lark-base

飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限、模板中心（多维表格模板分类/列表/搜索）；遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps；文件导入/导出转 lark-drive，认证/授权转 lark-shared。

Quality

96%

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

92%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, actionable skill body: executable commands and examples, clear sequenced workflows with validation checkpoints, and clean progressive disclosure into real reference files. The only minor weakness is a few conceptually restative sentences that slightly inflate token use.

Suggestions

Tighten the "应用模式与 Workspace 心智模型" intro: the ownership-division explanation (Workspace 负责资源归属，App 负责页面和组件，Base 负责数据) restates relationships Claude can infer from the resource model above — consider trimming to the actionable routing rules.

The opening "普通 Base 是数据容器..." paragraph re-explains the Block taxonomy that the subsequent ASCII tree already shows; collapse the prose into the tree to save tokens.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes Claude's competence, with concrete commands and minimal concept explanation, but includes a few explanatory passages (e.g. the Workspace/BaseApp 心智模型 framing) that could be trimmed slightly; not a 5 because some sentences restate conceptual relationships Claude can infer.	4 / 5
Actionability	It provides concrete, copy-paste-ready commands throughout — `+record-list`, `+record-batch-create`, jsonc filter/CellValue examples, and bash snippets with real flags — covering the common cases with executable guidance.	5 / 5
Workflow Clarity	Multi-step processes are clearly sequenced with explicit validation and feedback loops: "更新前先读取现状，每次只修改一个字段", read-modify-write guidance, batch concurrency warning (1254291), and destructive-op guards (form-questions-delete --keep-field).	5 / 5
Progressive Disclosure	The SKILL.md is an overview that points to one-level-deep, well-signaled reference files (e.g. [Workflow](references/lark-base-workflow.md), [Record 查询与分析 SOP](references/lark-base-record-query-and-analysis-sop.md)) which are real files in ./references/, with content appropriately split and easy to navigate.	5 / 5
	Total	19 / 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 tightly written, comprehensive description that covers concrete capabilities, natural trigger phrases, explicit use-when guidance, and clear boundary routing against sibling skills. It avoids fluff and verbosity while remaining highly specific.

Dimension	Reasoning	Score
Specificity	The description enumerates concrete capabilities across the full domain — "建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限、模板中心" — giving comprehensive, specific action coverage rather than vague abstractions.	5 / 5
Completeness	It explicitly answers both "what" (the capability list) and "when" via the concrete trigger clause "遇到 Base/多维表格/bitable... 时使用", plus boundary routing to adjacent skills.	5 / 5
Trigger Term Quality	It includes natural user-facing terms and synonyms plus URL patterns — "Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接" — covering the common ways a user would actually phrase the need.	5 / 5
Distinctiveness Conflict Risk	It carves a clear niche with distinct triggers and explicit conflict avoidance ("BaseApp 不走 lark-apps；文件导入/导出转 lark-drive，认证/授权转 lark-shared"), minimizing mis-trigger risk.	5 / 5
	Total	20 / 20 Passed

Validation

81%

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 — 13 / 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

	Total	13 / 16 Passed

Repository: larksuite/cli
Path: skills/lark-base/SKILL.md
Commit: 6646386

Reviewed: ~19 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.