CtrlK
BlogDocsLog inGet started
Tessl Logo

dingtalk-dev

钉钉开放平台企业内部应用管理:应用查询/创建/修改/删除/停启、凭证、权限点、成员、安全配置、网页应用、机器人、版本发布。Use when 用户说 开发者后台应用/开放平台应用/企业内部应用/agentId/clientId/appKey/appSecret/customKey/应用权限/权限点/scopeValue/创建机器人/智能体机器人/机器人配置/机器人回调/IP白名单/登录重定向/端内免登/应用版本/版本发布/发布审核/选审批人/把机器人接到本地调试/connect。

73

Quality

92%

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

85%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 skill body with concrete commands, explicit validation checkpoints, and clean one-level-deep reference navigation. The only weakness is redundancy in completion-state handling across the MUST DO checklist and the 生效模型 section.

Suggestions

Consolidate the completion-state gate handling: keep the hard gates (BLOCKED_BY_VERSION_PUBLISH/mustContinue, BLOCKED_BY_MISSING_UNIFIED_APP_ID, LOCAL_DEBUG_ONLY) in one place—either the MUST DO checklist or the 生效模型 section—and cross-reference from the other to remove the duplicated strings.

In 生效模型, the BLOCKED_BY_VERSION_PUBLISH / BLOCKED_BY_MISSING_UNIFIED_APP_ID bullets repeat rules 7, 8, and 10 nearly verbatim; reduce them to a one-line pointer to the MUST DO rules to tighten token usage.

DimensionReasoningScore

Conciseness

The body is dense and high-signal with no basic-concept filler, but the completion-state gates (BLOCKED_BY_VERSION_PUBLISH, mustContinue, BLOCKED_BY_MISSING_UNIFIED_APP_ID, LOCAL_DEBUG_ONLY) are restated in both MUST DO rules 7-10 and the 生效模型 section, which could be tightened. Not a 3 because not every token earns its place due to this duplication; not a 1 because it is lean overall and assumes Claude's competence.

2 / 3

Actionability

Gives exact commands and flags ("--format json", "--dry-run" then "--yes", "dws dev app --help"), exact field/completion-state values, and a copy-paste shortcuts table, matching the fully-executable anchor.

3 / 3

Workflow Clarity

The numbered MUST DO sequence includes explicit validation checkpoints (dry-run before yes, write-then-readback) and the 生效模型 diagrams the full version flow with feedback loops; destructive/batch ops have validation so no cap applies.

3 / 3

Progressive Disclosure

A clear overview with a product-index table mapping each command group to one real reference file, one level deep, with content appropriately split (verified all referenced files exist).

3 / 3

Total

11

/

12

Passed

Description

100%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 dense, well-constructed description that names concrete capabilities and pairs them with an extensive explicit trigger clause in third-person voice. It fully answers both what the skill does and when to use it with low conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities—"应用查询/创建/修改/删除/停启、凭证、权限点、成员、安全配置、网页应用、机器人、版本发布"—matching the anchor for enumerating several specific actions rather than vague language.

3 / 3

Completeness

It explicitly answers both what (the capability list) and when (an explicit "Use when 用户说..." trigger clause), and uses third-person voice with no first/second-person phrasing to penalize.

3 / 3

Trigger Term Quality

The "Use when 用户说 ...开发者后台应用/企业内部应用/agentId/clientId/appKey/appSecret/...创建机器人/...把机器人接到本地调试/connect" clause covers both natural user phrasings and the identifiers users actually cite, matching the high-coverage anchor.

3 / 3

Distinctiveness Conflict Risk

The niche is sharply scoped to 钉钉开放平台企业内部应用管理 with distinct, domain-specific triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

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.