CtrlK
BlogDocsLog inGet started
Tessl Logo

dingtalk-chat

钉钉群聊与消息。Use when 收发/搜索消息、建群、群治理、Bot/Webhook、文件,或仅限 IM 的消息谓词筛选。跨源主题/行为轨迹走 dingtalk-aisearch;DING/班级群走 dingtalk-misc;邮件走 dingtalk-mail。

71

Quality

90%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

A dense, high-signal routing skill: executable commands for every user endpoint, explicit write lifecycles with validation and feedback loops, and clean one-level-deep progressive disclosure into a well-organized reference bundle. The single notable flaw is that the Schema/Help/drift policy is stated three times almost verbatim, spending tokens that could be reclaimed.

Suggestions

State the Schema/Help/unknown-command policy once (e.g., in the runtime contract) and have the Shortcut 发现 and 错误最短路径 sections reference it instead of repeating it, reclaiming ~10% of the body.

DimensionReasoningScore

Conciseness

The body is exceptionally lean and telegraphic with zero explanation of concepts Claude already knows, but the Schema/Help/unknown-command policy ("Schema 不可用才读已知 leaf Help…unknown command 禁 Help…禁全 Catalog") is repeated near-verbatim across the runtime contract, Shortcut 发现, and 错误最短路径 sections. Not 5 because those duplicated tokens could be trimmed; not 3 since there is no over-explanation, only redundant repetition of one rule set.

4 / 5

Actionability

The Golden Route table supplies copy-paste-ready commands with exact flags and placeholders (e.g., `dws chat +dm --to <姓名> --content <内容>`, `dws chat message list-all --start <开始> --end <结束> --page-all --no-reactions`) plus an exact schema-query command, covering ~20 user endpoints.

5 / 5

Workflow Clarity

The 写生命周期 section gives an explicit sequence (校验目标/限制/内容/确认 → 串行执行 → 验证/读回), destructive and batch operations require confirmation plus post-write verification with ledger/completeness retention, and the numbered 错误最短路径 provides a concrete one-shot retry feedback loop (仅 retryable=true 重试一次, unknown flag 修正一次). No validation cap applies since verification is explicit throughout.

5 / 5

Progressive Disclosure

SKILL.md is a routing overview with a 按需加载 table mapping scenarios to one-level-deep references; every referenced path (references/chat/*.md, references/card/schema.md, references/contracts.md, etc.) exists in the bundle, and remaining files (card/create|update|a2ui, intent-guide) are reachable via a single lateral hop from a referenced file rather than nested. The bulk of the 1,843 lines of detail correctly lives outside the body.

5 / 5

Total

19

/

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.

A tight, well-scoped description that names the product, lists concrete capability areas, provides an explicit Use-when clause, and actively disambiguates against sibling skills. The only weaknesses are modest coverage gaps and missing common trigger synonyms (e.g., @, unread, emoji, pin).

Suggestions

Add one or two more trigger synonyms for common user phrasings, e.g. "@我/提到我、未读、表情、置顶/Pin", to strengthen natural-term coverage.

Mention the moderation/governance sub-capabilities (禁言/管理员/公告) explicitly in the capability list to close the specificity gap with the skill's actual coverage.

DimensionReasoningScore

Specificity

Concrete actions are named ("收发/搜索消息、建群、群治理、Bot/Webhook、文件,或仅限 IM 的消息谓词筛选") rather than generic domain language. Falls short of 5 because covered capabilities like pins/top, unread, reactions/emoji, and muting are absent, leaving minor gaps in coverage.

4 / 5

Completeness

Explicitly answers both questions: the what ("钉钉群聊与消息" plus a concrete action list) and a concrete, explicit "Use when" clause with specific trigger tasks. Sibling-skill routing (aisearch/misc/mail) further sharpens the when; not 4 because the when is fully explicit rather than weakly implied.

5 / 5

Trigger Term Quality

Includes natural phrases users would say ("搜索消息", "建群", "Bot/Webhook", "文件") alongside the domain term. Not 5 because common variations such as @我/提到我, 未读, 表情/emoji, 拉群, and 置顶 are missing from the trigger list.

4 / 5

Distinctiveness Conflict Risk

Names the product (钉钉), scopes to group chat/IM only, and explicitly delegates adjacent domains (跨源主题 → dingtalk-aisearch, DING/班级群 → dingtalk-misc, 邮件 → dingtalk-mail), giving it a clear niche with minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

75%

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

Validation — 12 / 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

relative_links

Relative link issues: 11 deeper-than-1-level, 1 suspicious

Warning

referenced_paths_exist

Referenced path issues: 11 deeper-than-1-level

Warning

Total

12

/

16

Passed

Repository
DingTalk-Real-AI/dingtalk-workspace-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.