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

89%

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

86%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.

The content is a lean, well-structured shared-rules base that encodes critical non-obvious contract and safety gotchas with concrete flags and a clear reference routing table. Weakness is actionability at the directive level rather than full executable command blocks, and workflow clarity is shaped by its role as a routing base rather than a single cohesive procedure.

Suggestions

Add 1-2 complete example command invocations (e.g. a full 'lark-cli auth qrcode --output qr.png' line) to lift actionability from directive-level to copy-paste-ready.

Optionally include a short canonical end-to-end auth-login sequence with an explicit validation checkpoint to strengthen workflow_clarity beyond the routing-table form.

Consider adding one-line purpose summaries to the reference trigger table rows so the destination of each link is clear before reading.

Dimension	Reasoning	Score
Conciseness	The body is dense with non-obvious contract gotchas (ok==true vs code==0, exit code 10 as a confirmation gate, relative-path-only constraints) and assumes Claude's competence — no basic-concept padding, and every directive carries actionable signal.	5 / 5
Actionability	Gives concrete executable guidance via specific commands and flags ('lark-cli auth qrcode', '--format json', '--dry-run', '--domain', exit code 10) and exact JSON fields (ok/code/msg/error), but stops at directive-level rather than full copy-paste command examples.	4 / 5
Workflow Clarity	The high-risk approval flow is explicitly sequenced with a checkpoint (exit 10 → confirm intent → append flag → retry) and the reference trigger table gives ordered reading, but as a shared rules base it lacks a single end-to-end multi-step workflow with full feedback loops.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview that signals five one-level-deep references (all verified to exist) via a clear 'strong-trigger index' table mapping conditions to files, making navigation easy and keeping detail out of the base.	5 / 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.

The description is specific, well-triggered, and clearly distinguishes the skill's niche; it answers both what and when with concrete, mostly-natural terms. Main weakness is a slightly technical bias in trigger phrasing that omits a few user-level synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'auth login/status/logout', 'user vs bot identity', 'business-domain permissions (--domain, including all/docs/drive)', 'missing scopes', 'revoking authorization', 'handling _notice JSON' — covering the skill's scope comprehensively rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both 'what' (the enumerated setup/auth tasks) and 'when' via the leading 'Use for lark-cli setup/auth tasks' trigger clause with concrete trigger phrases, in third-person imperative voice.	5 / 5
Trigger Term Quality	Strong natural/technical trigger terms a lark-cli user would actually say ('auth login/status/logout', 'missing scopes', 'revoking authorization', '_notice JSON', '--domain'), but coverage leans technical and omits a few common synonyms/variations.	4 / 5
Distinctiveness Conflict Risk	Scoped tightly to 'lark-cli setup/auth' with highly specific triggers (--domain, _notice JSON, missing scopes), giving it a clear niche with minimal overlap risk against unrelated 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: ceace6d

Reviewed: 4 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.