Agent skills for Claude Code

LLM integration patterns including API usage, streaming, function calling, RAG pipelines, and cost optimization

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 Tuning Patterns

Review and control AI Agent changes to a local Markdown, Obsidian, or Open Knowledge Format wiki.

Compile a Raw source into concise, linked Wiki notes.

Validate Wiki and source note health. Use before commits, after ingests, or when notes were edited by hand.

Answer questions from the compiled Wiki.

Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests…

Creates slash commands from procedural doc sections.

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.

Configures Swagger/OpenAPI documentation for backend APIs.

Upgrades dependencies across all detected package managers.

Reduces JS/TS bundle size via tree-shaking, code splitting, and unused dependency removal.

Restore a previously saved mix snapshot

Agent skill for load-balancer - invoke with $agent-load-balancer