lark-workflow-meeting-summary

会议纪要整理工作流：汇总指定时间范围内的会议纪要并生成结构化报告。当用户需要整理会议纪要、生成会议周报、回顾一段时间内的会议内容时使用。

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

86%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 well-structured workflow skill with highly actionable commands, clear sequencing, and strong feedback loops for permission and missing-artifact cases. The main gap is the absence of an explicit final validation/completeness check for the batch aggregation.

Suggestions

Add a final verification step in Step 4 (e.g., confirm the count of summarized meetings equals the searched meeting count, and explicitly list any meetings skipped as '无纪要') to close the batch-validation gap.

Trim minor filler such as '学习命令使用方式' and '你更佳擅长解析 JSON 数据' to lift conciseness to a 5.

Make the time-range splitting rule in Step 2 an explicit checkpoint (split >1 month into monthly sub-queries, then assert all sub-results merged) so the batch sequence is fully self-checking.

Dimension	Reasoning	Score
Conciseness	Dense, technical content with concrete parameters and limits that assumes Claude's competence; only minor over-explanation (e.g. "你更佳擅长解析 JSON 数据", "学习命令使用方式") keeps it just below a 5.	4 / 5
Actionability	Provides copy-paste-ready executable commands with real flags and placeholders for every step (vc +search, vc +detail, note +detail, drive metas batch_query, docs +create/+update) plus the fallback minutes path, covering the common cases.	5 / 5
Workflow Clarity	A clear 5-step sequence with a diagram and explicit checkpoints (page_token pagination, 50-meeting/10-doc batching, permission retry loop, missing-note_id fallback); it is not a 5 because there is no explicit final completeness/verification check after the batch aggregation.	4 / 5
Progressive Disclosure	The SKILL.md is a concise overview that pushes command semantics and scene detail to clearly signaled one-level-deep references (lark-shared, lark-meeting, lark-doc, scene docs, command reference files) in a dedicated 参考 section, with easy navigation.	5 / 5
	Total	18 / 20 Passed

Description

78%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 description that clearly states what the workflow does and when to use it, with natural trigger phrases. It could list more concrete sub-actions to lift specificity and add synonyms to reduce overlap with the sibling meeting skill.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ("汇总指定时间范围内的会议纪要" and "生成结构化报告"), matching the 1-2 concrete actions anchor; it is not a 4 because coverage is not broader than these two actions.	3 / 5
Completeness	Explicitly states both the what ("汇总...会议纪要并生成结构化报告") and the when with a concrete trigger clause ("当用户需要...时使用"), matching the clear-what-and-when anchor.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ("整理会议纪要", "生成会议周报", "回顾一段时间内的会议内容") with good coverage; it is not a 5 because some synonyms/variants (e.g. "会议总结", "会议回顾") are absent.	4 / 5
Distinctiveness Conflict Risk	The time-range aggregation / weekly-report niche is mostly distinct with specific triggers, but there is minor overlap risk with the sibling lark-meeting skill that also handles meeting content review, so it is not a 5.	4 / 5
	Total	16 / 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: 17 suspicious	Warning

	Total	12 / 16 Passed

Repository: larksuite/cli
Path: skills/lark-workflow-meeting-summary/SKILL.md
Commit: 6646386

Reviewed: ~20 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.