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".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

80%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, highly actionable reference whose concrete config and commands are excellent, but it is structurally weakened by orphaned bundle files and missing validation checkpoints around destructive operations. Splitting inline deep-dives into the existing references and adding verify steps would lift both weak dimensions.

Suggestions

Add explicit validation/verification checkpoints after destructive or system-changing steps — e.g. after clearing caches, confirm Cursor restarts cleanly and memory drops; after the sysctl change, verify `cat /proc/sys/fs/inotify/max_user_watches` reflects the new value before proceeding.

Replace the inline per-topic deep-dives with one-level-deep links to the existing bundle files (e.g. '## Editor Optimization — see [editor-optimization.md](references/editor-optimization.md)'), so SKILL.md becomes an overview and the orphaned references are actually surfaced.

Add a 'verify the bottleneck is resolved' step at the end of the diagnostic workflow so each branch closes with a feedback loop rather than ending at the fix.

Dimension	Reasoning	Score
Conciseness	The body is packed with Cursor-specific actionable config (settings.json blocks, bash commands, tables) and avoids explaining concepts Claude already knows; despite its length, most tokens earn their place rather than padding.	3 / 3
Actionability	Provides fully executable, copy-paste-ready guidance — complete settings.json keys, 'rm -rf' cache paths, sysctl commands, and per-extension mitigations with exact thresholds — rather than abstract direction.	3 / 3
Workflow Clarity	The diagnostic decision-tree gives a clear sequence, but verification checkpoints are absent and destructive/batch operations (rm -rf cache dirs, editing /etc/sysctl.conf) have no validate-then-retry feedback loop, which caps the score at 2.	2 / 3
Progressive Disclosure	The body has section structure, but ten per-topic reference bundle files exist (editor-optimization, indexing-optimization, etc.) and none are referenced or signaled, while the content that belongs in them is dumped inline in a ~310-line monolith.	2 / 3
	Total	10 / 12 Passed

Description

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.

A strong, third-person description that pairs concrete capabilities with an explicit trigger clause of natural user keywords. It cleanly answers both what the skill does and when to invoke it with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'reduce memory usage, speed up indexing, tune AI features, and manage extensions' — matching the multi-action anchor rather than the single-domain score-2 example.	3 / 3
Completeness	Explicitly answers what ('Optimize Cursor IDE performance: reduce memory usage...') and when via an explicit 'Triggers on...' clause equivalent to a 'Use when' trigger, satisfying both halves.	3 / 3
Trigger Term Quality	Natural user phrases like 'cursor slow', 'speed up cursor', and 'cursor lag' give good coverage of terms a user would actually say, beyond generic jargon.	3 / 3
Distinctiveness Conflict Risk	The Cursor-specific niche and 'cursor ...' trigger phrases make it clearly distinguishable and unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 3022dd3

Reviewed: 2 days 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.