Name: xai-models
Rating: 64.8 (1 reviews)
Author: fernandezbaptiste

xai-models

xAI Grok model selection and capabilities guide. Use when choosing the right Grok model for your task, comparing model features, or optimizing costs.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/xai-models/SKILL.md

The canonical home for this skill is xai-models in fernandezbaptiste/Skrillz

Quality

Content

67%Weight 40%Scale 1-5

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

A dense, well-structured reference guide with concrete executable code and a clear model-selection decision tree. Its main weakness is data redundancy across repeated pricing/capability tables and limited use of separate reference files to keep SKILL.md lean.

Suggestions

Dedupe pricing and context data: keep a single canonical table and have the decision tree and comparison matrices reference it rather than restating the numbers.

Move the detailed per-model profiles and cost-optimization recipes into a reference file (e.g. references/models.md) and link to it from SKILL.md to improve progressive disclosure and conciseness.

Add minimal import/client context to the per-profile code snippets so each is independently copy-paste executable.

Dimension	Reasoning	Score
Conciseness	The body avoids over-explaining concepts Claude already knows, but pricing and capability data is repeated across the Quick Reference table, the decision tree, and the Context Window / Capabilities Matrix tables, so it could be tightened; this matches 'mostly efficient but could be tightened' rather than the lean 4.	3 / 5
Actionability	Mostly executable, copy-paste-ready Python (the base64 vision example and the full API usage example with imports and client setup), but several profile snippets are illustrative fragments without imports, leaving minor gaps below the fully-executable 5.	4 / 5
Workflow Clarity	The selection decision tree and numbered cost-optimization strategies give a clear sequence; the skill is non-destructive so the validation cap does not apply, but explicit checkpoints for the pipeline configurations are only implied, keeping it below 5.	4 / 5
Progressive Disclosure	Content is well-organized into clearly signaled sections with an explicit References list and Related Skills, and no nested references exist; the only gap is that detailed model profiles and cost tables could live in separate reference files, so it sits below the optimally-split 5.	4 / 5
	Total	15 / 20 Passed

Description

87%Weight 40%Scale 1-5

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 concise, well-structured description that clearly answers both what the skill does and when to use it, with concrete trigger phrases and a distinct xAI Grok niche. The only weakness is slightly limited trigger synonym/model-name coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'choosing the right Grok model', 'comparing model features', 'optimizing costs' — with only minor coverage gaps, matching the 'several specific actions' anchor rather than the comprehensive 5.	4 / 5
Completeness	It explicitly states the 'what' ('xAI Grok model selection and capabilities guide') and a concrete 'when' clause ('Use when choosing the right Grok model for your task, comparing model features, or optimizing costs'), matching the explicit both-what-and-when anchor.	5 / 5
Trigger Term Quality	Natural phrases like 'choosing the right Grok model', 'comparing model features', and 'optimizing costs' give good keyword coverage, but common synonyms and specific model-name triggers (e.g. grok-4) are missing, so it sits below the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	The 'xAI Grok' niche with model-selection triggers is clearly distinguishable from other skills and unlikely to fire for the wrong skill, matching the clear-niche anchor.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: .claude/skills/xai-models/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.