Use for authorized security assessment of LLM applications and AI agents, including prompt injection, tool abuse, RAG exposure, memory…
Use when: (1) Entering an LLM-based Kaggle competition (open-source model required, prompt engineering, few-shot), (2) Need to choose…
Configure RuVLLM local inference with model selection, MicroLoRA fine-tuning, and SONA adaptation
Harden an LLM application against unbounded consumption with input/output caps, token budgets, rate limiting, and cost controls.
This skill should be used when the user asks about "LLM gateway", "Bankr LLM", "LLM credits", "top up credits", "auto top-up"…
Classify leads using LLM for complex distinctions like product SaaS vs agencies.
Use when improving prompts for any LLM. Applies proven prompt engineering techniques to boost output quality, reduce hallucinations, and…
Audit and improve public static websites so LLM agents and crawlers can discover, retrieve, and understand their content without depending…
Parse SGLang/vLLM startup logs to explain GPU memory use and request capacity.
LLM streaming response patterns. Use when implementing real-time token streaming, Server-Sent Events for AI responses, or streaming with…
LLM Tuning Patterns
Compile a Raw source into concise, linked Wiki notes.
Manages lightweight, folder-based Markdown knowledge bases with fast offline vector search, BM25 indexing, and automated AI note ingestion.
Validate Wiki and source note health. Use before commits, after ingests, or when notes were edited by hand.
Routine maintenance and safe commits. Use when committing changes, rebuilding indexes, or checking overall vault health.
Answer questions from the compiled Wiki.
LLMs and Generative AI: 83 concepts, no maths assumed.
Generates seed data from ORM schemas or entity definitions to any target format.
Removes platform-specific artifacts from Replit, StackBlitz, CodeSandbox, Glitch.
Generates GitHub Actions CI workflow configuration.
Configures ESLint, Prettier, Ruff, mypy, and .NET analyzers.