By Alex-Kopylov
LLM application design, agent pattern selection, and schema-guided reasoning patterns.
Use this skill when designing Pydantic models that guide LLM reasoning through structured output. Triggers include "schema-guided reasoning", "SGR", "structured reasoning schema", "pydantic structured output", "reasoning steps schema", "constrained decoding", "step-by-step schema", "LLM reasoning pipeline", "discriminated union for tool routing", "tool-calling schema design", or any situation where the user wants to improve LLM accuracy by defining the shape of the output. Also use when the user builds Pydantic models for OpenAI/Anthropic structured output and wants to maximize reasoning quality, designs agent tool dispatch with discriminated unions, or structures chain-of-thought via field ordering — even if they don't mention SGR by name.
Use when choosing LLM agent or LLM workflow design patterns for a presented problem, decomposing an LLM-based system into stages, comparing candidate agent architectures, selecting execution topologies such as chain, route, parallel, orchestrate, loop, or hierarchy, or producing a final recommendation for which patterns fit each stage. Also use when the user asks for agent architecture trade-offs, pattern selection, workflow decomposition, multi-agent design, reflection or governance patterns, or a framework-neutral way to decide how an LLM system should be structured.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub alex-kopylov/zweihander --plugin llm-application-devGenerate and validate Mermaid diagrams with synced syntax references.
Skills for listing and inspecting OpenAPI endpoints on running services.
Python-specific pytest, Redis test patterns, Celery, and unit-test review/execution agents.
Dropbox, Google Drive, OneDrive, and MEGA style user-file storage tools.
Research knowledge-base and Obsidian vault workflows for agent-maintained notes.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Memory compression system for Claude Code - persist context across sessions
Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, ad creative, and growth
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.