cursor-debug-bundle
Debug AI suggestion quality, context issues, and code generation problems in Cursor. Triggers on "debug cursor ai", "cursor suggestions wrong", "bad cursor completion", "cursor ai debug", "cursor hallucination".
85
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
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 distinctiveness for its niche (Cursor AI debugging). The main weakness is that the capability description could be more specific about what concrete actions the skill performs (e.g., checking .cursorrules, analyzing context window settings, reviewing indexing configuration). Overall it performs well for skill selection purposes.
Suggestions
Add more specific concrete actions like 'checks .cursorrules configuration, analyzes context window settings, reviews codebase indexing, and diagnoses prompt engineering issues' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Cursor AI) and some actions ('debug AI suggestion quality, context issues, and code generation problems'), but doesn't list multiple concrete specific actions like step-by-step debugging procedures or specific outputs. | 2 / 3 |
Completeness | Clearly answers both 'what' (debug AI suggestion quality, context issues, and code generation problems in Cursor) and 'when' (explicit triggers listed with 'Triggers on' clause specifying exact phrases). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would actually say: 'debug cursor ai', 'cursor suggestions wrong', 'bad cursor completion', 'cursor hallucination'. These are realistic phrases a frustrated user would type. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting Cursor IDE AI debugging specifically. The trigger terms are highly distinctive and unlikely to conflict with general coding, debugging, or other AI tool skills. | 3 / 3 |
Total | 11 / 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 solid, actionable debugging guide with excellent symptom-to-fix mapping and a well-structured escalation workflow. Its main weakness is length — the content could be more concise by trimming obvious root cause explanations and splitting detailed sections into referenced files. The Enterprise Considerations section adds little value for an AI skill.
Suggestions
Remove or significantly trim the Enterprise Considerations section, which contains generic advice Claude doesn't need.
Consider splitting detailed sections (Logs and Diagnostics, Bug Report Reproduction) into separate referenced files to improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some unnecessary framing (e.g., the diagnostic framework box with percentages, the Enterprise Considerations section which is generic advice). The symptom-fix format is good but some explanations of root causes state the obvious. | 2 / 3 |
Actionability | Provides concrete, copy-paste ready fixes including YAML rule files, specific commands (Cmd+Shift+P > 'Cursor: Resync Index'), exact file paths for logs, and specific prompt patterns with @-references. Each symptom maps to executable remediation steps. | 3 / 3 |
Workflow Clarity | The 'Systematic Debug Workflow' section provides a clear 5-step escalation sequence with explicit checkpoints (test with minimal context, test with different model). Each step has a clear validation criterion (e.g., 'If this works, the issue was context pollution'). The bug report reproduction steps are also well-sequenced. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and symptom-based sections, but it's a fairly long monolithic document (~150 lines of substantive content). The symptom-specific fixes, systematic workflow, logs/diagnostics, and enterprise sections could be split into referenced files. External links are provided but no internal file references for deeper content. | 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
70e9fa4
- 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.