Content
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill functions as a well-organized catalog/index of 70 React and Next.js performance rules, with clear prioritization and categorization. However, it critically lacks actionable content — there are no code examples, no concrete implementation patterns, and no executable guidance within the skill itself. All substantive content is deferred to external rule files that are not provided in the bundle, making the skill essentially a table of contents without the book.
Suggestions
Add at least one concrete, executable code example per category (especially for CRITICAL categories like Eliminating Waterfalls and Bundle Size) showing the anti-pattern and the correct pattern inline.
Include the bundle rule files (e.g., rules/async-parallel.md, rules/bundle-barrel-imports.md) or at minimum provide the AGENTS.md compiled document so the referenced content actually exists.
Add a brief workflow section for how to apply these rules during code review or refactoring, including validation steps (e.g., 'Run bundle analyzer before/after to verify size reduction').
Trim the exhaustive rule listing — consider showing only the top 2-3 rules per category inline and deferring the full list to a reference file, which would improve conciseness while maintaining discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly a catalog/index of 70 rules, which is useful as a reference, but the extensive listing of every rule name with one-line descriptions is quite long. The 'When to Apply' section explains obvious triggers Claude could infer. However, the table format and categorization add structure that justifies much of the length. | 2 / 3 |
Actionability | The skill provides no executable code, no concrete examples, and no specific implementation guidance. It is essentially a table of contents listing rule names with brief descriptions, deferring all actual actionable content to external rule files. Claude cannot act on 'async-parallel - Use Promise.all() for independent operations' without the referenced files. | 1 / 3 |
Workflow Clarity | The priority ordering provides a clear sequence for which optimizations to tackle first, and the 'When to Apply' section gives trigger conditions. However, there are no validation steps, no feedback loops for verifying performance improvements, and no process for how to apply multiple rules during a refactoring session. | 2 / 3 |
Progressive Disclosure | The skill references individual rule files (e.g., 'rules/async-parallel.md') and a compiled 'AGENTS.md', which is good progressive disclosure structure. However, no bundle files are provided, so the referenced files don't actually exist, making the references non-functional. The SKILL.md itself is also quite long for what is essentially an index. | 2 / 3 |
Total | 7 / 12 Passed |