CtrlK
BlogDocsLog inGet started
Tessl Logo

dingtalk-aisearch

AI搜问:人员语义搜索与跨源定位。Use when 按姓名/工号/部门/职责/上下级或手机号线索找人,跨文档/消息/邮件/听记检索,或回溯“我发过/收到过”。完整手机号反查走 dingtalk-contact;找到 userId 后由 contact 补详情。命令前缀:dws aisearch。

72

Quality

91%

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

88%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 tightly written, highly actionable skill body with clear multi-step SOPs and validation feedback loops, supported by well-organized one-level-deep references. The main issue is a broken inline reference (references/ding.md) and minor redundancy between the SOPs and the hard-constraints section.

Suggestions

Fix or remove the broken reference to references/ding.md (the file is absent from the bundle); either add the file or point the DING handoff at dingtalk-misc's own skill/reference.

Trim the 高频硬约束 section where it merely restates rules already enforced in the SOP steps, to reduce token redundancy.

Consider folding the 跨产品协作 section (which repeats the SOP-1 衔接 handoffs) into a single handoff table to avoid stating the same cross-skill transitions twice.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence — pure commands, triggers, and constraints with no boilerplate concept explanations — but the 高频硬约束 section repeats rules already stated in the SOPs, a minor over-explanation that could be trimmed.

4 / 5

Actionability

Commands are fully executable and copy-paste ready with explicit flags (--query, --dimension, --format json) and real returned fields (userId/openDingTalkId), covering the common cases across all three SOPs.

5 / 5

Workflow Clarity

Each SOP is a numbered sequence (定维度→执行→解析→衔接→失败) with explicit checkpoints — multi-candidate selection, one-retry cap, and a '如实告知' failure feedback loop; aisearch is read-only so the destructive-validation cap does not apply.

5 / 5

Progressive Disclosure

The body is a concise overview with bulk detail pushed one level deep to clearly signaled references (aisearch.md, intent-guide.md, lite-recipes.md), but it also references references/ding.md which does not exist in the bundle, a navigation gap keeping it below 5.

4 / 5

Total

18

/

20

Passed

Description

95%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 strong, well-scoped description that clearly states what the skill does and when to use it with rich natural trigger terms and explicit cross-skill boundaries. Minor specificity gaps keep it just below a perfect score on that single dimension.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions (人员语义搜索, 跨文档/消息/邮件/听记检索, 行为回溯, 手机号反查 handoff) with only minor coverage gaps, fitting the 'lists several specific actions' anchor rather than the fully comprehensive 5.

4 / 5

Completeness

It explicitly answers both 'what' (semantic person search, cross-source content locating, behavior recall) and 'when' via a concrete 'Use when …' clause with multiple trigger scenarios, matching the top anchor.

5 / 5

Trigger Term Quality

Comprehensive natural user phrasings are present — '找张三', '谁负责 XX', '上下级', '我发过/收到过' — covering synonyms and concrete clue types users would actually say, matching the comprehensive-coverage anchor.

5 / 5

Distinctiveness Conflict Risk

Clear niche with command prefix 'dws aisearch' and explicit boundary handoffs to dingtalk-contact/chat/misc, giving minimal conflict risk with sibling skills.

5 / 5

Total

19

/

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.

Validation12 / 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: 1 suspicious

Warning

referenced_paths_exist

Referenced path issues: 2 missing

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.