lark-cli-workflow

Coordinate Lark/Feishu CLI tasks from Codex. Use when a request involves Feishu/Lark docs, wiki, Drive files, Sheets, Base, Calendar, Minutes, IM, Mail, Tasks, Contacts, Slides, whiteboards, approvals, attendance, or when a Lark URL/token must be read, edited, summarized, routed, or turned into a real work artifact.

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

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.

A well-crafted thin routing skill: tightly organized sections, lean token usage, and concrete per-domain routing and safety rules with named commands and flags. The main gap is that command guidance is mostly flag/command fragments rather than complete executable invocations, and the high-risk dry-run checkpoint is prescribed without showing how to perform it.

Suggestions

Include one or two complete example command lines (e.g. a full lark-cli docs fetch with --as user and --api-version v2) so the common read path is copy-paste ready rather than assembled from fragments.

Show how to perform the recommended dry run for high-risk actions (e.g. the exact flag or command form for a delete/permission change dry run) so the safety checkpoint is executable rather than only stated.

Add a brief note on how to detect that a URL is a wiki node wrapper versus a direct object token (e.g. URL shape), since the unwrap step currently assumes that recognition.

Dimension	Reasoning	Score
Conciseness	Lean bullet-style routing guidance with no concept explanation; every line adds non-obvious domain knowledge (token semantics, identity choice, repo safety rules). Matches the lean-and-efficient anchor; nothing to trim without losing information.	5 / 5
Actionability	Concrete guidance throughout: exact flags and commands ("docs +fetch --api-version v2", "--as user", "--as bot", "auth login --scope ...") and specific object/action mappings per skill. Not 5 because few complete copy-paste command invocations are shown — the exact command shapes are deferred to the routed lark-* skills.	4 / 5
Workflow Clarity	Clear three-step Default Route, a validation checkpoint for high-risk actions ("need explicit intent or a dry run first"), an error-recovery loop for missing scopes ("follow the CLI hint and request the minimum needed auth login --scope ..."), and a Completion Check checklist — so the destructive-operation cap does not apply. Not 5 because the dry-run step is stated as policy without showing how to execute it.	4 / 5
Progressive Disclosure	Single-file skill (~55 lines) with no bundle files and no external content needed; sections are well-organized and navigation to the routed lark-* skills is clearly signaled by name. Fits the well-organized-sections exception for compact skills.	5 / 5
	Total	18 / 20 Passed

Description

95%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 strong description: it explicitly states both what the skill does and when to use it, with near-exhaustive natural trigger terms covering all Lark/Feishu product surfaces and both platform names. The only soft spot is that the primary action ('Coordinate CLI tasks') is more abstract than the concrete per-product actions that follow it.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ("must be read, edited, summarized, routed, or turned into a real work artifact") over a specific domain. Not 5 because the headline action "Coordinate Lark/Feishu CLI tasks" is abstract and per-object action coverage is thin; not 3 because multiple specific actions are explicitly listed, matching the minor-gaps anchor.	4 / 5
Completeness	Explicitly answers both: what ("Coordinate Lark/Feishu CLI tasks from Codex") and when ("Use when a request involves Feishu/Lark docs, wiki, Drive files, Sheets, Base, Calendar...") with concrete trigger phrases. Matches the 5 anchor exactly; nothing below fits since both elements are explicit.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including the Lark/Feishu synonym pair and every product surface users would name (docs, wiki, Drive files, Sheets, Base, Calendar, Minutes, IM, Mail, Tasks, Contacts, Slides, whiteboards, approvals, attendance) plus Lark URL/token phrasing. Clearly matches the comprehensive anchor.	5 / 5
Distinctiveness Conflict Risk	A clear niche scoped to Feishu/Lark with distinct triggers; generic terms (docs, Sheets, Calendar) are all qualified by "Feishu/Lark", minimizing overlap with generic document or spreadsheet skills. Fits the minimal-conflict anchor.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: huangruiteng/CS-Notes
Path: .codex/skills/lark-cli-workflow/SKILL.md
Commit: 77c775d

Reviewed: 1 day 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.