dingtalk-pat

钉钉 PAT 行为授权与本地浏览器策略管理。Use when 用户说 PAT 授权/行为权限/scope 授权/一次性授权/会话授权/永久授权/批量授权，或允许、禁止 PAT 授权流程打开浏览器。Distinct from dingtalk-dev（开放平台应用权限）。命令前缀：dws pat。

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/multi/dingtalk-pat/SKILL.md

Quality

Content

57%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.

The body is a well-structured overview with excellent progressive disclosure and a clear safety gate, but it is held back by placeholder chmod commands, a missing error-recovery feedback loop for batch operations, and a slightly verbose experimental preamble.

Suggestions

Replace the 'dws pat chmod ...' placeholders in the intent table with one concrete, copy-paste-ready example (e.g. with --products and --grant-type filled in) so the body is executable without opening the reference.

Add an explicit feedback loop for chmod: state what to do when the --dry-run preview shows unexpected scopes (adjust and re-preview) before adding --yes, satisfying the batch/destructive feedback-loop requirement.

Tighten the experimental preamble by dropping bilingual redundancy and the tangential mono-mode/issue-feedback detail, keeping only the stability caveat essential to safe usage.

Dimension	Reasoning	Score
Conciseness	The intent table and safety boundaries are lean, but the experimental preamble carries bilingual redundancy ('EXPERIMENTAL · 试验版 / Preview') and tangential meta-guidance (mono-mode setup command, '问题请提 issue 反馈') that could be tightened; it is mostly efficient rather than fully lean.	2 / 3
Actionability	browser-policy rows give executable commands, but the chmod rows use '...' placeholders ('dws pat chmod ... --dry-run --format json') with key details deferred to pat.md, so guidance is concrete but incomplete rather than copy-paste ready.	2 / 3
Workflow Clarity	The dry-run → user confirmation → --yes sequence is an explicit validation gate, but no error-recovery feedback loop is given for the batch/destructive chmod operation, which the rubric caps at 2.	2 / 3
Progressive Disclosure	The body is a clear overview that well-signals one-level-deep references — '命令参考：[pat.md](references/pat.md)' (a real, verified file) and the dws-shared prerequisite — with detail appropriately split out.	3 / 3
	Total	9 / 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 strong description: it explicitly covers what the skill does, when to use it with natural trigger terms, and how it differs from the related dingtalk-dev skill. The only soft spot is specificity, which states the domain and a few actions rather than a comprehensive list of concrete operations.

Dimension	Reasoning	Score
Specificity	Names the domain and a few concrete actions ('行为授权与本地浏览器策略管理', '允许、禁止 PAT 授权流程打开浏览器') but does not list multiple specific concrete actions in the score-3 sense; it is closer to 'Names domain and some actions' than to a comprehensive action list.	2 / 3
Completeness	Explicitly answers both what ('钉钉 PAT 行为授权与本地浏览器策略管理') and when via an explicit 'Use when...' trigger clause, matching the score-3 anchor.	3 / 3
Trigger Term Quality	Provides good coverage of natural trigger terms a user would say ('PAT 授权/行为权限/scope 授权/一次性授权/会话授权/永久授权/批量授权' plus '允许、禁止...打开浏览器'), including common variations of grant types.	3 / 3
Distinctiveness Conflict Risk	States a clear niche with an explicit disambiguation ('Distinct from dingtalk-dev（开放平台应用权限）') and a command prefix ('命令前缀：dws pat'), making conflicts unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

81%

Warnings & errors only

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

Criteria	Description	Result
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
Path: skills/multi/dingtalk-pat/SKILL.md
Commit: 1877870

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

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.