CtrlK
BlogDocsLog inGet started
Tessl Logo

dingtalk-doc

钉钉在线文字文档(adoc)内容:查找、创建、读取编辑、块、评论、媒体/附件、白板卡片容器、导入导出、版本、模板、权限、分享及 Markdown/JSONML。不做白板图形/原生 .md/电子表格(dingtalk-misc)、文档空间与钉盘存储(dingtalk-drive)、知识库组织(dingtalk-wiki)、AI 表格(dingtalk-aitable)。命令前缀:dws doc。

64

Quality

79%

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/multi/dingtalk-doc/SKILL.md
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 exceptionally dense, high-signal routing skill: nearly every line is an executable command, a boundary, or a recovery rule, with explicit write-verification and per-error feedback loops. The only deductions are repeated Schema/Help gating rules across three sections and reference chains that nest two levels deep.

DimensionReasoningScore

Conciseness

The body is telegraphic with zero concept padding ('禁以产品 Schema/全文/atomic 起步', '复用 ID,禁标题/钉盘重搜'), but the Schema/Help gating rules ('Schema 不可用才读一次 leaf Help', 'unknown flag 用同 leaf Help 修正一次', '禁全 Catalog/root/parent/product Help') repeat nearly verbatim in the runtime contract, Shortcut 发现, and 错误最短路径 sections.

4 / 5

Actionability

Every route is a copy-paste-ready command with concrete flags and placeholders, e.g. 'dws doc +search --query <精确标题>', 'dws doc +create --name <标题> --content <文本|-|@文件>', 'dws drive +recent [--operate-type 1] --limit <N>', and boundaries like '-=stdin,禁 @-' make the common cases fully executable.

5 / 5

Workflow Clarity

The Golden Route states an explicit ordering principle ('稳定 ID → shortcut → 局部读 → 精确写'), writes carry mandatory validation ('写后验证结果,不凭退出码宣称成功', '回读匹配才报完成'), and the 错误最短路径 section defines a distinct feedback loop per failure class (REVISION_CONFLICT → re-read and diff before overwrite; commit-unknown → re-read, no auto-retry; partial_success → only complete unfinished steps).

5 / 5

Progressive Disclosure

A trigger-condition table maps each situation to exactly one existing reference file with anti-preload rules ('禁止读取 reference;禁预加载/连读'), keeping the root skill an overview. However, some reference chains nest a second level (doc-create.md → format/doc-jsonml-cookbook.md, style/doc-style-guideline.md → format/doc-jsonml-schema.md), which falls short of the clean one-level-deep anchor.

4 / 5

Total

18

/

20

Passed

Description

70%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 specific, well-bounded description that comprehensively lists capability areas and explicitly disambiguates against four sibling skills. Its main gap is the missing positive 'Use when…' trigger clause, leaving 'when to use this skill' only weakly implied by the exclusion list.

Suggestions

Add an explicit positive trigger clause (e.g. '用于…当用户提到钉钉文档/在线文档/协作文档时使用') so the 'when' side is stated, not just implied by exclusions — this would lift completeness from 3 to 4-5.

Include a few more natural user phrasings as trigger terms, such as 协作/共同编辑, 划词评论, and 在线文档, to broaden trigger-term coverage beyond the current capability nouns.

Spell out 2-3 of the terse verb-noun pairs into concrete actions (e.g. '按标题搜索文档' instead of bare '查找') to nudge specificity toward the comprehensive anchor.

DimensionReasoningScore

Specificity

The description enumerates many concrete capability areas ('查找、创建、读取编辑、块、评论、媒体/附件…导入导出、版本、模板、权限、分享及 Markdown/JSONML'), going well beyond naming the domain. It stops short of anchor 5 because these are terse verb-noun pairs rather than fully spelled-out concrete actions with comprehensive coverage.

4 / 5

Completeness

The 'what' is clear and detailed, and the exclusion list ('不做白板图形/原生 .md/电子表格…知识库组织…AI 表格') gives negative trigger guidance, but there is no positive 'Use when…' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is above anchor 2 because the 'what' is specific and the 'when' is partially implied by the exclusions.

3 / 5

Trigger Term Quality

Good coverage of natural terms a DingTalk user would say — 钉钉, 在线文字文档, 评论, 分享, 模板, 权限, 导出/导入, 附件 — plus the command prefix 'dws doc'. A few natural synonyms and variations (e.g. 协作/共同编辑, 划词评论, 在线文档 as a standalone phrase) are missing, so it does not reach anchor 5.

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche and names the four sibling skills it must not trigger ('dingtalk-misc', 'dingtalk-drive', 'dingtalk-wiki', 'dingtalk-aitable') with what each handles instead, giving minimal conflict risk.

5 / 5

Total

16

/

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: 8 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 8 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.