model-selection

Automatically applies when choosing LLM models and providers. Ensures proper model comparison, provider selection, cost optimization, fallback patterns, and multi-model strategies.

1.25x

Quality

—

Does it follow best practices?

Impact

93%

1.25x

Average score across 6 eval scenarios

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 — fully executable, copy-paste-ready implementations — but it is a verbose, monolithic ~700-line code dump with no progressive disclosure and no validation checkpoints in its workflows. Hardcoded version-specific model IDs and pricing further hurt conciseness.

Suggestions

Split the full class implementations and the model-metadata registry into files under scripts/ or references/, leaving SKILL.md as a concise overview with one-level-deep, clearly signaled links.

Tighten the code: remove redundant '# Usage' blocks and verbose docstrings, and move time-sensitive model IDs and pricing out of inline code (or into a clearly dated/deprecated reference) to avoid penalizing conciseness.

Add explicit validation checkpoints to the Auto-Apply workflow (e.g., verify registered models resolve, confirm fallback chains trigger correctly, sanity-check cost estimates) so the sequence earns a higher workflow-clarity score.

Dimension	Reasoning	Score
Conciseness	The ~700-line body reimplements well-known patterns (registry, router, fallback, ensemble) with full docstrings and repeated '# Usage' blocks, and hardcodes version-specific IDs and pricing outside any deprecated section, so it could be tightened considerably; it stays above 1 only because the content is actionable code rather than concept prose.	2 / 3
Actionability	It provides complete, executable Python (ModelRegistry, ModelRouter, FallbackChain, CostOptimizer, ModelEnsemble) with concrete usage examples, matching the copy-paste-ready score-3 anchor.	3 / 3
Workflow Clarity	The 'Auto-Apply' section lists a 7-step sequence, but there are no validation checkpoints between steps and the batch_cost_analysis path has no verification, matching the score-2 anchor of steps present but checkpoints missing.	2 / 3
Progressive Disclosure	It has clear ## section structure, but everything is inline in one monolithic file with no references/, scripts/, or assets/ bundle files, so content that should be split (full class implementations, model-data registry) is not separated — matching the score-2 'content that should be separate is inline' anchor.	2 / 3
	Total	9 / 12 Passed

Description

85%

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 is strong: it names concrete capabilities, gives an explicit 'applies when' trigger, and carves out a distinct niche. Its main weakness is trigger-term quality, where several terms are more technical jargon than natural user phrasing and common variations are missing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'model comparison, provider selection, cost optimization, fallback patterns, and multi-model strategies' — matching the score-3 anchor for naming several specific actions rather than vague abstraction.	3 / 3
Completeness	'Automatically applies when choosing LLM models and providers' gives an explicit when-trigger, while 'Ensures proper model comparison...' states the what, clearly answering both; the explicit 'applies when' clause avoids the cap at 2.	3 / 3
Trigger Term Quality	It includes relevant terms like 'choosing LLM models', 'model comparison', and 'cost optimization', but leans technical ('fallback patterns', 'multi-model strategies') and omits common natural variations such as provider names or 'routing', so it falls short of the full-coverage score-3 anchor.	2 / 3
Distinctiveness Conflict Risk	The model-selection / provider-management niche has distinct triggers and is unlikely to conflict with non-LLM skills, matching the clear-niche score-3 anchor.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (713 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: majiayu000/claude-skill-registry
Commit: cb3ef45

Reviewed: about 18 hours 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.