llm

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

Quality

23%

Does it follow best practices?

Impact

Pending

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 supported providers but lacks actionable specificity about what operations it enables. The critical weakness is the complete absence of trigger guidance ('Use when...'), making it difficult for Claude to know when to select this skill over others. The description would benefit from concrete actions and explicit usage scenarios.

Suggestions

Add a 'Use when...' clause with trigger scenarios like 'Use when the user wants to call LLM APIs, compare model outputs, or switch between AI providers'

Include concrete actions such as 'send prompts to multiple providers, compare responses, manage API keys, handle rate limiting'

Add common user terms like 'GPT', 'Claude API', 'Gemini', 'chat completion', 'AI API' to improve trigger term coverage

Dimension	Reasoning	Score
Specificity	Names the domain (LLM integration) and lists providers (OpenAI, Anthropic, Google, local models), but doesn't describe concrete actions like 'send prompts', 'compare responses', or 'switch between models'.	2 / 3
Completeness	Describes what (unified interface for multiple LLM providers) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Includes some relevant keywords (OpenAI, Anthropic, Google, LLM, local models) but misses common user terms like 'GPT', 'Claude API', 'Gemini', 'chat completion', 'API calls', or 'language model'.	2 / 3
Distinctiveness Conflict Risk	The multi-provider focus provides some distinction, but 'LLM integration' is broad enough to potentially conflict with provider-specific skills or general API integration skills.	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 list or README placeholder rather than actionable guidance. It tells Claude what the skill can do but provides zero implementation details, code examples, or configuration instructions. Claude would not know how to actually use any of the mentioned providers or features after reading this.

Suggestions

Add executable code examples for at least one provider (e.g., OpenAI API call with proper authentication and response handling)

Include a workflow for common tasks like 'Compare models on a task' with concrete steps: 1) Send prompt to provider A, 2) Send to provider B, 3) Compare outputs

Provide configuration examples showing how to set up API keys and connect to each provider

Add references to detailed documentation files for each provider (e.g., 'See [OPENAI.md](OPENAI.md) for GPT-4 integration details')

Dimension	Reasoning	Score
Conciseness	The content is relatively brief but lacks substance - it lists features and providers without providing actionable implementation details. The bullet points are efficient but the content is thin rather than lean.	2 / 3
Actionability	No concrete code, commands, or executable guidance provided. The 'Usage Examples' section shows natural language prompts rather than actual implementation code or API calls. Claude cannot execute anything from this skill.	1 / 3
Workflow Clarity	No workflow or process is defined. The skill lists features but provides no steps for how to actually integrate with any provider, configure connections, or handle responses. No validation or error handling mentioned.	1 / 3
Progressive Disclosure	The content is a shallow overview with no references to detailed documentation, configuration files, or examples. There's no navigation to deeper content for any of the listed providers or features.	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: 45f9fac

Reviewed: 27 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.