lark-skill-maker

创建 lark-cli 的自定义 Skill。当用户需要把飞书 API 操作封装成可复用的 Skill（包装原子 API 或编排多步流程）时使用。

Quality

66%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/lark-skill-maker/SKILL.md

Quality

Content

71%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 compact, actionable meta-skill that teaches how to build lark-cli skills with concrete command forms and a usable template. Its main weakness is progressive disclosure — there is almost no bundle to structure — and the template placeholders keep actionability just short of fully executable.

Suggestions

Add a concrete, runnable example of a finished generated SKILL.md (with real path, real scope, and a working api call) alongside the placeholder template to push actionability to 5.

Either move detailed scope/permission tables or shortcut reference lists into a references/ file linked from the body, or explicitly state that no bundle is needed so the structure is intentional — this clarifies progressive disclosure.

Strengthen workflow validation by adding an explicit 'verify the generated skill runs end-to-end (e.g. lark-cli <service> <resource> <method> --dry-run)' checkpoint in the creation flow.

Dimension	Reasoning	Score
Conciseness	The body is lean, focused on CLI commands and a template, and avoids explaining concepts Claude already knows; only minor phrasing could be trimmed further.	4 / 5
Actionability	Provides concrete, executable lark-cli command forms and a copy-paste-ready SKILL.md template with example API calls; the template body uses placeholder '{...}' and 'xxx' which keeps it slightly below fully executable.	4 / 5
Workflow Clarity	The 调研 API section gives a clear 1-2-3 sequence and the template shows multi-step orchestration with data-passing comments and a 安全 'dry-run / confirm' checkpoint; the cap that would limit destructive skills to 3 is avoided by the explicit confirm/dry-run guidance, but full validation feedback loops are only lightly signaled.	4 / 5
Progressive Disclosure	Content is well sectioned for an under-50-line skill, but the only external reference is a sibling ../lark-openapi-explorer/SKILL.md link; no references/, scripts/, or assets/ bundle exists, so there is little actual multi-file structure to reward, and the openapi-explorer pointer is one-level-deep but lightly signaled.	3 / 5
	Total	15 / 20 Passed

Description

62%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.

The description clearly states what the skill does and provides an explicit 'Use when' trigger, placing it above the midpoint. It is held back by modest specificity and limited trigger-term coverage rather than lacking either axis.

Suggestions

Add 2-3 concrete action verbs (e.g. '包装原子 API、编排多步流程、生成权限表') to lift specificity toward score 5.

Broaden trigger keywords with natural user phrases and synonyms (e.g. '飞书/Lark 接口、调用 API、Skill 封装、把命令做成 Skill').

Dimension	Reasoning	Score
Specificity	Names the domain (lark-cli custom Skill) and one concrete action ('封装飞书 API 操作成可复用 Skill'), but does not enumerate multiple specific actions or distinguish wrapping atomic APIs from multi-step orchestration beyond a parenthetical.	3 / 5
Completeness	Both 'what' (创建 lark-cli 的自定义 Skill) and 'when' (当用户需要把飞书 API 操作封装成可复用的 Skill 时使用) are present, though the 'when' clause is somewhat narrow and could name more specific trigger scenarios.	4 / 5
Trigger Term Quality	Contains the natural trigger phrase '当用户需要...时使用', but keywords are limited to '飞书 API 操作' and 'Skill' with few common synonyms or variations a user might actually say.	3 / 5
Distinctiveness Conflict Risk	The lark-cli / 飞书 API niche is fairly distinct and unlikely to overlap with unrelated skills, though a sibling skill like lark-openapi-explorer covers adjacent territory creating minor overlap risk.	4 / 5
	Total	14 / 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: 2 suspicious	Warning

	Total	12 / 16 Passed

Repository: larksuite/cli
Path: skills/lark-skill-maker/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.