cursor-indexing-issues
Troubleshoot Cursor codebase indexing: stuck indexing, empty search, @codebase failures, and performance issues. Triggers on "cursor indexing", "cursor index", "@codebase not working", "cursor search broken", "indexing stuck".
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 defines its scope (Cursor codebase indexing troubleshooting), lists specific problem scenarios it addresses, and provides explicit trigger terms. It uses third person voice appropriately and is concise without being vague. The explicit 'Triggers on' clause with natural user phrases makes it easy for Claude to select this skill at the right time.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions/issues: stuck indexing, empty search, @codebase failures, and performance issues. These are concrete problem scenarios rather than vague language. | 3 / 3 |
Completeness | Clearly answers both 'what' (troubleshoot Cursor codebase indexing issues including stuck indexing, empty search, @codebase failures, performance issues) and 'when' (explicit 'Triggers on' clause with specific trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: 'cursor indexing', 'cursor index', '@codebase not working', 'cursor search broken', 'indexing stuck'. These are realistic phrases a user would type when experiencing these issues. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Cursor IDE codebase indexing troubleshooting. The specific product name (Cursor), feature (@codebase), and problem domain (indexing) make it very unlikely to conflict with other 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 troubleshooting skill with excellent actionability — concrete commands, platform-specific paths, and copy-paste ready configurations. The diagnostic table at the top provides quick triage, and workflows are well-sequenced. The main weakness is moderate verbosity: some explanatory content (semantic search explanation, enterprise considerations, benchmarks) could be trimmed or split out to keep the core troubleshooting guide leaner.
Suggestions
Trim the 'Semantic vs Keyword Search' explanation (Check 4) to a single sentence — Claude understands embedding-based search.
Consider moving 'Enterprise Considerations' and 'Performance Optimization' benchmarks to separate referenced files to reduce the main skill's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of tables and structured content, but some sections like the semantic vs keyword search explanation and enterprise considerations add information Claude likely already knows or that isn't directly actionable for troubleshooting. The benchmarks table and some explanatory text could be tightened. | 2 / 3 |
Actionability | Provides fully executable commands, specific file paths for cache clearing across all three OSes, concrete .cursorignore examples, exact command palette entries, and copy-paste ready configuration snippets. Every fix section gives specific steps to follow. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced (Step 1 → Step 2 → Step 3 for stuck indexing, Check 1 → Check 2 → Check 3 → Check 4 for no results). The stuck indexing workflow includes a clear escalation path: reduce scope → resync → clear cache if resync fails. The stale results fix includes a verification step (wait for 'Indexed' status). | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and a diagnostic table up front, but it's a fairly long monolithic document (~180 lines of content). The enterprise considerations and some of the detailed ignore file explanations could be split into separate referenced files. However, with no bundle files, this is a standalone skill that manages its length reasonably well with good section headers. | 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
3a2d27d
- 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.