lark-im

飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件（支持大文件分片下载）、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured CLI skill hub: highly actionable command surface and excellent progressive disclosure into per-command reference files. Its main weaknesses are sheer verbosity with some inline detail duplicating reference files, and the absence of inline validation feedback loops for destructive/batch operations.

Suggestions

Move the inline --download-resources and Sender Name Resolution detail fully into their reference files, leaving only a one-line pointer in the body to tighten conciseness.

Add an inline sequenced workflow with an explicit validation checkpoint (e.g. schema → call → inspect ok:false ledger → retry failures) for batch/destructive operations like chat.members.delete and feed-group batch ops.

Consider splitting the large inline API Resources + permission table into a reference doc, keeping only the shortcut table and identity notes in the overview.

Dimension	Reasoning	Score
Conciseness	The body is dense, factual, and free of basic-concept padding, but at ~240 lines it is voluminous and several inline blocks (e.g. the --download-resources paragraph and Sender Name Resolution) summarize material that also lives in dedicated reference files, so it could be tightened.	2 / 3
Actionability	Gives concrete executable command patterns ("lark-cli im +<verb> [flags]", "lark-cli schema im.<resource>.<method>"), a per-operation shortcut table with identity and key flags, and an explicit schema-before-call instruction with an exact scope table.	3 / 3
Workflow Clarity	Clear guardrails exist (read lark-shared first, run schema before calling, MUST-read card workflow) but there are no inline sequenced validate→fix→retry loops for the batch/destructive operations (member removal, message revoke, batch feed ops), which per the feedback-loops note caps this at 2.	2 / 3
Progressive Disclosure	The body is an overview/index pointing to ~26 verified one-level-deep reference files via clearly signaled markdown links and "[Must-read]" tags, with an organized card/ sub-bundle — textbook progressive disclosure.	3 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description: it enumerates concrete IM capabilities and pairs them with an explicit natural-language trigger clause, in third person. Every dimension hits the top anchor with no fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — "发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件（支持大文件分片下载）…发送和处理交互卡片…监听卡片按钮回调" — each a specific capability rather than vague language.	3 / 3
Completeness	Clearly answers both what (the action list) and when (the explicit "当用户需要…时使用" trigger clause), matching the score-3 anchor exactly.	3 / 3
Trigger Term Quality	The explicit trigger clause covers natural user requests users would actually say: "当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊…".	3 / 3
Distinctiveness Conflict Risk	Scoped tightly to Feishu IM (飞书即时通讯) with messaging/group/chat-specific triggers unlikely to fire for other skills; uses third-person voice with no first/second-person phrasing.	3 / 3
	Total	12 / 12 Passed

Validation

68%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 deeper-than-1-level, 1 suspicious	Warning
referenced_paths_exist	Referenced path issues: 2 deeper-than-1-level	Warning

	Total	11 / 16 Passed

Repository: larksuite/cli
Path: skills/lark-im/SKILL.md
Commit: a7865cd

Reviewed: about 23 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.