CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ui-review

Publish a Storybook review that shows the user the stories a UI change affects, or the components and stories they ask to see.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 lean, highly operational body: concrete commands, explicit approval conditions, correct-directory and sandbox guidance, and an exact end-state specification, with no padding or concept re-explanations. The only soft spot is that the downstream review-publishing commands are delegated to the CLI's own output rather than stated inline, which leaves a minor actionability gap.

DimensionReasoningScore

Conciseness

Every paragraph carries operational instructions (install/version prerequisites, working directory, sandbox escalation, the exact npx command, final-answer format) with zero concept explanations. Not 5 because minor clauses could be trimmed — the prerelease version-pattern enumeration ("11.0.0-alpha.x, -beta.x or -rc.x", "0.0.0-pr-*") and the parenthetical "(for example, it finds no free port to bind to)" slightly exceed what is strictly needed; not 3 because there is no genuinely unnecessary explanation.

4 / 5

Actionability

Concrete, copy-paste-ready commands are given ("npx storybook skills ui-review", "/storybook-init", "/storybook-upgrade") with precise execution details (run from the Storybook package directory, no head/tail, end with the three lines "review create" prints). Not 5 because the commands that actually find affected stories and publish the review are delegated to the CLI's dynamic output rather than stated inline, leaving a minor explicitness gap; not 3 because nothing is pseudocode or high-level hand-waving.

4 / 5

Workflow Clarity

A short single-purpose skill under 50 lines with an unambiguous core action: check numbered prerequisites (with explicit approval conditions), run the skill command from the correct directory, follow its output, and format the final answer exactly. Conditional branches (sandbox escalation, init/upgrade approval) are each clearly specified, and no destructive or batch operation requires a validation loop, so the simple-skill exception applies. Not 4 because there are no actual sequence or checkpoint gaps.

5 / 5

Progressive Disclosure

A 17-line body with no bundle files and no need for external references: the numbered Prerequisites list plus short operational paragraphs fully organize the content. The only cross-references (/storybook-init, /storybook-upgrade) are one-level, clearly signaled skill invocations. Per the rubric's simple-skill guidance, this earns a 5.

5 / 5

Total

18

/

20

Passed

Description

70%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 concise, third-person description with a clear niche and strong natural keywords (Storybook, review, stories, components, UI change). Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness, and it misses a few trigger synonyms such as 'preview'.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user makes a UI or component change and wants to see which stories it affects, or asks to preview or review specific components and stories in Storybook."

Include natural synonyms such as 'preview changes', 'visual review', or 'show me the affected stories' to broaden trigger-term coverage.

Mention the monorepo/CI context if relevant (e.g. 'when working in a package with Storybook stories') to sharpen the 'when' further.

DimensionReasoningScore

Specificity

"Publish a Storybook review that shows the user the stories a UI change affects, or the components and stories they ask to see" names the domain and several concrete behaviors (publish review, surface affected stories, honor requested components) with no gaps for this single-purpose skill. Not 5 because it does not enumerate multiple distinct operations like the comprehensive anchor example; not 3 because coverage of the skill's scope is complete rather than partial.

4 / 5

Completeness

The 'what' is clear (publish a Storybook review showing affected or requested stories), but there is no explicit 'Use when...' clause; the 'when' is only weakly implied via "a UI change affects" and "they ask to see". Per the guideline, a missing explicit trigger clause caps completeness at 3; it is not 4 because the 'when' is never stated on its own.

3 / 5

Trigger Term Quality

Natural terms users would say are present: "Storybook", "review", "stories", "components", "UI change". Not 5 because synonym variations users might use ("preview", "visual review", "review my changes") and phrasing around asking to see components are not covered; not 3 because the core natural vocabulary is all there.

4 / 5

Distinctiveness Conflict Risk

"Storybook review" carves out a clear niche with distinct triggers; a user mentioning Storybook, stories, or reviewing a UI change would land here and not on sibling skills like storybook-init or storybook-upgrade. It is not 4 because no meaningful overlap risk with related skills is apparent in the text.

5 / 5

Total

16

/

20

Passed

Validation

100%

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

storybookjs/storybook

Path

code/lib/claude-plugin/skills/ui-review/SKILL.md

Reviewed

Table of Contents

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.