CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dws

独立脑图的带内容创建与主题读写使用 dws mind;空白脑图走 wiki,听记内置思维导图走 minutes。 管理钉钉产品能力(Agoal目标管理/AI表格/AI搜问/日历/通讯录/群聊与机器人/待办/审批/法务智能合同/考勤/日志/DING消息/开放平台文档/钉钉文档/钉钉云盘/原生Markdown文件/AI听记/邮箱/在线电子表格/知识库等)。当用户需要查询战略解码、经营合约字段、目标规则周期、个人目标、目标模板或周月报规则的按时/迟交/未提交统计与跟催,操作表格数据、管理日程会议、模糊找人/查谁负责某事项、查询通讯录、管理群聊、机器人发消息、创建待办、提交审批、查询或创建合同台账、批量导入合同、按听记起草合同、归档合同、管理合同项目/相对方/账款、查看考勤、提交日报周报(钉钉日志模版)、读写钉钉文档、上传下载云盘文件、读取或修改原生.md文件、查询听记纪要、收发邮件、读写在线电子表格(axls)、管理钉钉知识库,或订阅个人 IM、OA 审批、VoIP 通话邀请、待办、互动卡片回调、听记或日历变化事件、实时监听群成员加入、群成员退出、群改名和群解散、审批实例发起/抄送/终止/完成、审批任务创建/完成/转交、VoIP 通话邀请、待办创建/更新/删除,互动卡片回调,以及听记创建/纪要生成、主日历创建/修改/取消时使用。周报/月报正文填报属于日志 Report;规则级提交统计、迟交、未提交和跟催属于 Agoal。

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Failed to scan

The risk profile of this skill

SKILL.md
Quality
Evals
Security

Quality

Content

67%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, command-rich CLI skill body with strong routing, safety-confirmation, and error-recovery workflows plus a well-organized, verified reference tree. Its main weaknesses are rule redundancy across sections, an overloaded ~48KB overview that should shed detail into references, and a nearly impenetrable AI 表格 policy section.

Suggestions

Consolidate the AI 表格 MUST-DO bullets (lines 23–30) into a single sequenced checklist in references/products/aitable.md, keeping one short rule per concern in SKILL.md — link-fidelity rules are currently restated across four separate bullets.

Merge the three shortcut-guidance sections (使用原则, Shortcut 总览, 命令发现) into one, retaining the statistics table; the same selection rules ('不要为已知意图加载完整产品 Catalog') currently appear in multiple forms.

Move the Schema 字段速查 and --all/--compact boundary detail into a reference file (e.g. global-reference.md) and keep only the 4-layer progressive query ladder inline, shrinking SKILL.md toward a true overview.

DimensionReasoningScore

Conciseness

The body is information-dense and never explains concepts Claude already knows, but at ~48KB it restates the same rules repeatedly — link-fidelity/percent-encoding rules recur across the AI 表格 bullets ('逐字符比对', '%3D 不改为 %3d'), and shortcut-selection guidance appears in three separate sections (使用原则, Shortcut 总览, 命令发现). Mostly efficient but needs tightening, so 3 rather than 4, where redundancy would be only minor.

3 / 5

Actionability

Concrete copy-paste-ready commands are plentiful ('dws schema "calendar event create" --compact', 'dws auth login --intl', 'dws event consume user_card_action_triggered --flatten -f ndjson') and protocols cite exact JSON fields ('error.reason == "confirmation_required"'). Falls short of 5 because common business operations are delegated to references and many invocations remain placeholders ('dws <service> +<verb> ...').

4 / 5

Workflow Clarity

Core flows are clearly sequenced with explicit validation checkpoints: the 4-step intent flow (URL 预检 → 意图分类 → 歧义处理 → 产品映射), the 3-step confirmation flow, the confirmation_required retry protocol, and the whiteboard render→confirm and +diff→confirm loops with sourceDigest. Not 5 because the AI 表格 delivery/link rules (lines 24–30) form an unsequenced policy tangle around one of the most-used products (140 shortcuts).

4 / 5

Progressive Disclosure

Navigation is strong: a product table linking each product to its reference file, a '详细参考 (按需读取)' index with one-line descriptions, an explicit read-on-demand principle ('只读相关段落,不预加载全篇'), and all referenced files verified to exist. Not 5 because the overview itself carries large blocks (命令发现/Schema 字段速查, the AI 表格 policy wall, Shortcut 总览) that belong in reference files.

4 / 5

Total

15

/

20

Passed

Description

96%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.

An unusually comprehensive, trigger-rich description that explicitly answers both what and when with concrete natural-language triggers and internal routing distinctions. Its only weaknesses are extreme length with duplicated items ('VoIP 通话邀请' and '互动卡片回调' each appear twice) and domain overlap with sibling dingtalk-* product skills.

DimensionReasoningScore

Specificity

The description lists many concrete named operations — '批量导入合同、按听记起草合同、归档合同', '提交日报周报(钉钉日志模版)', '读写在线电子表格(axls)', '上传下载云盘文件' — covering every sub-product with specific actions rather than abstractions, matching the comprehensive 5 anchor; score 4 would require coverage gaps that are not evident.

5 / 5

Completeness

Both questions are explicitly answered: the 'what' ('管理钉钉产品能力(Agoal目标管理/AI表格/...)') and an explicit 'when' clause ('当用户需要…时使用') with concrete trigger phrases. This clearly fits the 5 anchor rather than 4, where the 'when' would be less explicit or specific.

5 / 5

Trigger Term Quality

Natural user phrasings are comprehensive: '机器人发消息', '查看考勤', '查谁负责某事项', '收发邮件', '监听消息撤回', plus file extensions ('原生.md文件', 'axls') and raw event keys. This matches the 5 anchor's 'comprehensive coverage including synonyms and file extensions'; 4 would mean a few natural terms are missing.

5 / 5

Distinctiveness Conflict Risk

The DingTalk niche is clear with explicit internal disambiguation ('空白脑图走 wiki,听记内置思维导图走 minutes'; '周报/月报正文填报属于日志 Report;…属于 Agoal'), but the description claims chat/doc/calendar/todo/wiki domains that the body's 'multi skill' column shows are also served by sibling dingtalk-* skills — a real overlap risk with closely related skills. Fits 4 ('mostly distinct; minor overlap risk') better than 5.

4 / 5

Total

19

/

20

Passed

Validation

68%

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

Validation — 11 / 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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 48 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 4 deeper-than-1-level

Warning

Total

11

/

16

Passed

Repository

DingTalk-Real-AI/dingtalk-workspace-cli

Path

skills/mono/SKILL.md

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.