storybook-upgrade

Upgrade Storybook to a specific version (canary or release). Use this when upgrading Storybook packages in an external app, reproduction, or test project.

Quality

80%

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

87%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 exemplary in conciseness, actionability, and organization for a simple single-purpose skill, with copy-paste examples and clear constraints. The single weakness is the absence of validation or verification steps for what is a batch package-upgrade operation.

Suggestions

Add an explicit validation step after upgrading (e.g., 'Run the project's build/test or `npx storybook doctor` to confirm packages resolved and the app still builds') to turn the batch upgrade into a verified workflow and lift workflow_clarity above 3.

Include a brief error-recovery note for when the upgrade reports peer-dependency conflicts or version mismatches, giving the workflow a feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean, avoids explaining what Storybook is or how package managers work, and every section (Usage, Examples, What it does, Important) earns its place; for a sub-50-line simple skill this matches the 'lean and efficient, every token earns its place' anchor.	5 / 5
Actionability	Provides a fully executable base command (`npx storybook@<VERSION> upgrade`) plus three copy-paste examples (canary, latest, specific release) that cover the common cases, matching the 'fully executable, copy-paste ready, covers common cases' anchor.	5 / 5
Workflow Clarity	The 'What it does' list describes the tool's behavior rather than a validated user workflow, and upgrading all @storybook/* packages is a batch operation with no verification/error-recovery checkpoints, so per the destructive/batch cap workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	No bundle files are needed and the sub-50-line body is cleanly organized into well-signaled sections (Why, Usage, Examples, What it does, Important), satisfying the simple-skill exception that lets progressive disclosure score 5 on well-organized sections alone.	5 / 5
	Total	18 / 20 Passed

Description

73%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 concise, domain-specific, and answers both what it does and when to use it with low conflict risk. Its main limitation is that the 'when' clause reads as usage context rather than natural user trigger phrases, and it lists a single concrete action rather than multiple.

Suggestions

Add concrete user-trigger phrasing to the 'when' clause (e.g., 'Use when the user asks to upgrade or migrate Storybook, bump Storybook versions, or test a canary build') to push completeness toward 5.

Expand the action list slightly (e.g., 'upgrade all @storybook/* packages and resolve peer dependencies') to lift specificity from a single action toward several concrete actions.

Dimension	Reasoning	Score
Specificity	Names the Storybook domain and one concrete action ('Upgrade Storybook to a specific version') with canary/release qualifiers, but does not enumerate multiple distinct actions, fitting the '1-2 concrete actions' anchor rather than the 'several specific actions' level above.	3 / 5
Completeness	Provides a clear 'what' and an explicit 'Use this when...' clause listing contexts, but the 'when' is framed as usage contexts rather than concrete user-utterance trigger phrases, so it does not reach the explicit-trigger-phrases anchor of 5.	4 / 5
Trigger Term Quality	Includes natural terms like 'Upgrade Storybook', 'canary', 'release', and 'Storybook packages', giving good keyword coverage, though it misses common synonyms or extension-style triggers that would warrant a 5.	4 / 5
Distinctiveness Conflict Risk	Scoped to a single narrow tool (Storybook upgrade) with distinct, specific triggers, giving it a clear niche with minimal overlap risk with other skills.	5 / 5
	Total	16 / 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: storybookjs/storybook
Path: .agents/skills/storybook-upgrade/SKILL.md
Commit: 8403f24

Reviewed: about 18 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.