lark-vc

飞书视频会议：搜索历史会议记录、查询会议纪要（总结/待办/章节/逐字稿）、查询参会人快照。当用户查询已结束的会议、获取会议产物（纪要/妙记）、查看参会人时使用；查询未来日程走 lark-calendar。不负责：Agent 真实入会/离会、会中实时事件（走 lark-vc-agent）。

Quality

92%

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

Quality

Content

85%

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, actionable overview of a complex multi-product domain, with executable commands, clear routing/decision tables, and properly disclosed references. Its main weakness is repetition of the same boundary/selection rules across several sections, which inflates token cost without adding information.

Suggestions

Consolidate the '智能纪要 vs 妙记' selection rule into one canonical location and reference it elsewhere instead of restating it in the intent-routing table, '产物选择决策', and '资源关系' callouts.

Merge the per-domain boundary callouts (MeetingNotes/妙记/Note 域边界) into a single '域边界' section to avoid restating the same deferrals in both '资源关系' and '不在本 skill 范围'.

Consider moving the full selection-decision tables into references/vc-domain-boundaries.md and keeping only the routing summary in SKILL.md to further trim the always-loaded surface.

Dimension	Reasoning	Score
Conciseness	Mostly dense and domain-specific, but the smart-note-vs-minutes selection rule and domain boundaries are restated across the intent-routing table, '产物选择决策', the '资源关系' boundary callouts, and '不在本 skill 范围' — material that could be consolidated.	2 / 3
Actionability	Concrete, copy-paste-ready lark-cli invocations throughout ('vc +search', 'vc meeting get --with-participants', 'docs +fetch', 'drive metas batch_query') with realistic --params JSON and inline schema-learning commands.	3 / 3
Workflow Clarity	Core scenarios are numbered and sequenced (search → detail → note routing) with explicit checkpoints like paginating multi-result searches and the note_display_type routing rule; the selection tables function as decision checklists.	3 / 3
Progressive Disclosure	SKILL.md is an overview with clearly signaled one-level-deep references to four real bundle files (lark-vc-search/detail/recording.md, vc-domain-boundaries.md) plus cross-skill SKILL.md links; content is appropriately split rather than monolithic.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 concise, specific, and self-boundaried: it states three concrete capabilities, gives an explicit 'use when' trigger, and disambiguates against two adjacent skills. It fully satisfies the what/when/which-skill criteria with no padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '搜索历史会议记录、查询会议纪要（总结/待办/章节/逐字稿）、查询参会人快照' — naming specific deliverables rather than vague verbs.	3 / 3
Completeness	Explicitly answers both what (the three query actions) and when — '当用户查询已结束的会议、获取会议产物（纪要/妙记）、查看参会人时使用' — with an explicit trigger clause.	3 / 3
Trigger Term Quality	Covers natural phrasings users would say: '已结束的会议', '会议纪要', '参会人', '总结/待办/章节/逐字稿', '会议产物'.	3 / 3
Distinctiveness Conflict Risk	Carves a clear niche and explicitly defers overlapping cases to siblings ('查询未来日程走 lark-calendar'; '不负责：Agent 真实入会/离会、会中实时事件（走 lark-vc-agent）'), minimizing wrong-skill triggering.	3 / 3
	Total	12 / 12 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: 36 suspicious	Warning

	Total	12 / 16 Passed

Repository: larksuite/cli
Path: skills/lark-vc/SKILL.md
Commit: a7865cd

Reviewed: about 23 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.