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".
80
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/cursor-pack/skills/cursor-common-errors/SKILL.mdQuality
Discovery
89%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 solid skill description with excellent trigger terms and clear completeness. Its main weakness is that the capability descriptions are category-level rather than listing specific concrete actions (e.g., 'reset auth tokens', 'rebuild index', 'clear cache'). Overall it would perform well in skill selection scenarios.
Suggestions
Expand the capability list with more specific concrete actions, e.g., 'reset authentication tokens, rebuild code index, clear completion cache, diagnose API connectivity' instead of just naming issue categories.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Cursor IDE) and lists categories of issues (authentication, completion, indexing, API, performance), but doesn't describe specific concrete actions like 'reset authentication tokens' or 'clear index cache'. The actions are categorized rather than enumerated. | 2 / 3 |
Completeness | Clearly answers both 'what' (troubleshoot common Cursor IDE errors across authentication, completion, indexing, API, and performance) and 'when' (explicit trigger phrases listed with 'Triggers on...' clause). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: 'cursor error', 'cursor not working', 'cursor issue', 'cursor problem', 'fix cursor', 'cursor crash'. These are highly natural phrases a frustrated user would type. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche — specifically targets Cursor IDE troubleshooting. The trigger terms all include 'cursor' which makes it unlikely to conflict with other skills. Clear and narrow domain. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid troubleshooting reference with strong actionability — specific commands, paths, settings, and domain lists make it immediately useful. The main weaknesses are its monolithic structure (could benefit from splitting into sub-files for each error category) and missing validation/verification steps around destructive operations like cache deletion and settings reset. Some sections like Enterprise Considerations and Resources add marginal value for an AI assistant context.
Suggestions
Add validation checkpoints for destructive operations: verify Cursor is closed before cache deletion, confirm successful deletion, and verify Cursor starts correctly afterward.
Split into sub-files by category (e.g., auth-errors.md, performance-errors.md) with SKILL.md serving as a concise index with symptom-based navigation.
Remove or trim the Enterprise Considerations and Resources sections — these are generic and don't help Claude troubleshoot specific errors.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of tables and structured formatting, but includes some unnecessary context Claude would know (e.g., 'Cursor auto-saves by default', explaining what hot exit does, the Enterprise Considerations section is somewhat generic). The 'Poor Quality Suggestions' section borders on general advice rather than error-specific troubleshooting. | 2 / 3 |
Actionability | Provides specific, executable commands (rm -rf paths, cursor --disable-extensions, Cmd+Shift+P commands), exact settings values, specific domain allowlists, and concrete step-by-step fixes. Nearly every error has copy-paste ready solutions rather than vague guidance. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced within each error category, and the Performance section has a good diagnostic workflow. However, destructive operations like deleting cache directories lack validation checkpoints (no 'verify Cursor is closed first' or 'confirm cache was cleared successfully' steps), and the crash recovery 'nuclear option' lacks a verification step after the fix. | 2 / 3 |
Progressive Disclosure | Well-organized with clear headers and categories making navigation easy, but the content is monolithic — a 150+ line single file that could benefit from splitting detailed sections (e.g., network configuration, crash recovery) into separate referenced files. The mention of 'see cursor-keybindings skill' is a good cross-reference but is the only one. | 2 / 3 |
Total | 9 / 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
3e83543
- 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.