ai-models
Latest AI models reference - Claude, OpenAI, Gemini, Eleven Labs, Replicate
53
43%
Does it follow best practices?
Impact
Pending
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 and lacks both concrete actions and usage triggers. It reads more like a title or tag list than a functional skill description. The brand names provide some keyword value, but without explaining what the skill actually does or when to use it, Claude would struggle to select it appropriately.
Suggestions
Add concrete actions describing what the skill does, e.g., 'Provides up-to-date model names, capabilities, pricing, and API details for Claude, OpenAI, Gemini, Eleven Labs, and Replicate models.'
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about latest AI model versions, model comparisons, API references, or needs current model names and specifications.'
Include natural trigger terms users would say, such as 'model comparison', 'latest model', 'API reference', 'model pricing', 'GPT-4', 'Claude 4', 'Gemini 2.5' to improve selection accuracy.
| 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. | 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 listing of specific AI provider names gives it some distinctiveness, but 'reference' is so vague it could overlap with any skill involving AI models, APIs, or documentation lookups. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured reference document with excellent actionability—every provider has concrete, executable code examples and specific model IDs. Its main weaknesses are redundancy across three different model recommendation sections (top matrix, per-provider selection, bottom quick reference) and being monolithic when it could benefit from splitting provider details into separate files. The time-sensitive nature of model versions is acknowledged with the 'Last Updated' header and update checklist, which is good practice.
Suggestions
Split per-provider details into separate files (e.g., ANTHROPIC.md, OPENAI.md) and keep SKILL.md as the selection matrix + quick reference with links to provider files
Consolidate the three overlapping model recommendation sections (top matrix, per-provider model selection trees, bottom 'Best For Each Task') into a single authoritative recommendation section to reduce redundancy
Add a concrete validation step to the Model Update Checklist, such as a curl command to verify a model ID is valid against each provider's API
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is a reference document so length is somewhat justified, but there's redundancy between the model selection matrix at the top, per-provider model selection sections, and the 'Best For Each Task' quick reference at the bottom. Some sections like Stability AI add marginal value. The tree-format model selection blocks repeat information already in the code constants. | 2 / 3 |
Actionability | Every provider includes fully executable TypeScript code examples with proper imports, API initialization, and realistic usage patterns. Model ID strings are concrete and copy-paste ready, environment variable templates are provided, and pricing is specific. | 3 / 3 |
Workflow Clarity | This is primarily a reference skill rather than a multi-step workflow, so the bar is lower. However, the 'Model Update Checklist' at the end provides a useful workflow but lacks validation steps (e.g., how to verify model IDs are valid, what to do if a model is deprecated). The model selection guidance is clear but could benefit from a decision tree or explicit if/then logic. | 2 / 3 |
Progressive Disclosure | The content is a monolithic ~500-line file that could benefit from splitting provider details into separate files (e.g., ANTHROPIC.md, OPENAI.md) with the main file serving as the selection matrix and quick reference. The mention of 'Load with: base.md + llm-patterns.md' hints at a multi-file system but the main content doesn't leverage it for its own organization. | 2 / 3 |
Total | 9 / 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 (685 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
d4ddb03
- 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.