CtrlK
BlogDocsLog inGet started
Tessl Logo

dingtalk-aitable

钉钉 AI 表格(多维表)。Use when 用户说 AI表格/多维表/数据表/base/table/建表/查记录/写数据/字段/记录增删改查/筛选/排序/公式/模板搜索/批量导入CSV或JSON/导出/仪表盘/图表/上传附件到表格/按字段类型建表/数据源/创建数据源/更新数据源配置/触发数据源同步/按任务 ID 查询同步状态/获取数据源配置/列出数据源可用来源/获取数据源可同步字段/审批数据同步。不做电子表格单元格读写(走 dingtalk-misc)、文档编辑(走 dingtalk-doc);听记待办入表先用 dingtalk-minutes 提取,再由本 skill 写入。命令前缀:dws aitable。

74

Quality

94%

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.

A tight, command-first skill body with excellent actionability and validation-rich workflows for destructive/batch operations. Progressive disclosure is well structured with verified references; the only gaps are mild rule repetition and a couple of vague directory-level reference pointers.

Suggestions

Consolidate the repeated 'don't preload / max one reference / don't read aitable.md by default' guidance into a single 按需加载 section to remove the 3-way restatement.

Replace the vague '附件、表单、工作流 → references/aitable/ 下对应的一个精确文件' row with explicit links to aitable-attachment.md, aitable-form.md, and aitable-workflow.md so navigation is fully direct.

DimensionReasoningScore

Conciseness

Lean command-routing prose that assumes Claude's competence and explains no basic concepts, but the progressive-disclosure discipline (no preload, one reference max, don't read aitable.md by default) is restated across 当前最短路径, 按需加载, and the Shortcut/Golden Route sections.

4 / 5

Actionability

Every common intent maps to a copy-paste-ready `dws aitable …` command with concrete flags and JSON structures (e.g. base-bootstrap with name/fields, record-query with --field-ids/--filters/--sort).

5 / 5

Workflow Clarity

Multi-step processes carry explicit validation checkpoints (write-then-read-back by new ID, check completed/failed, hasMore=false for completeness, partial_success≠done) plus feedback loops in 错误最短路径 and confirmation gating for destructive/batch ops.

5 / 5

Progressive Disclosure

Clear one-level-deep trigger→reference table with all referenced files verified present, but the '附件、表单、工作流' row points vaguely to 'references/aitable/ 下对应的一个精确文件' instead of naming the specific files, a minor navigation gap.

4 / 5

Total

18

/

20

Passed

Description

100%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 dense, highly specific description that names the product, enumerates concrete actions, provides an explicit Use-when trigger clause with natural synonyms, and disambiguates against sibling skills via clear boundary routing. Minor density aside, it satisfies what/when/distinctiveness comprehensively.

DimensionReasoningScore

Specificity

Lists many concrete actions (建表, 查记录, 写数据, 筛选, 排序, 批量导入CSV或JSON, 导出, 仪表盘, 图表, 数据源创建/同步/审批) with comprehensive coverage rather than vague language.

5 / 5

Completeness

Explicitly answers both what (钉钉 AI 表格 + enumerated actions) and when via a concrete 'Use when 用户说…' clause with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger terms a user would say, including synonyms (AI表格/多维表/数据表, base/table) and specific operations (记录增删改查, 上传附件, 模板搜索).

5 / 5

Distinctiveness Conflict Risk

Clear niche with explicit boundary routing away to dingtalk-misc (电子表格), dingtalk-doc (文档编辑) and dingtalk-minutes (听记), minimizing conflict risk.

5 / 5

Total

20

/

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.

Validation12 / 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.