CtrlK
BlogDocsLog inGet started
Tessl Logo

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、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。

61

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/lark-im/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-5

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

The body is well-structured with excellent progressive disclosure and mostly actionable guidance, but it carries redundant table content and lacks explicit validation/retry loops for batch and destructive IM operations.

Suggestions

Add explicit validate->fix->retry feedback loops for destructive/batch operations (messages.delete, messages.patch, reactions create/delete, folder expansion) to lift workflow_clarity above the batch/destructive cap of 3.

Trim redundancy between the Shortcuts table, API Resources section, and 权限表 by keeping SKILL.md to discovery-level summaries and deferring scope/flag detail to the reference files.

Include one or two complete copy-paste command examples (e.g. a send-message and a list-messages invocation with real flags) to move actionability from tabular flags toward fully executable guidance.

DimensionReasoningScore

Conciseness

Mostly efficient but the large Shortcuts table, API Resources section, and 权限表 partly duplicate details that also live in the references, and dense explanatory blocks (Identity/Token Mapping, Sender Name Resolution) could be trimmed; fits the 'mostly efficient but could be tightened' anchor rather than the lean 4.

3 / 5

Actionability

Gives concrete commands and flags ("lark-cli im +<verb> [flags]", "lark-cli schema im.<resource>.<method>", specific scopes, batch limits) with minor gaps; not a 5 because most guidance is tabular flags rather than complete copy-paste examples covering common cases.

4 / 5

Workflow Clarity

Sequencing exists (schema-before-call checkpoint, card-create MUST-read gate), but destructive/batch operations (messages.delete, patch, reactions, folder expansion) lack explicit validate->fix->retry feedback loops, so the batch/destructive cap of 3 applies.

3 / 5

Progressive Disclosure

Clear overview with well-signaled one-level-deep references; all 28 referenced bundle files exist, bulk detail is pushed to references/, and the only deeper nesting (card/components) sits behind the card-create entry point for justified reasons.

5 / 5

Total

15

/

20

Passed

Description

87%Weight 40%Scale 1-5

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

The description is specific, trigger-rich, and clearly answers both what the skill does and when to use it, with a distinct Lark-IM niche. It would improve with added synonyms and file-extension-style triggers.

DimensionReasoningScore

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...发送交互卡片、监听卡片按钮回调"), slightly below 5 because the enumeration is broad rather than tightly comprehensive on a few sub-features.

4 / 5

Completeness

Explicitly answers both 'what' (detailed action list) and 'when' (a concrete '当用户需要...时使用' clause enumerating specific triggers), matching the top anchor.

5 / 5

Trigger Term Quality

Strong natural user phrasing ("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...时使用"), but coverage is Chinese-only with few synonyms or file-extension variants, so not the top anchor.

4 / 5

Distinctiveness Conflict Risk

Clearly scoped to 飞书即时通讯 with concrete Lark-IM-specific triggers (群聊, 卡片回调, Feed 置顶), giving it a distinct niche with minimal overlap risk.

5 / 5

Total

18

/

20

Passed

Validation

68%

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

Validation11 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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: 2 deeper-than-1-level, 1 suspicious

Warning

referenced_paths_exist

Referenced path issues: 3 deeper-than-1-level

Warning

Total

11

/

16

Passed

Repository
larksuite/cli
Reviewed

Table of Contents

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.