cursor-performance-tuning
Optimize Cursor IDE performance: reduce memory usage, speed up indexing, tune AI features, and manage extensions for large codebases. Triggers on "cursor performance", "cursor slow", "cursor optimization", "cursor memory", "speed up cursor", "cursor lag".
89
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates specific capabilities (memory reduction, indexing speed, AI feature tuning, extension management) for a well-defined niche (Cursor IDE performance). The explicit trigger terms cover natural user language variations effectively, and the description is concise without unnecessary padding. It uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'reduce memory usage', 'speed up indexing', 'tune AI features', and 'manage extensions for large codebases'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (optimize Cursor IDE performance via memory, indexing, AI features, extensions) and 'when' (explicit trigger terms listed with 'Triggers on' clause). The trigger guidance is explicit and well-defined. | 3 / 3 |
Trigger Term Quality | Includes excellent natural keywords users would actually say: 'cursor performance', 'cursor slow', 'cursor optimization', 'cursor memory', 'speed up cursor', 'cursor lag'. These cover common variations of how users would describe performance issues with Cursor IDE. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a specific IDE (Cursor) with specific performance optimization concerns. The trigger terms are all Cursor-specific, making it very unlikely to conflict with general IDE or performance skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with excellent diagnostic workflow structure and concrete, copy-paste ready configurations. Its main weakness is length—the document packs a lot of detail inline that could be split into referenced files for better progressive disclosure. The content is mostly efficient but has some sections (enterprise considerations, basic explanations of built-in tools) that add marginal value.
Suggestions
Split the detailed .cursorignore template, extension audit table, and cache management commands into separate reference files, keeping only summaries and links in the main SKILL.md.
Remove or significantly trim the Enterprise Considerations section, which is vague and not directly actionable for Claude assisting a user.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some content that could be tightened—e.g., the enterprise considerations section adds little actionable value, and some explanations (like what Process Explorer shows) are somewhat obvious. However, most content earns its place with concrete settings and commands. | 2 / 3 |
Actionability | Highly actionable throughout: copy-paste ready JSON settings, executable bash commands for cache clearing and monitoring, specific .cursorignore contents, concrete extension mitigation strategies with exact setting keys, and specific command palette actions. | 3 / 3 |
Workflow Clarity | The diagnostic workflow at the top provides a clear decision tree for identifying bottlenecks and routing to the correct section. Each section has clear steps, and the memory monitoring section includes thresholds and remediation steps. The cache management section includes a validation note (restart after clearing, caches rebuild automatically). | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and sections, but it's a long monolithic document (~200+ lines of substantive content) that could benefit from splitting detailed sections (e.g., the full .cursorignore template, extension audit details) into separate reference files. External links are provided at the end but internal progressive disclosure is minimal. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
c8a915c
- 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.