CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

70

Quality

89%

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

78%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 thorough, highly actionable CLI skill with strong progressive disclosure and explicit safety/validation gates for destructive and send operations. The main weakness is conciseness: the confirmation-before-send and draft-default rules are restated several times across sections, inflating the token budget without adding new information.

Suggestions

State the '默认存草稿 / --confirm-send 发送前需用户确认' rule once in the security section and reference it from the workflow and shortcut table instead of restating the full rule in each location.

Trim core-concept definitions that restate the obvious (e.g. what a folder or label is) to just the Lark-specific identifiers and behaviors (message_id, thread_id, built-in folder/label IDs).

Deduplicate the shortcut table's repeated 'save as draft (default). Use --confirm-send to send immediately after user confirmation' phrasing by noting the default once and keeping only per-shortcut differences.

DimensionReasoningScore

Conciseness

Mostly efficient and information-dense, but the send-confirmation rule and '默认存草稿 / --confirm-send' phrasing are repeated across the security rules, typical-workflow, command-selection, and shortcut-table sections, and a few core-concept definitions (folder/label) state the obvious — could be tightened.

3 / 5

Actionability

Fully executable, copy-paste-ready CLI commands throughout (e.g. `lark-cli mail +send --to alice@example.com --subject '周报' --body '…'`) plus a concrete schema→flag mapping table and worked GET/POST examples covering the common native-API cases.

5 / 5

Workflow Clarity

Clear sequenced processes (11-step typical workflow, 3-step native-API procedure) with explicit validation/feedback loops for destructive and batch ops (confirmation previews with affected counts, send_status delivery verification, the triage→preview→confirm→trash example); the main workflow list reads more as a feature tour than an inline-checkpointed process, a minor gap.

4 / 5

Progressive Disclosure

Clear overview structure with well-signaled one-level-deep references — a shortcuts table and 常用操作速查 link each operation to its references/*.md file, bulk detail is delegated to 28 reference files and assets/templates/, and sampled referenced paths are real.

5 / 5

Total

17

/

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 strong, well-crafted trigger description: it states the domain, enumerates concrete natural trigger phrases with synonyms, gives explicit 'Use when' guidance, and carves out negative scope to avoid collision with related skills. No fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete mail actions (起草/写/草稿/发送/回复/转发/查阅/看/搜索邮件, folders, labels, contacts, watch, rules) — comprehensive coverage of the mail domain rather than vague language.

5 / 5

Completeness

Explicitly answers both what (飞书邮箱 + listed operations) and when ('Use when user mentions …') with concrete trigger phrases, and adds negative scope ('Do not use for docs/sheets/calendar…').

5 / 5

Trigger Term Quality

Comprehensive natural terms users would say, including synonyms (写邮件/起草邮件/草稿, 看邮件/查阅邮件) plus the English 'mail/email intent' fallback; mail has no file extension so the synonym coverage is the relevant signal.

5 / 5

Distinctiveness Conflict Risk

Clear niche (Lark mail only) with explicit disambiguation against sibling skills ('Do not use for docs/sheets/calendar/auth setup/pure contact lookup/IM chat tasks'), 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

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
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.