Content
72%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The content is actionable and well-structured for a simple single-purpose skill, with concrete npx commands covering common cases. Its main weakness is the absence of any validation or verification step for a batch package-upgrade operation.
Suggestions
Add a verification step after the upgrade (e.g., check package.json versions are in sync, run `npm ls @storybook/*`, or start Storybook to confirm it boots) to satisfy the batch-operation validation expectation.
Replace or supplement the unfilled <VERSION> placeholder in the Usage block with a one-line note on how to find a valid canary SHA or release version.
Trim the 'What it does' section, which largely restates the intro and the command behavior, to improve token efficiency.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and command-focused, with only minor redundancy between the intro, 'What it does', and 'Why this matters' sections that could be trimmed. | 4 / 5 |
Actionability | Provides concrete executable commands across canary, latest, and specific-release examples, but the primary Usage block uses an unfilled <VERSION> placeholder with no guidance on locating a version/SHA. | 4 / 5 |
Workflow Clarity | A rough sequence is described in 'What it does', but this is a batch operation (upgrades all @storybook/* packages) with no validation or verification checkpoint, capping the score at 3 per the destructive/batch guideline. | 3 / 5 |
Progressive Disclosure | A short single-purpose skill with no bundle files and clear section headers; per the simple-skills note, well-organized sections alone warrant a 5. | 5 / 5 |
Total | 16 / 20 Passed |