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。

72

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

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.

An unusually rigorous operational skill body: copy-ready commands, explicit result semantics, and validation gates on every destructive or paginated operation. Weaknesses are limited to some repeated boundary rules and one cross-skill nested reference.

Suggestions

State the '+move-to-drive / 我的文档' exception once (e.g. in Golden Route) and reference it from 当前最短路径 and 跨产品边界 instead of repeating the full rule three times.

Inline the essential steps of the doc-import flow into lite-recipes.md so readers do not need to follow the nested ../../dingtalk-doc/references/doc/doc-import.md link.

DimensionReasoningScore

Conciseness

Lean and dense with zero concept explanation, but the +move-to-drive/我的文档 exception is restated three times (Golden Route table, 当前最短路径 twice, 跨产品边界), which is trimmable repetition rather than over-explanation.

4 / 5

Actionability

Fully executable throughout: exact commands with flags (`+space-list --type <type> --limit 50 --page-all`), exact schema/jq queries, and exact response field names (autoPageComplete, spaceTypeVerified, success=true) to act on.

5 / 5

Workflow Clarity

Multi-step cross-product flows are explicitly ordered (e.g. `+space-create` → `doc +import` → `+move-to-drive`), and every write path carries explicit validation checkpoints plus a dedicated error-recovery section with stop conditions.

5 / 5

Progressive Disclosure

Clear on-demand loading table maps trigger conditions to all five existing one-level-deep references; the minor gap is lite-recipes.md pointing onward to `../../dingtalk-doc/references/doc/doc-import.md`, a nested hop outside the bundle.

4 / 5

Total

18

/

20

Passed

Description

92%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, boundary-aware trigger description: concrete action inventory, explicit Use-when clause, and explicit deferral rules to sibling skills. Keyword coverage is good though not exhaustive of natural phrasing variations.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across the full domain: "创建、查找或列出知识库", "库内节点创建、列表、搜索、复制、移动、删除", members, and "知识库动态" — comprehensive coverage with no padding.

5 / 5

Completeness

Explicitly answers both what ("钉钉知识库与空间管理" plus the enumerated operations) and when ("Use when 用户明确说 知识库/wiki/...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural-keyword coverage including the Chinese/English synonym pair 知识库/"wiki", "个人知识库", and "知识库成员"; a few plausible user phrasings (e.g. 团队空间/企业知识库 variations) are not covered.

4 / 5

Distinctiveness Conflict Risk

Negative trigger guidance explicitly routes overlapping cases away ("仅说'文档空间/我的文档'不触发:…走 dingtalk-drive;节点正文读写走 dingtalk-doc"), giving a clear niche with minimal conflict risk.

5 / 5

Total

19

/

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.

Validation — 14 / 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.