cursor-model-selection
Configure and select AI models in Cursor for Chat, Composer, and Agent mode. Triggers on "cursor model", "cursor gpt", "cursor claude", "change cursor model", "cursor ai model", "cursor auto mode".
65
58%
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-model-selection/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 description with excellent trigger terms and clear distinctiveness. The main weakness is that the 'what' portion could be more specific about the concrete actions available (e.g., listing available models, setting defaults, comparing model capabilities). The explicit trigger terms are a strong point that makes skill selection reliable.
Suggestions
Expand the capability description with more specific actions, e.g., 'Configure and select AI models in Cursor, set default models for Chat/Composer/Agent modes, compare available models, switch between GPT-4 and Claude variants.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (AI models in Cursor) and some actions ('configure and select'), but doesn't list specific concrete actions like adding models, switching between models, setting default models, or configuring API keys. | 2 / 3 |
Completeness | Clearly answers both 'what' (configure and select AI models in Cursor for Chat, Composer, and Agent mode) and 'when' (explicit trigger terms listed with 'Triggers on' clause), satisfying the requirement for explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes a strong set of natural trigger terms that users would actually say: 'cursor model', 'cursor gpt', 'cursor claude', 'change cursor model', 'cursor ai model', 'cursor auto mode'. These cover common variations well. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — the combination of 'Cursor' editor + AI model configuration is a very specific niche. The trigger terms are specific enough to avoid conflicts with general AI model skills or general Cursor usage skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a comprehensive reference guide or documentation page than a focused, actionable skill for Claude. It contains substantial amounts of information Claude either already knows (model behavior differences, what reasoning models do) or that is time-sensitive and likely to become outdated (specific model names, quota numbers, pricing tiers). The content would benefit greatly from aggressive trimming to focus on the actionable configuration steps and decision framework, with detailed reference material split into separate files.
Suggestions
Cut the 'Model Behavior Differences' section entirely — Claude knows how different models generate code and what reasoning models do.
Move the model tables, BYOK details, and enterprise considerations into separate bundle files (e.g., MODELS.md, BYOK.md, ENTERPRISE.md) and reference them from a concise overview.
Add validation steps after BYOK configuration (e.g., 'Send a test message in Chat to verify the key works; if you see an auth error, check the key format').
Remove or drastically shorten the cost optimization section — quota numbers and pricing are time-sensitive and Claude doesn't need to manage a user's budget.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Significant verbosity throughout. The code generation style comparison section explains things Claude already knows about its own behavior vs GPT models. The enterprise considerations, cost optimization strategies, and quota management details are padding that Claude doesn't need to perform model selection. Model tables include information that changes frequently and could be outdated. | 1 / 3 |
Actionability | The 'How to Switch Models' section provides concrete UI navigation paths, and the BYOK configuration shows specific key formats and settings. However, much of the content is informational/descriptive rather than instructional — the model comparison tables and behavior differences describe rather than instruct. No executable code for actual model configuration tasks. | 2 / 3 |
Workflow Clarity | The 'Adding Custom Models' section has a clear 5-step sequence. The tiered model usage provides a decision framework. However, there are no validation checkpoints — e.g., no step to verify an API key works after configuration, no troubleshooting for failed model connections, and no feedback loops for when model selection doesn't produce desired results. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text at ~150+ lines with no bundle files to offload content to. The model tables, BYOK configuration, cost optimization, enterprise considerations, and behavior differences could all be separate reference files. External links at the bottom are to Cursor docs, not to organized bundle files. Everything is inlined in one large document. | 1 / 3 |
Total | 6 / 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.