lark-markdown

飞书 Markdown：查看、创建、上传、编辑和比较 Markdown 文件。当用户需要创建或编辑 Markdown 文件、读取、修改、局部 patch 或比较差异时使用。不负责将 Markdown 导入为飞书在线文档，也不负责文件搜索、权限、评论、移动、删除等云空间管理操作。

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

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

A well-organized, concise overview with strong progressive disclosure (real one-level reference files) and clear error/identity decision logic. The one weakness is actionability: the body relies on the shortcut references for full executable syntax, so as standalone content it offers routing rather than copy-paste-ready commands.

Suggestions

Add one minimal copy-paste-ready command example per shortcut in the body (e.g. a one-line `+create` and `+fetch` invocation) so the SKILL.md is actionable without opening every reference file.

Include the `--as user`/`--as bot` flags directly in at least one example command so the identity-selection guidance is executable, not just descriptive.

Consider a one-line note on when to prefer `+patch` vs `+overwrite` (partial vs full replacement) as concrete decision guidance.

Dimension	Reasoning	Score
Conciseness	The 70-line body is lean and assumes Claude's competence — a decision table of trigger-to-command mappings plus core boundaries and a regex-escaping example, with no padding or explanation of concepts Claude already knows. It is not a 2 because nothing reads as unnecessary explanation that could be tightened.	3 / 3
Actionability	The body names specific commands (`lark-cli markdown +create/+fetch/+patch/+overwrite/+diff`) and flags, but the only complete executable example is the regex-escaping snippet; most operational detail and full command syntax live in the shortcut reference files rather than inline, leaving it somewhat incomplete as standalone guidance.	2 / 3
Workflow Clarity	Decision logic is explicit and sequential: identity selection (`--as user`/`--as bot`) with auth precondition, trigger-to-command routing, an error-handling rule (stop-and-handle for scope/permission/not-found/quota vs. limited backoff for rate_limit/server_error), and the patch semantic (download→local-replace→overwrite) with an empty-result guard. Checkpoints for the risky overwrite/patch operations are present.	3 / 3
Progressive Disclosure	Clear overview with well-signaled, one-level-deep references — a shortcuts table links to five real files (lark-markdown-{create,diff,fetch,patch,overwrite}.md), all of which exist, and the SKILL.md itself stays a concise overview rather than inlining their detail.	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.

A strong, third-person description that names concrete actions, gives explicit use-when triggers, and sharply distinguishes itself from sibling skills via explicit exclusions. No first/second-person voice or vague fluff is present.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "查看、创建、上传、编辑和比较" plus "读取、修改、局部 patch" — matching the anchor for enumerating several specific operations rather than just naming a domain.	3 / 3
Completeness	Explicitly answers both what (查看/创建/上传/编辑/比较) and when ("当用户需要创建或编辑 Markdown 文件、读取、修改、局部 patch 或比较差异时使用"), satisfying the explicit 'Use when...' trigger requirement.	3 / 3
Trigger Term Quality	Natural phrasings a user would actually say appear throughout — "创建或编辑 Markdown 文件", "读取、修改", "局部 patch", "比较差异" — with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The exclusion clause ("不负责将 Markdown 导入为飞书在线文档，也不负责文件搜索、权限、评论、移动、删除等云空间管理操作") carves out a clear niche and prevents overlap with lark-drive, making wrong-skill triggering unlikely.	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: 6 suspicious	Warning

	Total	12 / 16 Passed

Repository: larksuite/cli
Path: skills/lark-markdown/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.