lark-mail

飞书邮箱：Use when user mentions 起草邮件、写邮件、草稿、发送/回复/转发邮件、查阅邮件、看邮件、搜索邮件、邮件文件夹、邮件标签、邮件联系人、监听新邮件、邮件收信规则等；use for mail/email intent only. Do not use for docs/sheets/calendar/auth setup/pure contact lookup/IM chat tasks.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%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.

Highly actionable and well-structured with strong workflows and progressive disclosure; the main weakness is repetition of the send-confirmation and security rules across multiple sections, which inflates token cost without adding guidance.

Suggestions

Consolidate the send-confirmation rule into a single authoritative statement; the 命令选择 and 典型工作流 sections can reference it instead of restating it.

Tighten the 安全规则 and 数据真实性 sections, which overlap on confirmation/forgery themes — merge or cross-link to remove redundancy.

The 核心概念 definitions (Thread/Label/Rule) are partly inferable; consider trimming to only the CLI-specific distinctions (Draft vs Sent, inline CID attachments).

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational prose, but the send-confirmation rule is restated across 安全规则, 命令选择, and 典型工作流, and the 8-point security section overlaps with the 数据真实性 section, adding repetition that could be tightened.	3 / 5
Actionability	Provides copy-paste-ready commands with exact --params/--data JSON, a mail-type→command selection table, and concrete bash examples covering the common cases end-to-end.	5 / 5
Workflow Clarity	An 11-step 典型工作流 with explicit validation checkpoints (send_status after send, --html=false for verification, batch-preview counts before destructive ops) and a worked confirm-then-execute example with error feedback.	5 / 5
Progressive Disclosure	SKILL.md is an overview with ~30 one-level-deep reference links clearly signaled as 'ref: [name](path)', a shortcuts table linking each verb to its reference, and an assets/templates pointer — easy to navigate.	5 / 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 tight, third-person description that enumerates concrete capabilities, natural trigger phrases, and explicit use/non-use boundaries. It cleanly satisfies the what/when requirement with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete mail actions — 起草邮件、写邮件、草稿、发送/回复/转发邮件、查阅邮件、看邮件、搜索邮件、邮件文件夹、邮件标签、邮件联系人、监听新邮件、邮件收信规则 — giving comprehensive coverage rather than vague domain naming.	5 / 5
Completeness	Explicitly states both what (飞书邮箱 with the enumerated operations) and when ('Use when user mentions …'), plus explicit negative boundaries, satisfying both anchors concretely.	5 / 5
Trigger Term Quality	Covers natural user phrasings with synonyms (起草/写/草稿, 查阅/看, 发送/回复/转发) that a user would actually say; mail has no relevant file extensions to include.	5 / 5
Distinctiveness Conflict Risk	Scoped to mail/email intent only with an explicit exclusion list (docs/sheets/calendar/auth setup/pure contact lookup/IM chat), minimizing conflict with adjacent skills.	5 / 5
	Total	20 / 20 Passed

Validation

75%

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 — 12 / 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	12 / 16 Passed

Repository: larksuite/cli
Path: skills/lark-mail/SKILL.md
Commit: ceace6d

Reviewed: 2 hours 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.