份,再按下表选命令:"

To improve: Explain how to determine the active identity and identify the response fields needed to resolve a contact.

Complete workflowAre prerequisites, failure cases, and recovery covered?2/4

Examples and several edge cases are covered, but installation, authentication, required permissions, zero-result handling, and concrete recovery steps are missing or delegated to unavailable files.

EVIDENCE

SKILL.md: "- **41050 / Permission denied** 受当前身份的可见范围限制(三条命令都可能遇到)。细节见 [`lark-shared`](../lark-shared/SKILL.md)。"

To improve: Provide prerequisites and an ordered lookup workflow with explicit recovery for permission errors and empty results.

Repeatable resultsAre examples and dependencies specific enough to repeat the work?2/4

Concrete commands and a schema-discovery step support repeatability, but the CLI compatibility requirements, input fixtures, and expected response structure are unspecified.

EVIDENCE

SKILL.md: "lark-cli contact +search-user --query \"张三\" --has-chatted --as user"

To improve: State the supported CLI requirements and include representative inputs and responses that explain how to extract and validate open_id.

Checkable outcomesCan you tell whether the task succeeded?1/4

The document offers observable behavioral rules, but no response fixtures, tests, or explicit success checks establish whether lookup results satisfy the intended task.

EVIDENCE

SKILL.md: "搜索命中多条且后续操作有副作用(发消息、邀请会议等),把候选列给用户挑;不要擅自选第一条。"

To improve: Add acceptance examples for unique, multiple, and zero matches, checking identity fields and required user selection.

Supporting filesDo the supplied scripts and references support the workflow?1/4

Supporting references are explicitly required for command details and troubleshooting, but none were supplied. Their coherence and completeness remain unknown.

EVIDENCE

SKILL.md: "参数细节等见 [`lark-contact-search-bot.md`](references/lark-contact-search-bot.md)。"

To improve: Supply all three linked command references and the relevant shared guidance so their parameters and workflows can be checked against SKILL.md.

Review scope & scoring

Scores describe source evidence: 0 absent or contradicted, 1 weak, 2 incomplete, 3 solid, 4 strong. Supporting files are excluded when not applicable. Instruction skills can demonstrate quality through examples and checkable outcomes without executable tests.

Provisional source score: 45/100
Files reviewed: 1
Source coverage: skill only
Reviewed: 2026-10-04
Rubric: 2026-09-25-v3
Assessed version: sha256:e4639
Latest catalog version: sha256:e4639

Review limitations

Only SKILL.md was supplied; linked references and related skills could not be assessed.
This was a static review. No commands were executed and runtime behavior was not verified.

This review does not execute the skill or verify runtime results. Install counts and publisher reputation do not increase the score.

The full skill.

Original instructions from the publisher’s SKILL.md

## 选哪个命令

**user 身份和 bot 身份是两条完全独立的路径**。先确定当前身份,再按下表选命令:

| 想做什么 | user 身份 | bot 身份 |
|---|---|---|
| 按姓名 / 邮箱搜员工拿 open_id | [`+search-user`](references/lark-contact-search-user.md) | 不支持 |
| 按关键词搜索当前用户可见的机器人 / 智能体 | [`+search-bot`](references/lark-contact-search-bot.md) | 不支持 |
| 已知 open_id 取他人资料 | `+search-user --user-ids <id>` | [`+get-user --user-id <id>`](references/lark-contact-get-user.md) |
| 查看自己 | `+get-user` 或 `+search-user --user-ids me` | 不支持 |
| 查同事的个人状态 / 签名 | `user_profiles batch_query` | 不支持 |

已知 open_id 只是想发消息 / 排日程,不必经过 contact —— 直接 [`lark-im`](../lark-im/SKILL.md) / [`lark-calendar`](../lark-calendar/SKILL.md)。

### 名字没说清是人还是机器人 / 智能体

用户给的名字常常不表明类型。例如「和 reviewDuck 约个会」里的 reviewDuck 可能是同事昵称,也可能是机器人。
- 名字含 bot / agent / AI / 助手 / 机器人 / 智能体 / assistant 等明显特征时,反过来先搜机器人更快
- 不确定的话两边都搜一下

## 典型场景

找张三给他发消息:先搜,确认 open_id,再发:

```bash
lark-cli contact +search-user --query "张三" --has-chatted --as user
lark-cli im +messages-send --user-id ou_xxx --text "Hi!"
```

批量查同事的个人状态 / 个性签名(先用 schema 看参数)。

```bash
lark-cli schema contact.user_profiles.batch_query
lark-cli contact user_profiles batch_query \
  --params '{"user_id_type":"open_id"}' \
  --data '{"user_ids":["ou_xxx","ou_yyy"],"query_option":{"include_personal_status":true,"include_description":true}}' \
  --as user
```

搜索命中多条且后续操作有副作用(发消息、邀请会议等),把候选列给用户挑;不要擅自选第一条。

## 搜索机器人 / 智能体

`+search-bot` 使用 user 身份按关键词搜索当前用户可见的机器人,返回 `ou_` 开头的机器人 open_id。参数细节等见 [`lark-contact-search-bot.md`](references/lark-contact-search-bot.md)。

```bash
lark-cli contact +search-bot --query '会议助手' --as user
lark-cli contact +search-bot --queries '会议助手,日报助手,审批助手' --as user
```

## 注意事项

- **41050 / Permission denied** 受当前身份的可见范围限制(三条命令都可能遇到)。细节见 [`lark-shared`](../lark-shared/SKILL.md)。
- **跨租户用户**(`is_cross_tenant=true`)多数业务字段为空字符串,这是飞书可见性规则,下游做空值兜底。
- **ID 类型**:`+get-user` 可通过 `--user-id-type` 使用 `open_id`、`union_id` 或 `user_id`;`+search-user` 使用用户 open_id;`+search-bot` 不支持按 ID 查询,它按关键词搜索并返回机器人 open_id。

## 不在本 skill 范围

- 发消息 / 查聊天记录 → [`lark-im`](../lark-im/SKILL.md)
- 排日程 / 邀请会议 → [`lark-calendar`](../lark-calendar/SKILL.md)
- 部门树 / 按部门列员工 / 组织架构 → [`lark-openapi-explorer`](../lark-openapi-explorer/SKILL.md) 查找原生接口