> 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.

fetch
$curl "https://skillshub.wtf/daymade/claude-code-skills/llm-icon-finder?format=md"
SKILL.mdllm-icon-finder

Finding AI/LLM Brand Icons

Access AI/LLM model brand icons and logos from the lobe-icons library. The library contains 100+ icons for models (Claude, GPT, Gemini), providers (OpenAI, Anthropic, Google), and applications (ComfyUI, LobeChat).

Icon Formats and Variants

Available formats: SVG (scalable), PNG (raster), WEBP (compressed) Theme variants: light, dark, and color (some icons)

CDN URL Patterns

Construct URLs using these patterns:

# SVG
https://raw.githubusercontent.com/lobehub/lobe-icons/refs/heads/master/packages/static-svg/{light|dark}/{icon-name}.svg

# PNG
https://raw.githubusercontent.com/lobehub/lobe-icons/refs/heads/master/packages/static-png/{light|dark}/{icon-name}.png

# WEBP
https://raw.githubusercontent.com/lobehub/lobe-icons/refs/heads/master/packages/static-webp/{light|dark}/{icon-name}.webp

# Color variant (append -color to icon-name)
https://raw.githubusercontent.com/lobehub/lobe-icons/refs/heads/master/packages/static-png/dark/{icon-name}-color.png

Icon naming convention: Lowercase, hyphenated (e.g., claude, chatglm, openai, huggingface)

Workflow

When users request icons:

  1. Identify icon name (usually lowercase company/model name, hyphenated if multi-word)
  2. Determine format (default: PNG) and theme (default: dark)
  3. Construct CDN URL using pattern above
  4. Provide URL to user
  5. If download requested, use Bash tool with curl
  6. Include web viewer link: https://lobehub.com/icons/{icon-name}

Finding Icon Names

Common icons: See references/icons-list.md for comprehensive list organized by category (Models, Providers, Applications, Chinese AI)

Uncertain names:

  • Browse https://lobehub.com/icons
  • Try variations (e.g., company name vs product name: alibaba vs alibabacloud)
  • Check for -color variants if standard URL fails

Chinese AI models: Support Chinese queries (e.g., "智谱" → chatglm, "月之暗面" → moonshot)

Examples

Single icon request:

User: "Claude icon"
→ Provide: https://raw.githubusercontent.com/lobehub/lobe-icons/refs/heads/master/packages/static-png/dark/claude.png
→ Also mention color variant and web viewer link

Multiple icons download:

curl -o openai.svg "https://raw.githubusercontent.com/lobehub/lobe-icons/.../dark/openai.svg"
curl -o anthropic.svg "https://raw.githubusercontent.com/lobehub/lobe-icons/.../dark/anthropic.svg"

Chinese query:

User: "找一下智谱的图标"
→ Identify: 智谱 = ChatGLM → icon name: chatglm
→ Provide URLs and mention related icons (zhipu, codegeex)

Troubleshooting

If URL returns 404:

  1. Try -color suffix variant
  2. Check alternate naming (e.g., chatgpt vs gpt, google vs gemini)
  3. Direct user to https://lobehub.com/icons to browse
  4. Search repository: https://github.com/lobehub/lobe-icons

Reference Files

  • references/icons-list.md - Comprehensive list of 100+ available icons by category
  • references/developer-info.md - npm installation and React usage examples

> related_skills --same-repo

> doc-to-markdown

Converts DOCX/PDF/PPTX to high-quality Markdown with automatic post-processing. Fixes pandoc grid tables, simple tables, image paths, CJK bold spacing, attribute noise, and code blocks. Benchmarked best-in-class (7.6/10) against Docling, MarkItDown, Pandoc raw, and Mammoth. Trigger on "convert document", "docx to markdown", "parse word", "doc to markdown", "解析word", "转换文档".

> asr-transcribe-to-text

Transcribe audio and video files to text using a remote ASR service (Qwen3-ASR or OpenAI-compatible endpoint). Extracts audio from video, sends to configurable ASR endpoint, outputs clean text. Use when the user wants to transcribe recordings, convert audio/video to text, do speech-to-text, or mentions ASR, Qwen ASR, 转录, 语音转文字, 录音转文字, or has a meeting recording, lecture, interview, or screen recording to transcribe.

> youtube-downloader

Download YouTube videos and HLS streams (m3u8) from platforms like Mux, Vimeo, etc. using yt-dlp and ffmpeg. Use this skill when users request downloading videos, extracting audio, handling protected streams with authentication headers, or troubleshooting download issues like nsig extraction failures, 403 errors, or cookie extraction problems.

> windows-remote-desktop-connection-doctor

Diagnose Windows App (Microsoft Remote Desktop / Azure Virtual Desktop / W365) connection quality issues on macOS. Analyze transport protocol selection (UDP Shortpath vs WebSocket), detect VPN/proxy interference with STUN/TURN negotiation, and parse Windows App logs for Shortpath failures. This skill should be used when VDI connections are slow, when transport shows WebSocket instead of UDP, when RDP Shortpath fails to establish, or when RTT is unexpectedly high.

┌ stats

installs/wk0
░░░░░░░░░░
github stars978
██████████
first seenMar 20, 2026
└────────────

┌ repo

daymade/claude-code-skills
by daymade
└────────────