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".
64
77%
Does it follow best practices?
Impact
—
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 capabilities listed are category-level (authentication, completion, indexing) rather than specific concrete actions, which keeps specificity at a moderate level. Overall it would perform well in skill selection scenarios.
Suggestions
Add specific concrete actions beyond 'troubleshoot', e.g., 'reset authentication tokens, rebuild code index, diagnose API connection failures, resolve high CPU usage'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Cursor IDE) and lists categories of issues (authentication, completion, indexing, API, performance), but doesn't describe concrete actions like 'reset authentication tokens' or 'clear index cache'. The actions are implied by 'troubleshoot' but not 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). The 'Triggers on' clause serves as an explicit 'Use when' equivalent. | 3 / 3 |
Trigger Term Quality | Includes excellent natural trigger terms that users would actually say: 'cursor error', 'cursor not working', 'cursor issue', 'cursor problem', 'fix cursor', 'cursor crash'. These cover common variations of how users express problems with Cursor IDE. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — specifically targets Cursor IDE troubleshooting, which is a clear niche. The trigger terms all include 'cursor' combined with error-related terms, making it unlikely to conflict with other skills. | 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 highly actionable fixes, good use of tables, and clear categorization by error type. Its main weaknesses are the lack of verification steps after applying fixes (important for troubleshooting workflows) and the monolithic structure that could benefit from splitting detailed sections into separate files. Some minor verbosity could be trimmed by removing explanations Claude doesn't need.
Suggestions
Add verification/confirmation steps after each fix (e.g., 'Verify: AI completions should now appear when typing' or 'Expected: status bar shows indexing progress') to create proper feedback loops for troubleshooting.
Split detailed sections (Extension Conflicts table, Enterprise Considerations, Network allowlist) into separate referenced files to improve progressive disclosure and reduce the main file's length.
Remove explanatory 'Symptoms' and 'Cause' lines where they restate what the section heading already conveys — Claude can infer these from context.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of tables and structured formatting, but some sections include unnecessary context Claude would already know (e.g., explaining what symptoms look like, 'Cursor auto-saves by default', enterprise considerations section). Some tightening possible throughout. | 2 / 3 |
Actionability | Highly actionable with specific commands (Cmd+Shift+P sequences), exact file paths for cache deletion, concrete settings.json entries, CLI flags for crash recovery, and specific domain allowlists. Nearly every fix is copy-paste ready or immediately executable. | 3 / 3 |
Workflow Clarity | Most fixes are presented as clear numbered steps, and the performance diagnosis section has a good sequential workflow. However, there are no explicit validation/verification checkpoints — no 'confirm the fix worked' steps after applying resolutions, which is important for troubleshooting workflows where the first fix may not resolve the issue. | 2 / 3 |
Progressive Disclosure | Well-organized with clear section headers and logical categorization by error type, making navigation easy. However, the content is quite long (~200 lines) and monolithic — some sections like Enterprise Considerations or detailed extension conflict tables could be split into referenced files. No bundle files exist to offload detail. | 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
8a9cd04
- 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.