CtrlK
BlogDocsLog inGet started
Tessl Logo

dingtalk-minutes

钉钉 AI 听记。Use when 查询听记摘要、转写、关键词、待办或分享。写文档走 dingtalk-doc;日程走 dingtalk-calendar。

66

Quality

81%

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

72%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-structured CLI-routing skill body with strong progressive disclosure and good read-side workflows. The main gaps are mild rule repetition across sections and the absence of a validated SOP for the write/batch operations.

Suggestions

Add an explicit SOP with validation for write/batch operations (e.g. +replace-batch and +record-start) — a preview-then-confirm-before-write feedback loop — so these destructive/batch flows have the same checkpoints as the read SOPs.

De-duplicate the repeated scope-selection (mine/all/shared) and '--format json' rules: state each once in a canonical location and reference it elsewhere, to cut token repetition.

DimensionReasoningScore

Conciseness

The body is dense and operational (product-specific execution contracts, not concepts Claude already knows), but the same rules are restated multiple times — the mine/all/shared scope rule and the '--format json' requirement each recur across SOP-1, 高频硬约束, and referenced files — so it could be tightened.

2 / 3

Actionability

Concrete, copy-paste-ready commands with specific flags appear throughout ('dws minutes list all --start "<ISO>" --end "<ISO>" --format json', 'dws minutes get summary --id <taskUuid>', 'python scripts/minutes_recent_summary.py --max 5'), and the referenced scripts are real files.

3 / 3

Workflow Clarity

The read SOPs (SOP-1/SOP-2/SOP-3) are well-sequenced with checkpoints (confirm multiple candidates, empty-list fallback chain, stop-on-missing-prereq), but the write/batch operations (+replace-batch, +record-start) appear only in the shortcut table and lack a dedicated SOP with explicit validation/feedback loops, capping this per the batch-operation guidance.

2 / 3

Progressive Disclosure

The body is an organized overview that signals one-level-deep references with explicit links (minutes.md, 07-minutes.md, intent-guide.md, lite-recipes.md), all verified as real, substantive files with content appropriately split across them.

3 / 3

Total

10

/

12

Passed

Description

90%Weight 40%Scale 1-3

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 compact, well-targeted description with an explicit 'Use when' trigger and clear disambiguation routing against sibling skills. Its only weakness is that the capability list is query-centric and not comprehensive, omitting the write/record actions the skill actually supports.

Suggestions

Broaden the capability list beyond query actions to be comprehensive — e.g. mention 发起听记/recording, 批量替换, and 改标题 so the description reflects the full surface area shown in the body.

DimensionReasoningScore

Specificity

Names the domain ('钉钉 AI 听记') and several concrete capabilities ('查询听记摘要、转写、关键词、待办或分享') plus routing, but all fall under the single verb 查询 and omit real capabilities shown in the body (发起录音/record-start, 批量替换, 改标题), so it is not comprehensive.

2 / 3

Completeness

It states what ('钉钉 AI 听记') and gives an explicit 'Use when ...' trigger listing the actions, clearly answering both what and when with explicit trigger guidance.

3 / 3

Trigger Term Quality

The 'Use when 查询听记摘要、转写、关键词、待办或分享' clause lists natural terms (摘要/转写/关键词/待办/分享) a DingTalk user would actually say, giving good coverage of natural trigger vocabulary.

3 / 3

Distinctiveness Conflict Risk

Explicit routing ('写文档走 dingtalk-doc;日程走 dingtalk-calendar') carves out a clear niche and steers away from sibling skills, making wrong-skill triggering unlikely.

3 / 3

Total

11

/

12

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.

Validation13 / 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
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.