tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill cursor-model-selectionConfigure and select AI models in Cursor. Triggers on "cursor model", "cursor gpt", "cursor claude", "change cursor model", "cursor ai model". Use when working with cursor model selection functionality. Trigger with phrases like "cursor model selection", "cursor selection", "cursor".
Validation
81%| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 13 / 16 Passed | |
Implementation
22%This skill is a skeleton that lacks any concrete, actionable content. It describes what to do at a high level but provides no specific model names, settings paths, configuration steps, or examples. The content delegates everything useful to external files while the main skill offers only abstract guidance.
Suggestions
Add specific model names with their strengths (e.g., 'Use claude-3.5-sonnet for complex refactoring, gpt-4o-mini for quick completions')
Include concrete steps for accessing model settings in Cursor (e.g., 'Open Settings > Models > Default Chat Model')
Provide at least one inline example showing model selection for a specific task type
Replace vague instructions like 'Understand model strengths' with a quick reference table of models, context limits, and recommended use cases
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is relatively brief but includes some unnecessary filler like 'This skill helps you' and vague prerequisites like 'Understanding of model capabilities' that don't add value. Could be tighter. | 2 / 3 |
Actionability | Instructions are entirely abstract with no concrete guidance. 'Understand model strengths' and 'Choose model based on task type' provide no actual steps, commands, or specific model recommendations. No executable examples. | 1 / 3 |
Workflow Clarity | The 6 steps are vague directives without any specific actions, validation checkpoints, or concrete sequences. 'Configure default models in settings' doesn't explain where or how. | 1 / 3 |
Progressive Disclosure | References to external files (errors.md, examples.md) are present and one-level deep, but the main content is too thin to serve as a useful overview. The skill offloads all substance to other files without providing actionable quick-start content. | 2 / 3 |
Total | 6 / 12 Passed |
Activation
90%This is a solid skill description with excellent trigger term coverage and clear completeness. The main weakness is that the specificity could be improved by listing more concrete actions (e.g., 'switch between GPT-4 and Claude', 'configure default model', 'set model preferences'). The redundant trigger phrases at the end ('cursor selection', 'cursor') are overly generic and could cause false matches.
Suggestions
Add more specific actions like 'switch between GPT-4 and Claude models', 'configure default model settings', or 'view available models' to improve specificity
Remove overly generic trigger terms like 'cursor' alone, which could cause false matches with other Cursor-related skills
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (AI models in Cursor) and actions (configure, select), but lacks comprehensive detail about what specific configuration options or selection capabilities are available. | 2 / 3 |
Completeness | Clearly answers both what ('Configure and select AI models in Cursor') and when ('Use when working with cursor model selection functionality') with explicit trigger phrases listed. | 3 / 3 |
Trigger Term Quality | Includes good coverage of natural terms users would say: 'cursor model', 'cursor gpt', 'cursor claude', 'change cursor model', 'cursor ai model', 'cursor model selection'. These are realistic phrases users would type. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche focused on Cursor IDE model selection. The combination of 'Cursor' + 'model' creates distinct triggers unlikely to conflict with general AI or general IDE skills. | 3 / 3 |
Total | 11 / 12 Passed |
Reviewed
Table of Contents
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.