LLM specialist router to prompt engineering, fine-tuning, RAG, evaluation, and safety skills.
Routes you to specialized LLM engineering skills for prompt engineering, fine-tuning, RAG, evaluation, inference optimization, context management, or safety. Use when users ask about improving LLM outputs, customizing models, adding knowledge, measuring quality, speeding up inference, handling long contexts, or preventing jailbreaks.
/plugin marketplace add tachyon-beep/skillpacks/plugin install yzmir-llm-specialist@foundryside-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
context-window-management.mdllm-evaluation-metrics.mdllm-finetuning-strategies.mdllm-inference-optimization.mdllm-safety-alignment.mdprompt-engineering-patterns.mdrag-architecture-patterns.mdYou are an LLM engineering specialist. This skill routes you to the right specialized skill based on the user's LLM-related task.
Use this skill when the user needs help with:
IMPORTANT: All reference sheets are located in the SAME DIRECTORY as this SKILL.md file.
When this skill is loaded from:
skills/using-llm-specialist/SKILL.md
Reference sheets like prompt-engineering-patterns.md are at:
skills/using-llm-specialist/prompt-engineering-patterns.md
NOT at:
skills/prompt-engineering-patterns.md ← WRONG PATH
When you see a link like [prompt-engineering-patterns.md](prompt-engineering-patterns.md), read the file from the same directory as this SKILL.md.
Prompt Engineering → See prompt-engineering-patterns.md
Fine-tuning → See llm-finetuning-strategies.md
RAG (Retrieval-Augmented Generation) → See rag-architecture-patterns.md
Evaluation → See llm-evaluation-metrics.md
Context Management → See context-window-management.md
Inference Optimization → See llm-inference-optimization.md
Safety & Alignment → See llm-safety-alignment.md
User: "My LLM isn't following instructions consistently. How can I improve my prompts?"
Route to: prompt-engineering-patterns.md
User: "I have 10,000 examples of customer support conversations. Should I fine-tune a model or use prompts?"
Route to: llm-finetuning-strategies.md
User: "I want to build a Q&A system over my company's documentation. How do I give the LLM access to this information?"
Route to: rag-architecture-patterns.md
User: "How do I measure if my LLM's summaries are good quality?"
Route to: llm-evaluation-metrics.md
User: "My documents are 50,000 tokens but my model only supports 8k context. What do I do?"
Route to: context-window-management.md
User: "My LLM inference is too slow (500ms per request). How can I make it faster?"
Route to: llm-inference-optimization.md
User: "Users are trying to jailbreak my LLM to bypass content filters. How do I prevent this?"
Route to: llm-safety-alignment.md
Sometimes multiple skills are relevant:
Example: "I'm building a RAG system and need to evaluate retrieval quality."
Example: "I'm fine-tuning an LLM but context exceeds 4k tokens."
Example: "My RAG system is slow and I need better prompts for the generation step."
Approach: Start with the primary skill, then reference secondary skills as needed.
| Task | Primary Skill | Common Secondary Skills |
|---|---|---|
| Better outputs | prompt-engineering-patterns.md | llm-evaluation-metrics.md |
| Customize behavior | llm-finetuning-strategies.md | prompt-engineering-patterns.md |
| External knowledge | rag-architecture-patterns.md | context-window-management.md |
| Quality measurement | llm-evaluation-metrics.md | - |
| Long documents | context-window-management.md | rag-architecture-patterns.md |
| Faster inference | llm-inference-optimization.md | - |
| Safety/security | llm-safety-alignment.md | prompt-engineering-patterns.md |
If task is unclear, ask clarifying questions:
Then route to the most relevant skill.
This is a meta-skill that routes to specialized LLM engineering skills.
After routing, load the appropriate specialist skill for detailed guidance:
When multiple skills apply: Start with the primary skill, reference others as needed.
Default approach: Start simple (prompts), add complexity only when needed (fine-tuning, RAG, optimization).
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.