lark-minutes

飞书妙记：搜索妙记、查看妙记基础信息、下载/上传音视频、读取或编辑妙记的产物内容、改标题、替换说话人/关键词、申请妙记查看/编辑权限。当给出minute_token、本地音视频文件，要查/改/转妙记产物，或用户明确要主动申请妙记权限时使用；本地音视频转纪要/逐字稿优先走本 skill，不要用 ffmpeg/whisper 本地转写。不负责：获取会议关联妙记，或仅按自然语言标题定位纪要

Quality

92%

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

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and well-structured with clear workflows, validation checkpoints, and a strong progressive-disclosure design backed by real reference files. Its only weakness is mild redundancy between the SKILL.md routing tables and the reference docs, which slightly inflates the token budget.

Suggestions

Reduce duplication: the +upload three-step flow and the 'no ffmpeg/whisper' rule are stated both in SKILL.md and lark-minutes-upload.md; consolidate to one canonical location and link the other.

The 意图路由 table and the Shortcut table overlap on several rows (e.g. speaker-replace, summary, todo); consider merging or pruning rows that merely restate reference-file triggers to tighten the overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient (tables, code blocks, tight routing) but contains repeated steering content — the +upload flow and 'no ffmpeg/whisper' guidance appear in both the body and references, and routing tables restate several reference triggers, so it could be tightened. It is not padded with concepts Claude already knows, but it is not fully lean.	2 / 3
Actionability	Provides concrete, copy-paste-ready commands throughout (e.g. 'lark-cli minutes +detail --minute-tokens <token> --summary --todo --chapter --keyword --transcript', the --todos JSON batch example, the speakerlist GET), with specific flags and JSON shapes — fully executable guidance.	3 / 3
Workflow Clarity	Multi-step processes are explicitly sequenced with validation checkpoints: the upload flow (drive +upload → +upload → +detail --wait-ready), '先读后写' before todo/summary edits, and error-feedback loops (permission_denied, not_found) with recovery steps. Destructive/batch operations have explicit read-before-write and error handling.	3 / 3
Progressive Disclosure	Clear overview with well-signaled one-level-deep references — each Shortcut maps to a real file in references/ (verified: detail, download, search, speaker-replace, summary, todo, update, upload all exist), with the SKILL.md acting as a routing hub and detailed content pushed to the reference files. Navigation is easy and references do not nest beyond one level.	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 concrete and comprehensive, listing specific capabilities alongside explicit 'use when' triggers and a clear negative-scope boundary. Voice is third-person imperative, fully satisfying the rubric. It is dense but not padded.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — '搜索妙记、查看妙记基础信息、下载/上传音视频、读取或编辑妙记的产物内容、改标题、替换说话人/关键词、申请妙记查看/编辑权限' — each tied to a discrete capability, matching the anchor that lists multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both 'what' (the enumerated capabilities) and 'when' via '当给出minute_token、本地音视频文件，要查/改/转妙记产物，或用户明确要主动申请妙记权限时使用', plus negative scope ('不负责...'), matching the anchor for clearly answering both what AND when with explicit triggers.	3 / 3
Trigger Term Quality	Uses natural phrasing users would say ('搜索妙记','改标题','替换说话人/关键词','申请妙记权限','本地音视频转纪要/逐字稿') and concrete tokens like 'minute_token' and file types, giving good coverage of real trigger terms.	3 / 3
Distinctiveness Conflict Risk	The skill carves a clear niche (飞书妙记/Minutes), redirects away from competing tools ('不要用 ffmpeg/whisper','不负责：获取会议关联妙记...定位纪要'), so it is unlikely to trigger for the wrong skill.	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: 15 suspicious	Warning

	Total	12 / 16 Passed

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

Reviewed: 1 day 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.