llm-icon-finder
Finding and accessing AI/LLM model brand icons from lobe-icons library. Use when users need icon URLs, want to download brand logos for AI models/providers/applications (Claude, GPT, Gemini, etc.), or request icons in SVG/PNG/WEBP formats.
Install with Tessl CLI
npx tessl i github:fernandezbaptiste/claude-code-skills --skill llm-icon-finder95
Does it follow best practices?
Validation for skill structure
Discovery
100%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 is a well-crafted skill description that excels across all dimensions. It clearly specifies the capability (accessing AI/LLM brand icons), names the source library, provides concrete examples of models and formats, and includes an explicit 'Use when' clause with natural trigger terms. The description is concise yet comprehensive, making it easy for Claude to select this skill appropriately.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Finding and accessing AI/LLM model brand icons', 'icon URLs', 'download brand logos', and specifies formats 'SVG/PNG/WEBP'. Provides specific examples of models (Claude, GPT, Gemini). | 3 / 3 |
Completeness | Clearly answers both what ('Finding and accessing AI/LLM model brand icons from lobe-icons library') and when ('Use when users need icon URLs, want to download brand logos... or request icons in SVG/PNG/WEBP formats'). Has explicit 'Use when' clause with specific triggers. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'icon URLs', 'download', 'brand logos', 'AI models', specific model names (Claude, GPT, Gemini), and file formats (SVG/PNG/WEBP). These are terms users would naturally use when requesting icons. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: specifically targets AI/LLM brand icons from a named library (lobe-icons). The combination of 'AI model icons', specific model names, and the library name creates clear differentiation from generic icon or image skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%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-crafted skill that efficiently teaches Claude how to find and provide AI brand icons. The URL patterns are concrete and actionable, and the progressive disclosure to reference files is appropriate. The main weakness is the workflow could integrate validation (checking if URL returns 200) before providing to users, rather than treating troubleshooting as a separate afterthought.
Suggestions
Integrate URL validation into the main workflow: add a step to verify the URL returns 200 before providing to user, with immediate fallback to troubleshooting steps if it fails
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is lean and efficient, providing only necessary information. No unnecessary explanations of what icons are or how CDNs work - assumes Claude's competence throughout. | 3 / 3 |
Actionability | Provides concrete, copy-paste ready URL patterns and curl commands. Examples show exact inputs and outputs, making it immediately executable. | 3 / 3 |
Workflow Clarity | Workflow steps are listed but lack validation checkpoints. No verification step to confirm URL works before providing to user, and troubleshooting is separate rather than integrated as a feedback loop. | 2 / 3 |
Progressive Disclosure | Well-structured with clear overview, appropriately references external files (icons-list.md, developer-info.md) for detailed content, and provides web links for browsing. One-level-deep references are clearly signaled. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.