ai-models

Latest AI models reference - Claude, OpenAI, Gemini, Eleven Labs, Replicate

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/ai-models/SKILL.md

Quality

Content

42%

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

The skill is highly actionable with ready-to-use code and model IDs, but it is a verbose monolithic reference that violates token-budget and progressive-disclosure principles and carries time-sensitive data inline without an update/deprecation structure. It would benefit from splitting provider details into reference files.

Suggestions

Split each provider section into separate reference files (e.g. references/anthropic.md, references/openai.md) and keep SKILL.md a concise overview pointing to them.

Trim usage boilerplate and concepts Claude already knows; retain only model IDs, key specs, and selection guidance.

Add a model-update verification step (confirm the model ID is current via the provider's models endpoint before relying on it) since version-stamped IDs go stale.

Move dated 'Last Updated / December 2025' version data into a clearly marked section so stale IDs are obvious.

Dimension	Reasoning	Score
Conciseness	The ~680-line body reproduces full reference catalogs, usage boilerplate, and pricing tables that Claude largely already knows or could fetch on demand; it is a monolithic data dump rather than lean, value-add-only guidance.	1 / 3
Actionability	Provides concrete, copy-paste-ready executable code for every provider and explicit model ID strings and parameters, fully actionable.	3 / 3
Workflow Clarity	Selection matrices and per-model 'Best for / Use when' blocks give a usable selection sequence, but there is no validation/verification checkpoint (e.g. confirm model ID exists before calling) for batch or destructive API operations.	2 / 3
Progressive Disclosure	No bundle/reference files exist, and the entire provider catalog and API usage is inlined as one long SKILL.md rather than split into separate reference files — a monolithic structure with poor navigation.	1 / 3
	Total	7 / 12 Passed

Description

57%

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 identifies a clear niche (latest AI model specs across major providers) but stops short of explicit, natural trigger phrasing and concrete actions. It is functional but generic for its domain.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when choosing or comparing AI models, referencing model specs, or picking a provider for a task'.

List concrete actions (compare capabilities/costs, look up model IDs and context windows) rather than only the passive word 'reference'.

Expand trigger coverage with common phrasings like 'which model should I use', 'model comparison', or 'model pricing'.

Dimension	Reasoning	Score
Specificity	Names the domain (AI models) and lists providers ('Claude, OpenAI, Gemini, Eleven Labs, Replicate') but does not state concrete actions like comparing specs, pricing, or selecting models — only implies reference/lookup.	2 / 3
Completeness	The 'what' is covered (a reference of latest AI models) but the description itself has no 'Use when...' clause; per the rubric a missing explicit trigger caps completeness at 2 even though when-to-use exists in separate frontmatter.	2 / 3
Trigger Term Quality	Includes natural provider names (Claude, OpenAI, Gemini) users would say, but the only trigger phrasing ('Latest AI models reference') is generic and misses common variations like 'which model', 'model comparison', or 'pick a model'.	2 / 3
Distinctiveness Conflict Risk	Clearly scoped to AI model selection/specs across named providers, a distinct niche unlikely to trigger for unrelated skills.	3 / 3
	Total	9 / 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
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	14 / 16 Passed

Repository: alinaqi/claude-bootstrap
Path: skills/ai-models/SKILL.md
Commit: bb6195f

Reviewed: 6 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.