Claude Skills

Design and architect Obsidian plugins with proper structure, patterns, and best practices

Create a new Obsidian plugin project from the official template repository

Prisma relation modeling patterns

Spawnable research agent. Accepts research requests and uses the zotero-chunk-rag MCP server to search indexed PDFs. Callers spawn this via Task -- do not invoke directly.

ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.

Generate PROJECT-MAP.auto.scm by extracting structure from codebases. Invoke when user requests project mapping, structure extraction, or needs to create/update .phi maps.

Auto-invoked compositional project analysis using φ = ∫(structure × semantics × memory). Analyzes codebase using three integrated layers - structure, semantics, and memory - for understanding project layout, architecture, and accumulated insights.

On first run after claudesync setup, offer to install recommended plugins

Systematic peer review toolkit. Evaluate methodology, statistics, design, reproducibility, ethics, figure integrity, reporting standards, for manuscript and grant review across disciplines.

This skill should be used when the user asks to "split PDF by chapters", "divide book into chapters", "extract chapters from PDF", or "break PDF into sections". Splits PDF documents based on table of contents or text patterns using pypdf.

Combine 5 independent judge verdicts into actionable final recommendation.

Address feedback from pull request reviews systematically and efficiently

This skill should be used when the user asks to "run codex", "use codex CLI", "delegate to codex", "codex resume", or "continue with codex". Executes tasks via OpenAI Codex CLI with model selection, reasoning effort configuration, and session management.

This skill should be used when the user asks to "explore claude code source", "find internal features", "investigate cli.js", "check beta headers", "discover hidden settings", or mentions "minified code analysis", "anthropic-beta headers", "context management internals".

This skill should be used when the user asks to "lookup Amplitude user", "find user by device ID", "get user activity from Amplitude", or "search Amplitude user events". Queries Amplitude REST API for user data using Device ID or User ID.

This skill should be used when the user asks to "collect Linear activity", "generate Linear report", "show my Linear issues", "what did I work on in Linear", or requests activity summaries from Linear for specific date ranges. Provides workflow for collecting issues, projects, and cycles via Linear MCP.

Use when you have a spec or requirements for a multi-step task, before touching code

Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".