CtrlK
BlogDocsLog inGet started
Tessl Logo

dingtalk-wiki

钉钉知识库与空间管理。Use when 用户明确说 知识库/wiki/创建、查找或列出知识库/命名的团队知识空间/个人知识库/知识库成员/库内节点创建、列表、搜索、复制、移动、删除或知识库动态。仅说“文档空间/我的文档”不触发:普通存储管理与全局文件搜索走 dingtalk-drive;节点正文读写走 dingtalk-doc。命令前缀:dws wiki。

76

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

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.

The body is a highly operational dispatch guide with concrete commands, explicit validation for destructive/batch operations, and well-signaled one-level-deep references. Its only weakness is mild redundancy of the paging/resolve rules across sections.

Suggestions

Consolidate the paging-completion and resolve-space rules into a single canonical statement; the 当前最短路径, 关键结果语义, and 错误最短路径 sections currently restate the same autoPageComplete/单页不可证明唯一 conditions.

Consider merging 参数与安全边界 into the Golden Route table's 关键边界 column to remove a separate section that largely restates per-intent boundaries.

DimensionReasoningScore

Conciseness

The body is dense and operational with no concept padding, but paging/resolve and read-back rules recur across 当前最短路径, 关键结果语义, and 错误最短路径, so some lines could be tightened without loss.

4 / 5

Actionability

Concrete executable commands with exact flags and enum values throughout (e.g. `+node-create --workspace <ID> --name <名称> --type adoc`, roles `MANAGER|EDITOR|DOWNLOADER|READER`, limits 1-30/1-50), covering the common cases copy-paste ready.

5 / 5

Workflow Clarity

Routing is sequenced via the Golden Route table and 当前最短路径, with explicit validation checkpoints (read-back of new IDs, success=true, autoPageComplete checks) and a numbered 错误最短路径 feedback loop for recovery; destructive/batch ops carry validation so no cap applies.

5 / 5

Progressive Disclosure

Overview body points to one-level-deep references via a clear 按需加载 table (intent-guide, wiki-node-ops, wiki-members, wiki, lite-recipes), all of which exist in references/, with trigger conditions signaling when to load each.

5 / 5

Total

19

/

20

Passed

Description

100%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 a strong, third-person statement that covers what the skill does, when to trigger it with natural user phrases, and how it differs from sibling Drive/Doc skills. It avoids vague fluff and over-claims entirely.

DimensionReasoningScore

Specificity

Names the domain (钉钉知识库与空间管理) and lists multiple concrete actions — 创建、查找、列出知识库, 知识库成员, 库内节点创建/列表/搜索/复制/移动/删除, 知识库动态 — giving comprehensive coverage rather than generic verbs.

5 / 5

Completeness

Explicitly answers both 'what' (钉钉知识库与空间管理) and 'when' (Use when 用户明确说...) with concrete trigger phrases, so neither clause is missing or merely implied.

5 / 5

Trigger Term Quality

Includes the natural phrases a user would say (知识库, wiki, 团队知识空间, 个人知识库, 知识库成员, 节点...复制/移动/删除) plus an explicit anti-trigger (仅说"文档空间/我的文档"不触发), covering synonyms and boundary terms.

5 / 5

Distinctiveness Conflict Risk

Clear Wiki/知识库 niche with explicit routing away from dingtalk-drive (普通存储/全局搜索) and dingtalk-doc (节点正文读写), plus a command prefix (dws wiki), giving minimal overlap risk.

5 / 5

Total

20

/

20

Passed

Validation

87%

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

Validation14 / 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

Total

14

/

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.