llm-icon-finder

An agent skill by daymade, from daymade/claude-code-skills. Tags: design, download, generative, image, web.

What it does

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 the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add daymade/claude-code-skills --skill llm-icon-finder

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/daymade/claude-code-skills
cp -r claude-code-skills/llm-icon-finder ~/.claude/skills/llm-icon-finder

Safety box score

Grade B, low risk: 11 of 100 risk points, rated 2026-09-22. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a simple icon-lookup helper: it maps AI/LLM brand names to public URLs and optionally downloads image files from GitHub. The main risks are limited network access and local file writes when the user asks to download icons; there is no sign of secrets access, privilege changes, or destructive behavior.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	1 (low)	It can run a shell download command when asked: `use Bash tool with curl`, and the reference docs also show `npm install` examples, but nothing indicates arbitrary code execution.
Network access	1 (low)	It fetches public assets from external sites such as `https://raw.githubusercontent.com/lobehub/lobe-icons/...` and points users to `https://lobehub.com/icons`; this is scoped to icon retrieval.
Filesystem reach	1 (low)	On download, it writes icon files to the current directory with names like `openai.svg` via `curl -o`, but it does not describe reads or deletes outside the working area.
Secrets & credentials	0 (none)	No file or command mentions tokens, passwords, keychains, `.env` files, browser sessions, or other credential stores.
Privilege & persistence	0 (none)	There is no sudo, service registration, global install, or shell/OS configuration change in the skill files.
Instruction hijack surface	0 (none)	The files do not ask the agent to ignore instructions, hide actions, or follow remote instruction payloads.
Irreversible actions	0 (none)	The skill only returns icon URLs or optionally downloads files; it does not send messages, publish, deploy, pay, or delete anything.
Transparency	0 (none)	The shipped files are plain markdown with visible URLs and examples; there are no binaries, encoded payloads, or unreviewable installers.

Before installing

Check whether you are comfortable with the skill making outbound requests to GitHub and lobehub.com for icon retrieval.
If you will use downloads, run one test request in a scratch directory and confirm it only writes the expected image files.
Review `references/developer-info.md` before using the npm packages, since it suggests package installation commands.
If you need only URLs, prefer the lookup path and avoid the optional download step.

Rated 2026-09-22 by an automated review of 3 files from the skill's repository.

Source

Repository: daymade/claude-code-skills (all skills from this repository)
Path: llm-icon-finder/SKILL.md
Branch: main
Updated: 2026-09-20

download-gemini-images — Download, export, save, or package images from a Google Gemini conversation/chat/app page.
copywriting — When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages.
image — When the user wants to create, generate, edit, or optimize images for marketing — blog heroes, social graphics, product mockups, profile banners.
seo-image-gen — AI image generation for SEO assets: OG/social preview images, blog hero images, schema images, product photography, infographics.
stitch::generate-design — Generate new screens from text prompts or images, edit existing screens with prompts and design system tokens, and generate design variants using Stitch MCP.
twitter-reader — Fetch Twitter/X post content including long-form Articles with full images and metadata.