CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dingtalk-aitable

钉钉 AI 表格(多维表)业务操作。Use when 用户需要操作 AI 表格/多维表/Base/Table、应用模式/App 页面/Widget、建表、查写记录、字段、记录评论、评论回复、访问密钥(API Key)、SQL/PostgreSQL/SELECT/JOIN、筛选、排序、公式、模板、批量导入 CSV 或 JSON、导出、仪表盘、图表、上传附件、数据源配置与同步、按任务 ID 查询同步状态或审批数据同步。普通请求以完成明确的业务操作为主;当用户明确要求 CLI 契约评审、核对 aitable 合成 JSON 回执、dry-run、命令参数、Help/Schema 契约或恢复方案时,必须加载本 Skill。只评审 aitable 合成 JSON 回执也必须加载本 Skill;“不要执行线上业务”不等于免除本机离线契约核对,不能按通用 JSON 经验直接作答。这是本机 Help/Schema 契约核对,不是仓库源码审查,不从源码搜索开始;先加载正文确定入口与规则,不能仅凭摘要执行;以用户原文指定的核对入口为准,Skill 参数不得扩大范围。不做电子表格单元格读写或单元格批注(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。

Quality

87%

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

73%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 delivers exceptionally concrete, executable guidance with well-sequenced workflows and robust validation/error-recovery loops, and its reference navigation is genuinely on-demand with all paths resolving. Its main weaknesses are token efficiency — verbatim duplicated rules, massive run-on paragraphs, and specialized contract material inlined in the root file — which keep it well below ideal conciseness.

Suggestions

Deduplicate the repeated bullets in 执行约束 and 记录稳定约束 (write read-back, hasMore/partial_success checks, timestamp reuse, JSON field reuse) into a single occurrence each.

Move the specialized 表单分享用法回答契约 and 返回值评审专用查询 sections (~80 lines used only in narrow scenarios) into a dedicated reference file, keeping only the routing rule in SKILL.md.

Break the longest rule paragraphs (e.g. 链接保真必经步骤, the Golden Route psql paragraph) into bullet lists or route them to the existing references to cut root-file tokens.

DimensionReasoningScore

Conciseness

The ~47KB body contains verbatim duplicated bullet blocks ("新增或更新只使用真实返回的 ID 回读;写入效果未知时回读,不重放成功批次" and "全量查询检查 hasMore,批量写检查最终状态" each appear twice, as do the timestamp-reuse and JSON-reuse rules) and very long run-on rule paragraphs. While it avoids explaining concepts Claude already knows, the volume and repetition make it noticeably verbose rather than mostly efficient.

2 / 5

Actionability

Guidance is fully executable: exact commands with placeholders ("dws aitable +url-resolve --url <URL>"), exact JSON configs ("{\"currencyType\":\"CNY\",\"formatter\":\"FLOAT_2\"}"), precise schema-query invocations ("dws schema --cli-path ... --compact --format json"), and copy-paste-ready two-line response templates for the form-share usage case.

5 / 5

Workflow Clarity

Multi-step processes are explicitly sequenced with validation checkpoints and feedback loops: the psql flow (discover tables → inspect columns → LIMIT 3 minimal query → formal query), post-write independent read-back by real ID, token-based write-result reconciliation, INVALID_CURSOR recovery (discard all, requery without --cursor), and independent confirmation gates for destructive operations.

5 / 5

Progressive Disclosure

The on-demand loading table maps trigger conditions to specific reference files, all of which exist in the bundle and are effectively one level deep. However, the root file inlines ~80 lines of highly specialized form-share/review contracts that belong in a reference, and reference placement is inconsistent (references/aitable-record-ops.md and aitable-section.md at the root while siblings live in references/aitable/).

4 / 5

Total

16

/

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.

The description is highly specific, with comprehensive natural trigger terms in both Chinese and English, explicit what/when guidance, and explicit disambiguation against sibling dingtalk skills. Its only weakness is length — a substantial portion is directive meta-instruction about loading and review scope rather than capability description, though this does not dilute any rubric dimension.

DimensionReasoningScore

Specificity

The description enumerates many concrete operations — "建表、查写记录、字段、记录评论、评论回复、访问密钥(API Key)、SQL/PostgreSQL/SELECT/JOIN、筛选、排序、公式、模板、批量导入 CSV 或 JSON、导出、仪表盘、图表、上传附件、数据源配置与同步" — giving comprehensive, concrete coverage of the skill's capabilities rather than vague language.

5 / 5

Completeness

It explicitly answers both what ("钉钉 AI 表格(多维表)业务操作" with an enumerated operation list) and when ("Use when 用户需要操作..." plus explicit conditions for contract-review requests), with concrete trigger phrases throughout.

5 / 5

Trigger Term Quality

Natural trigger terms are covered with synonyms in both Chinese and English ("AI 表格/多维表/Base/Table", "App 页面/Widget"), plus concrete technical terms users would say (SQL/PostgreSQL/SELECT/JOIN, CSV/JSON, dry-run, Help/Schema, 仪表盘, 图表). No common variation is obviously missing.

5 / 5

Distinctiveness Conflict Risk

The DingTalk AITable niche is clear and it explicitly routes adjacent work away — "不做电子表格单元格读写或单元格批注(走 dingtalk-misc)、文档编辑(走 dingtalk-doc);听记待办入表先用 dingtalk-minutes 提取" — minimizing conflict with sibling skills.

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.

Validation — 12 / 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: 19 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 19 deeper-than-1-level

Warning

Total

12

/

16

Passed

Repository

DingTalk-Real-AI/dingtalk-workspace-cli

Path

skills/multi/dingtalk-aitable/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.