CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dingtalk-minutes

钉钉 AI 听记。Use when 查询或修改听记摘要、完整逐字稿、关键词、标签、纪要模板及默认模板、行动项、录音、上传、听记内置思维导图、发言人洞察、ASR 热词/识别词配置或分享权限。独立 .amind 脑图文件的创建和主题读写走 dingtalk-misc 的 mind reference;写文档走 dingtalk-doc;建待办走 dingtalk-todo;日程走 dingtalk-calendar。命令前缀:dws minutes。

Quality

90%

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

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 actionable routing skill: copy-paste commands with flags, pervasive validation and error-recovery checkpoints, and disciplined on-demand loading of real reference files. The main weaknesses are moderate duplication of the fallback/pagination rules across sections and a slightly imperfect one-level-deep reference structure.

DimensionReasoningScore

Conciseness

The body is dense and imperative with no concept explanations and full assumption of Claude's competence — every line is a constraint or a command. It is not 5 because the Schema/Help fallback ladder and the pagination stop conditions are each restated nearly verbatim in two to three sections (runtime contract, Shortcut 发现, 目标与完整性, 错误最短路径), which could be consolidated; it is well above the 'unnecessary explanation' level of 3.

4 / 5

Actionability

Fully executable, copy-paste-ready commands with flags cover the common cases: "dws minutes +search --scope all --query \"<关键词>\" --page-all", "dws minutes +detail --id <taskUuid> --artifacts basic,summary,keywords", "python3 <本Skill目录>/scripts/format_timestamp.py --unit ms --timezone Asia/Shanghai <时间戳1>", plus the concrete response fields to check (data.direction/data.complete/data.pages, meta.pagination). No gaps between instruction and execution.

5 / 5

Workflow Clarity

Validation checkpoints are explicit and pervasive: "写后验证结果,不凭退出码宣称成功", "必须由 published/path/manifest/files 证明落盘", complete=true pagination verification, and resume handles "taskUuid/taskId/sessionId/checkpoint". Feedback loops are present (unknown flag → same-leaf Help → correct once; async timeout → --resume), and destructive/batch operations have confirmation gates and per-member ledgers, so the missing-validation cap does not apply. The Golden Route table functions as a checklist with per-route sequencing and boundaries.

5 / 5

Progressive Disclosure

The skill is a clear routing overview with an explicit on-demand policy ("每个 Case 最多先读取一个最精确的文件") and a trigger-conditioned table pointing to real files (references/07-minutes.md, references/intent-guide.md, references/minutes.md, scripts/format_timestamp.py all exist in the bundle). It is not 5 because some content sits two levels deep from SKILL.md (references/minutes.md → references/recipes/conventions.md; intent-guide.md → 10/11 speaker files), and those second-level files plus lite-recipes.md are not surfaced in the SKILL.md loading table.

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 highly specific, well-scoped description that explicitly states what the skill does and when to use it, with natural trigger terms and explicit routing rules that distinguish it from sibling DingTalk skills. The only minor weakness is a few missing natural synonyms/variants (e.g. flash-card and export/download phrasing) in the trigger enumeration.

DimensionReasoningScore

Specificity

The description enumerates concrete capabilities in detail — "查询或修改听记摘要、完整逐字稿、关键词、标签、纪要模板及默认模板、行动项、录音、上传、听记内置思维导图、发言人洞察、ASR 热词/识别词配置或分享权限" — covering the skill's full surface (matching the body's Golden Route) rather than vague domain language. It is not 4 because there are no meaningful coverage gaps; every core capability area is explicitly named.

5 / 5

Completeness

Both questions are answered explicitly: the 'what' via "查询或修改听记摘要、完整逐字稿、关键词、标签、纪要模板及默认模板、行动项、录音、上传…" and the 'when' via the explicit "Use when" clause with concrete trigger phrases, plus the command prefix "命令前缀:dws minutes". This directly matches the anchor for clearly and explicitly answering both what and when with concrete triggers.

5 / 5

Trigger Term Quality

Strong natural keyword coverage — "听记摘要", "完整逐字稿", "关键词", "标签", "纪要模板", "行动项", "录音", "上传", "思维导图", "发言人洞察", "分享权限", "钉钉 AI 听记" — phrases a user would naturally say. It is not 5 because a few natural variants are absent (e.g. 闪记/flash-card, 导出/下载媒体, find-by-title phrasing), though coverage clearly exceeds the 'some relevant keywords' level of 3.

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche (DingTalk AI Minutes, "dws minutes") and actively routes ambiguous intents away from sibling skills — "独立 .amind 脑图文件的创建和主题读写走 dingtalk-misc 的 mind reference;写文档走 dingtalk-doc;建待办走 dingtalk-todo;日程走 dingtalk-calendar" — minimizing conflict risk. It is not 4 because the overlap-prone adjacent intents are explicitly disambiguated rather than merely implied.

5 / 5

Total

19

/

20

Passed

Validation

81%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

13

/

16

Passed

Repository

DingTalk-Real-AI/dingtalk-workspace-cli

Path

skills/multi/dingtalk-minutes/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.