DeFi

Execute configuration-driven analysis workflows from YAML files. Use for running analysis pipelines, data processing tasks, and automation workflows defined in YAML configuration.

Follow these patterns when implementing MLOps features in OptAIC. Use for ML model definitions (5-component structure), model instances, training/inference pipelines, model registry, and monitoring. Covers signal models, macro regime models, relevance models, and signal combining/filtering models.

Knowledge graph-based text replacement using Terraphim hooks.Intercepts commands and text to apply transformations defined in the knowledge graph.Works with Claude Code PreToolUse hooks and Git prepare-commit-msg hooks.

Generate detailed API contracts and specifications including OpenAPI/Swagger definitions, endpoint documentation, and integration guidelines

Production-tested setup for Content Collections - a TypeScript-first build tool that transformslocal content files (Markdown/MDX) into type-safe data collections with automatic validation.Use when: building blogs, documentation sites, or content-heavy applications with Vite + React,setting up MDX content with React components, implementing type-safe content schemas with Zod,migrating from Contentlayer, or encountering TypeScript import errors with content collections.Covers: Vite plugin setup, tsconfig path aliases, collection schemas with Zod validation,MDX compilation with compileMDX, transform functions for computed properties, rehype/remark plugins,React component integration with MDXContent, Cloudflare Workers deployment, and production build optimization.Keywords: content-collections, @content-collections/core, @content-collections/vite,@content-collections/mdx, MDX, markdown, Zod schema validation, type-safe content,frontmatter, compileMDX, defineCollection, defineConfig, Vite plugin, tsco

Develop AI agents, tools, and workflows with Mastra v1 Beta and Hono servers. This skill should be used when creating Mastra agents, defining tools with Zod schemas, building workflows with step data flow, setting up Hono API servers with Mastra adapters, or implementing agent networks. Keywords: mastra, hono, agent, tool, workflow, AI, LLM, typescript, API, MCP.

⚡ PRIMARY TOOL for: 'how does X work', 'find implementation of', 'trace data flow', 'where is X defined', 'audit integrations', 'find all usages'. Uses claudemem v0.3.0 AST with callers/callees analysis. GREP/FIND/GLOB ARE FORBIDDEN.

Generates evolution contracts for skills, defining what can be updated, what must remain stable, and how to extract knowledge. Use when creating new skills or formalizing update rules for existing skills. Adds a "Skill Contract" section to SKILL.md that guides skill-updater during project work.

Manages the specification-driven development workflow. Use this skill when the user runs /orbit,requests to "define feature", "create plan", "implement", or needs workflow guidance.It detects the current phase from artifacts and executes the appropriate action.

Generate complete multiplayer games for GameBuddies.io platform with full integration including streamer mode, lobby system, chat, WebRTC video, and real-time gameplay. Creates server logic, client UI, type definitions, and game mechanics following GameBuddies template patterns.

Use when defining brand motion identity, creating animation guidelines for brand expression, or aligning animation with brand personality.

Search for Lean 4 and Mathlib theorems, lemmas, and definitions by type signature, name, or subexpression pattern. Use when the user asks to find a theorem, look up a Lean definition, search for lemmas, or needs help discovering Mathlib functions.

Structure n8n nodes correctly with INodeTypeDescription, resource-operation patterns, and proper package.json configuration. Use this skill when creating new *.node.ts files, defining INodeTypeDescription properties, implementing resource and operation parameters, building trigger nodes, organizing complex nodes into actions folders, or configuring the n8n section in package.json. Apply when choosing between declarative and programmatic styles, setting up node metadata, or structuring community node packages.

Guide for creating and configuring custom sub-agents for Claude Code. Use this skill when you need to define specialized agents with dedicated system prompts, tool sets, and models to handle specific tasks.

Standards for writing CLAUDE.md and modular rules files (.claude/rules/) that maximize LLM execution efficiency. Use when creating or editing project instructions, defining conventions, or optimizing agent behavior for determinism and token efficiency. Focuses on eliminating ambiguity and producing consistent agent execution.

Implement step definitions for Gherkin scenarios, translating Given/When/Then into executable test code. Use after write-scenario when scenarios are defined but step definitions are missing.

Run user-defined macOS Shortcuts for custom automation workflows. Use when user wants to trigger a Shortcut by name or execute a custom automation.

Design database models with proper naming, data types, constraints, and relationships. Use this skill when creating or modifying ORM models, database schemas, or entity definitions. When working on files like models.py, models/, entities/, schemas/, or any file defining database tables and their relationships. When adding timestamps, foreign keys, indexes, or validation constraints. When defining model relationships (one-to-many, many-to-many) or cascade behaviors.

Use when translating a program/app idea into a VibeDev MCP Job (deliverables, definition of done, invariants, and a small step plan) and preparing it to transition to READY without implementing features yet

Detect and fix violations of project instructions defined in .claude/rules/. Use when checking code compliance, reviewing changes, or when the user asks about instruction violations.