Claude Code Skills Marketplace is a collection and marketplace of skills, plugins, agents, and instructions that extend Claude Code with specialized development workflows. It is for developers who want to install existing workflows or create, validate, and package their own Claude Code skills.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add daymade/claude-code-skills --skill llm-icon-findergit clone --depth 1 https://github.com/daymade/claude-code-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/daymade/claude-code-skills/llm-icon-finder)<a href="https://agentmods.dev/skills/daymade/claude-code-skills/llm-icon-finder"><img src="https://agentmods.dev/badge/skills/daymade/claude-code-skills/llm-icon-finder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/daymade/claude-code-skills/llm-icon-finder"><img src="https://agentmods.dev/badge/skills/daymade/claude-code-skills/llm-icon-finder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00061 | $0.00886 |
| Opus 5.5 | $0.00024 | $0.00354 |
| Sonnet 5.5 | $0.00012 | $0.00177 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
llm-icon-finder scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
5. If download requested, use Bash tool with curl How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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:
- Identify icon name (usually lowercase company/model name, hyphenated if multi-word)
- Determine format (default: PNG) and theme (default: dark)
- Construct CDN URL using pattern above
- Provide URL to user
- If download requested, use Bash tool with curl
- 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:
alibabavsalibabacloud) - Check for
-colorvariants 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
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 91 lines · 61 tokens per session scan A fe87e210af1e
llm-icon-finder is a skill published in the GitHub repository daymade/claude-code-skills (1,493 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 886 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
plan
Use when a request needs shaping before any code is written — a rough or vague prompt to sharpen, an ambiguous idea to design, or a clear-enough task to decompose. One chain-starter that amplifies the prompt, designs the approach, and decomposes it into a batched task file, skipping whichever phases the request…
dstack-prototyping
Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven. Guides task-first prototyping on real hardware, choosing fleets/backends that can reuse idle instances and caches, checking vLLM/SGLang sources, and verifying the final…
senior-data-engineer
World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, real-time streaming, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, Flink, Kinesis, and modern data stack. Includes data modeling, pipeline orchestration, data quality, streaming quality…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
bim-classification-ai
Classify BIM elements using AI and standard classification systems. Map elements to UniFormat, MasterFormat, OmniClass, and CWICR codes.
a11y-keyboard-playwright
Write keyboard-only test variants and focus management checks using Playwright: navigation patterns, focus expectations, helpers, and file structure conventions.