dws

管理钉钉产品能力(AI表格/AI搜问/日历/通讯录/群聊与机器人/待办/审批/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 事件或 OA 审批事件、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，以及审批任务创建/完成/转交时使用。

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

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 well-structured, highly actionable command-discovery and routing guide with explicit validation feedback loops and clean progressive disclosure into verified reference files. The only dimension short of the top anchor is conciseness, where a few dense Schema-boundary sections could be trimmed or moved deeper.

Suggestions

Tighten the 'Schema、Help 与业务数据的边界' and 'Helper-only 与本地 Cobra 命令' sections or move their detail into a dedicated reference file to reduce token load while keeping the boundary rules inline as a short checklist.

Consider collapsing the repeated guidance about --compact / --all / full-leaf behavior into a single short table since the same caveat appears across several sections.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and focused on command/contract semantics (Schema progressive query, --compact field whitelist, confirmation protocol) with little padding of concepts Claude already knows. It does not fully reach the lean 5 anchor because sections like 'Schema、Help 与业务数据的边界' and the helper-only discussion are lengthy and could be tightened or pushed deeper into references.	4 / 5
Actionability	It provides fully executable, copy-paste-ready commands (`dws schema`, `dws schema "calendar event create" --compact`, `--format json`, `--dry-run`, `--verbose`) plus a worked JSON leaf example and concrete decision-tree branches, matching the 'fully executable; specific examples cover the common cases' anchor.	5 / 5
Workflow Clarity	The core flow is a clearly sequenced four-step process with a URL-precheck step 0, plus an explicit destructive-operation confirmation protocol (summary → user consent → --yes) and a confirmation_required retry/feedback loop, matching the 'clear sequence with explicit validation steps; feedback loops for error recovery' anchor.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview pointing to one-level-deep references (products/, intent-guide.md, url-patterns.md, best_practices/, scripts/) with every referenced file verified to exist, and large detail (aitable sub-chapters) is appropriately split into separate files, matching the 'clear overview with well-signaled one-level-deep references' anchor.	5 / 5
	Total	19 / 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.

The frontmatter description is specific, trigger-rich, and explicitly pairs what the skill does with when to use it, scoring near the top of the rubric. Its only minor gap is that capabilities read as noun phrases rather than crisp action verbs.

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete product capabilities (AI表格/AI搜问/日历/通讯录/群聊与机器人/待办/审批/考勤/日志/DING消息/钉钉文档/钉钉云盘/原生Markdown/邮箱/在线电子表格/知识库), matching the 'lists several specific actions; minor gaps' anchor. It does not quite reach the 5 anchor because capabilities are listed as noun phrases rather than crisp concrete verbs like 'extract/fill/merge'.	4 / 5
Completeness	It explicitly answers both 'what' (manages DingTalk product capabilities across the enumerated products) and 'when' ('当用户需要...时使用' with a long concrete list of trigger scenarios), matching the anchor for clearly and explicitly answering both what AND when with concrete trigger phrases.	5 / 5
Trigger Term Quality	It includes extensive natural trigger phrases users would say ('找人/查谁负责某事项', '提交日报周报', '收发邮件', '读写钉钉文档', '上传下载云盘文件') plus file extensions (.md, axls) and synonyms, achieving comprehensive coverage matching the top anchor.	5 / 5
Distinctiveness Conflict Risk	It carves a clear niche — DingTalk product management via the dws CLI — with distinct triggers (subscription to IM/OA events, group lifecycle, approval instances) that would not collide with unrelated skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 5
	Total	19 / 20 Passed

Validation

81%

Warnings & errors only

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

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 42 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 3 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: DingTalk-Real-AI/dingtalk-workspace-cli
Path: skills/mono/SKILL.md
Commit: e9de685

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.