llm

Multi-provider LLM integration. Unified interface for OpenAI, Anthropic, Google, and local models.

Quality

23%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./public/skills/0xterrybit/llm/SKILL.md

Quality

Discovery

32%

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 its domain and lists supported providers, which gives some specificity, but it reads more like a tagline than a functional skill description. It lacks concrete actions the skill performs and entirely omits trigger guidance ('Use when...'), making it difficult for Claude to know when to select this skill over others.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user needs to call LLM APIs, compare outputs across providers, or integrate OpenAI/Anthropic/Google models into their application.'

List specific concrete actions such as 'Send prompts to multiple LLM providers, manage API keys, compare model responses, handle streaming completions, and switch between OpenAI GPT, Anthropic Claude, Google Gemini, and local models like Ollama.'

Include natural trigger terms users would say, such as 'GPT', 'Claude API', 'Gemini', 'Ollama', 'chat completion', 'model comparison', 'API key', and 'prompt routing'.

Dimension	Reasoning	Score
Specificity	Names the domain (LLM integration) and mentions specific providers (OpenAI, Anthropic, Google, local models), but doesn't describe concrete actions like 'send prompts', 'compare model outputs', 'switch between providers', or 'manage API keys'.	2 / 3
Completeness	Describes what it is (unified interface for multiple LLM providers) but completely lacks any 'Use when...' clause or explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also weak, so this scores 1.	1 / 3
Trigger Term Quality	Includes some relevant keywords like 'OpenAI', 'Anthropic', 'Google', 'local models', and 'LLM', but misses common user terms like 'API', 'chat completion', 'GPT', 'Claude', 'Gemini', 'Ollama', 'model switching', or 'prompt'.	2 / 3
Distinctiveness Conflict Risk	The mention of specific providers (OpenAI, Anthropic, Google) and the 'unified interface' concept gives it some distinctiveness, but 'LLM integration' is broad enough to potentially overlap with skills focused on individual providers or general AI/ML tooling.	2 / 3
	Total	7 / 12 Passed

Implementation

14%

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

This skill is essentially a feature advertisement rather than actionable guidance. It lists providers and capabilities but provides zero concrete implementation details—no code examples, no configuration steps, no API patterns, and no references to detailed documentation. For a multi-provider LLM integration skill, this is critically insufficient.

Suggestions

Add executable code examples showing the unified interface for at least 2 providers (e.g., OpenAI and Anthropic), including initialization, API key configuration, and a basic chat completion call.

Define a clear workflow for common tasks like provider setup, model comparison, and cost estimation with specific steps and validation (e.g., verify API key works before proceeding).

Create supporting reference files (e.g., PROVIDERS.md, EXAMPLES.md) with provider-specific details and link to them from the main skill for progressive disclosure.

Replace the natural language 'Usage Examples' with concrete code snippets or CLI commands that Claude can actually execute.

Dimension	Reasoning	Score
Conciseness	The content is relatively brief but includes feature bullet points that are vague and don't add actionable value. The supported providers list is somewhat useful but the features list is filler.	2 / 3
Actionability	There is no executable code, no concrete commands, no API examples, no configuration snippets, and no specific guidance on how to actually integrate with any provider. The 'Usage Examples' are just natural language prompts, not actionable instructions.	1 / 3
Workflow Clarity	There is no workflow, no sequenced steps, no setup instructions, no configuration process, and no validation checkpoints. The skill provides no guidance on how to accomplish any multi-provider LLM integration task.	1 / 3
Progressive Disclosure	The content is a flat, shallow overview with no references to any supporting files, no links to detailed documentation, and no bundle files exist to support it. There's no navigation structure for what should be a complex multi-provider topic.	1 / 3
	Total	5 / 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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	9 / 11 Passed

Repository: Demerzels-lab/elsamultiskillagent
Commit: f45fcb5

Reviewed: 19 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.