cursor-known-pitfalls
Avoid common Cursor IDE pitfalls: AI feature mistakes, security gotchas, configuration errors, and team workflow issues. Triggers on "cursor pitfalls", "cursor mistakes", "cursor gotchas", "cursor issues", "cursor problems", "cursor tips".
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-known-pitfalls/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.
The description effectively identifies its niche (Cursor IDE pitfalls) and provides explicit trigger terms, making it strong on completeness and distinctiveness. Its main weakness is that it describes what to avoid rather than listing concrete actions the skill performs (e.g., diagnosing issues, recommending fixes, validating configs). The category-level descriptions of pitfalls are helpful but could be more specific about the skill's actual outputs.
Suggestions
Reframe with concrete action verbs describing what the skill does, e.g., 'Identifies and resolves common Cursor IDE pitfalls: diagnoses AI feature misconfigurations, flags security vulnerabilities, validates .cursorrules settings, and recommends team workflow best practices.'
Add a few more specific examples of pitfalls to increase specificity, such as 'accidental API key exposure in .cursor files' or 'incorrect model selection in AI completions'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Cursor IDE) and lists categories of pitfalls (AI feature mistakes, security gotchas, configuration errors, team workflow issues), but doesn't describe concrete actions the skill performs—it says what to 'avoid' rather than what it actively does (e.g., 'diagnoses', 'recommends fixes', 'validates configuration'). | 2 / 3 |
Completeness | Answers both 'what' (avoid common Cursor IDE pitfalls across AI features, security, configuration, and team workflows) and 'when' (explicit trigger phrases listed with 'Triggers on...'). The 'when' clause is clearly stated. | 3 / 3 |
Trigger Term Quality | Explicitly lists multiple natural trigger terms users would say: 'cursor pitfalls', 'cursor mistakes', 'cursor gotchas', 'cursor issues', 'cursor problems', 'cursor tips'. These are realistic phrases a user would type when seeking help with Cursor IDE problems. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive—specifically targets Cursor IDE pitfalls and anti-patterns, which is a narrow niche unlikely to conflict with other skills. The trigger terms are all Cursor-specific. | 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 reference skill with strong actionability—nearly every pitfall has concrete, specific solutions with real commands and configurations. The main weaknesses are its length (could benefit from progressive disclosure into sub-files) and some unnecessary explanatory text that Claude doesn't need. The categorical organization is effective, but the document would be more token-efficient as a concise overview with links to detailed sub-documents.
Suggestions
Split the 18 pitfalls into separate category files (e.g., SECURITY_PITFALLS.md, CONFIG_PITFALLS.md) and keep SKILL.md as a concise index with one-line summaries linking to each.
Trim explanatory text that Claude already knows—e.g., remove 'The conversation history fills context, leaving no room for your new request' and just state the solution directly.
Add a verification step to Pitfall 7 (.cursorignore): after creating the file, verify it works by testing that @Codebase doesn't surface .env contents.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary framing and explanation that Claude would already know (e.g., explaining what context window overflow leads to, explaining what timing attacks are). Some pitfalls could be more tightly written, though overall it avoids extreme verbosity. | 2 / 3 |
Actionability | Nearly every pitfall includes concrete, specific solutions with exact commands, file paths, configuration snippets, and settings names. The solutions are copy-paste ready (e.g., .cursorignore content, settings.json config, .mdc rule examples) and reference specific UI paths. | 3 / 3 |
Workflow Clarity | Pitfall 1 has a clear sequential workflow with validation steps (build, test, commit before). However, most other pitfalls are standalone tips rather than multi-step workflows, and the overall document lacks explicit feedback loops or verification checkpoints for potentially destructive operations like applying Composer changes. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear category headers and numbered pitfalls, making it easy to scan. However, at ~200 lines it's quite long for a single SKILL.md and could benefit from splitting detailed sections (security, configuration, performance) into separate referenced files rather than inlining everything. | 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.