lark-shared

Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling _notice JSON.

Quality

90%

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

88%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, dense rule-base with explicit high-risk validation gates and clean one-level reference navigation. Slight actionability and progressive-disclosure gaps (abstract intent-confirmation wording, one unreferenced bundle file) keep it just below top marks.

Suggestions

Add a one-line pointer for lark-wiki-token-routing.md from the trigger index (or remove it) so every bundle file is reachable and none is orphaned.

Replace the abstract "确认用户意图" wording in the write/delete rule with a concrete confirmation prompt template or the specific fields to surface.

Consider one short copy-paste example for the exit-10 retry (argv before/after appending the confirmation flag) to make the high-risk flow fully executable.

Dimension	Reasoning	Score
Conciseness	Dense, lean rule-base with no concept padding; assumes Claude's competence and lets every rule earn its place (e.g., "判断成功用 ok == true" rather than explaining JSON envelopes).	5 / 5
Actionability	Provides concrete commands and decision rules ("lark-cli auth qrcode", "--format json", exit code 10 handling, relative-path-only) but a few rules stay abstract ("确认用户意图") and there are no copy-paste code blocks.	4 / 5
Workflow Clarity	The high-risk approval rule lays out an explicit sequence with a validation gate (stop → confirm action/risk/params → explicit consent → append hint flag to original argv → retry) plus a no-bypass guard, giving clear checkpoints and a feedback loop for destructive ops.	5 / 5
Progressive Disclosure	Clear overview body with a well-signaled trigger-index table linking one-level-deep references that all resolve to real files; the orphaned, unlinked lark-wiki-token-routing.md reference is a minor organization gap.	4 / 5
	Total	18 / 20 Passed

Description

92%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 tight, specific description that clearly states both capabilities and trigger conditions with concrete flag-level detail. Minor synonym coverage gaps keep trigger quality just short of a perfect score.

Dimension	Reasoning	Score
Specificity	Enumerates concrete actions ("auth login/status/logout", "revoking authorization", "handling _notice JSON") and concrete params ("--domain, including all/docs/drive"), giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	The explicit "Use for lark-cli setup/auth tasks: ..." clause states both what the skill does and when to invoke it, with concrete trigger phrases throughout.	5 / 5
Trigger Term Quality	Strong natural keywords ("auth login", "missing scopes", "revoking authorization", "_notice") plus flag names, but a few common synonyms (e.g., plain "login/logout", "token") are absent, placing it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Scoped narrowly to lark-cli auth/identity/permissions/notice handling, forming a clear niche with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	19 / 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-shared/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.