ai-models
Latest AI models reference - Claude, OpenAI, Gemini, Eleven Labs, Replicate
40
40%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/ai-models/SKILL.mdQuality
Discovery
22%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 description is extremely minimal — it lists provider names but fails to explain what the skill actually does or when it should be used. Without concrete actions (e.g., 'look up model specs', 'compare pricing', 'check context window sizes') and explicit trigger guidance, Claude would struggle to know when to select this skill over others.
Suggestions
Add concrete actions describing what the skill does, e.g., 'Provides up-to-date specifications, pricing, and capabilities for latest AI models including Claude, OpenAI GPT, Gemini, Eleven Labs, and Replicate.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about AI model comparisons, model specs, context window sizes, API pricing, or which model to choose.'
Clarify the scope of 'reference' — does it contain model names, API details, pricing, release dates, capabilities? Specificity here would greatly improve distinctiveness and trigger quality.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names some AI model providers but describes no concrete actions. There are no verbs indicating what the skill does — it only says 'reference' which is extremely vague. | 1 / 3 |
Completeness | The 'what' is barely addressed — 'reference' is not a clear capability description. There is no 'when' clause or any explicit trigger guidance whatsoever, which per the rubric should cap completeness at 2, but the 'what' is also very weak, warranting a 1. | 1 / 3 |
Trigger Term Quality | It includes some relevant brand names (Claude, OpenAI, Gemini, Eleven Labs, Replicate) that users might mention, but lacks natural trigger phrases like 'model comparison', 'which model', 'API pricing', or 'model capabilities' that would indicate when to use this skill. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of specific AI provider names gives it some distinctiveness, but 'reference' is so vague it could overlap with any skill that mentions AI models, APIs, or provider documentation. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive and highly actionable AI models reference with concrete, executable code examples for every provider and clear model selection guidance. Its main weakness is that it's a monolithic wall of content (~500+ lines) that would be far more effective split across provider-specific files, with the main SKILL.md serving as a concise overview and router. There's also some content duplication between the top-level selection matrix and the bottom quick reference section.
Suggestions
Split per-provider sections (Anthropic, OpenAI, Google, etc.) into separate files and keep SKILL.md as a concise overview with the selection matrix and links to each provider file.
Remove the duplicated 'Best For Each Task' section at the bottom since the Model Selection Matrix at the top already covers this.
Add a brief note about time-sensitivity and verification process—since model IDs and pricing change frequently, include guidance on how to verify current model availability (e.g., checking the API's list-models endpoint).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly efficient as a reference document, but there's some redundancy—the model selection matrix at the top duplicates the 'Best For Each Task' section at the bottom, and the per-provider 'Model Selection' ASCII trees repeat information already in the code constants. Some sections (Stability AI, Voyage AI) could be trimmed. However, it avoids explaining basic concepts and mostly earns its tokens. | 2 / 3 |
Actionability | Every provider section includes executable TypeScript code with proper imports, API initialization, and real method calls. Model ID strings are concrete and copy-paste ready. The environment variables template and model constants are immediately usable. | 3 / 3 |
Workflow Clarity | This is primarily a reference skill rather than a multi-step workflow, so workflow demands are lower. However, the 'Model Update Checklist' at the end is a useful workflow but lacks validation steps (e.g., how to verify model IDs are correct, what to do if a model is deprecated). The model selection guidance is clear but there's no decision flowchart or explicit process for choosing between providers. | 2 / 3 |
Progressive Disclosure | This is a monolithic ~500-line file with no bundle files to offload detail into. Each provider's full model list, usage examples, and selection guides are all inline. This would benefit enormously from splitting per-provider details into separate files (e.g., ANTHROPIC.md, OPENAI.md) with the main SKILL.md serving as the selection matrix and quick reference only. | 1 / 3 |
Total | 8 / 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (684 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- alinaqi/claude-bootstrap
- Commit
65efb33
- 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.