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".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete config paths and steps, but it is somewhat redundant and fails to use its own reference bundle: reference files are neither linked from the body nor kept consistent with it, and workflows lack validation checkpoints.

Suggestions

Link to the existing reference files from the relevant sections (e.g. model tables -> references/available-models.md, comparisons -> references/model-comparison.md) instead of duplicating their content inline.

Reconcile the body's model list (GPT-4o, GPT-5, Claude Sonnet/Haiku/Opus, Gemini 2.5 Pro) with the reference files, which still list older models (GPT-4, Claude 3.5 Sonnet, GPT-3.5 Turbo) — pick one source of truth to avoid conflicting guidance.

Trim non-instructional filler such as "Choosing the right model per task is a major productivity lever" and reduce the placeholder API-key blocks to a single example to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	Mostly efficient tables and snippets, but carries marketing fluff ("Choosing the right model per task is a major productivity lever") and duplicates model-availability info already present in references/available-models.md, so it could be tightened rather than fully lean.	2 / 3
Actionability	Provides concrete, copy-paste-ready guidance: exact settings paths ("Cursor Settings > Models"), BYOK key blocks, an Azure config block, and a numbered 5-step "Adding Custom Models" procedure.	3 / 3
Workflow Clarity	Steps are present (e.g. the numbered custom-model procedure and per-conversation/default switching) but there are no validation checkpoints or feedback loops; this matches the 'steps listed, checkpoints missing' anchor rather than the 3.	2 / 3
Progressive Disclosure	Five reference files exist (available-models.md, errors.md, examples.md, model-comparison.md, model-selection-by-task.md) but the body never links to them, and content that belongs in those files (model tables, comparisons, examples) is duplicated inline; the orphaned, inconsistent references match the 'references present but not clearly signaled' anchor.	2 / 3
	Total	9 / 12 Passed

Description

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.

A strong description: concrete actions, explicit trigger terms, third-person voice, and a clear niche. It clearly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Names concrete actions ("Configure and select AI models") plus the three concrete scopes ("Chat, Composer, and Agent mode"), matching the multiple-specific-actions anchor rather than the single-domain anchor at 2.	3 / 3
Completeness	Explicitly answers both what ("Configure and select AI models in Cursor...") and when ("Triggers on..."), with the explicit trigger clause satisfying the 'Use when' equivalent requirement.	3 / 3
Trigger Term Quality	Lists six natural phrases users would actually say ("cursor model", "cursor gpt", "cursor claude", "change cursor model", "cursor ai model", "cursor auto mode"), giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Scoped to Cursor model selection with distinct "cursor"-prefixed triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 3022dd3

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.