cursor-common-errors

Troubleshoot common Cursor IDE errors: authentication, completion, indexing, API, and performance issues. Triggers on "cursor error", "cursor not working", "cursor issue", "cursor problem", "fix cursor", "cursor crash".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

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, actionable troubleshooting guide with strong conciseness and concrete fixes, weakened by missing validation checkpoints in destructive flows and poor progressive disclosure — bundle files exist but are entirely unreferenced.

Suggestions

Add explicit validation/verify-after steps to destructive operations (e.g., after clearing the index cache or running the reset, instruct to relaunch Cursor and confirm the symptom is gone).

Link the existing reference files (completion-errors.md, indexing-errors.md, performance-errors.md, errors.md, examples.md) from the relevant body sections and move the duplicated detail out of SKILL.md so it serves as an overview.

De-duplicate the inline content against the reference files to avoid maintaining the same fixes in two places.

Dimension	Reasoning	Score
Conciseness	The body is a lean Symptoms/Fix reference that assumes Claude's competence and avoids explaining concepts Claude already knows; tokens largely earn their place, with only minor tightening possible in the enterprise section.	3 / 3
Actionability	Provides concrete, executable guidance throughout — exact command-palette paths, filesystem paths, bash flags (cursor --disable-extensions), settings JSON keys, and allowlist domains — with cause→fix tables mapping to specific resolutions.	3 / 3
Workflow Clarity	Multi-step processes are sequenced with numbered lists and a Step 1–5 diagnosis block, but validation/verification checkpoints are mostly implicit; destructive cache-clearing (rm -rf) lacks an explicit verify-after step, capping clarity at 2.	2 / 3
Progressive Disclosure	Sections are organized, but the ~230-line body is largely monolithic and never references the five provided bundle files in references/, which duplicate content already presented inline; references are neither signaled nor navigated.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 explicitly covers both capability and trigger conditions with natural user phrases. Its only weakness is that it names error categories rather than multiple distinct concrete actions.

Suggestions

Replace or supplement the single verb 'Troubleshoot' with multiple concrete actions (e.g., 'Diagnose, apply fixes, and verify resolution of Cursor IDE errors') to lift specificity.

Tighten the line-wrapped trigger list into a single compact clause so the description reads cleanly.

Dimension	Reasoning	Score
Specificity	Names the domain ('Cursor IDE errors') and enumerates concrete error categories (authentication, completion, indexing, API, performance), but 'troubleshoot' is a single general action rather than a list of multiple specific actions, so it is not comprehensive.	2 / 3
Completeness	Clearly states what the skill does ('Troubleshoot common Cursor IDE errors...') and provides explicit trigger guidance via the 'Triggers on...' clause, answering both what and when.	3 / 3
Trigger Term Quality	Includes natural user phrases — 'cursor error', 'cursor not working', 'cursor issue', 'cursor problem', 'fix cursor', 'cursor crash' — giving good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Scoped specifically to the Cursor IDE with cursor-named triggers, making it clearly distinguishable and unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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.