opencode-mastery

Persistent memory system with .memory.md, compaction, and cross-project sync

Analyzes sessions using ACE framework to generate prompt improvement suggestions focused on durable patterns.

Database technology selection and architecture - choose between SQL vs NoSQL, PostgreSQL vs MySQL vs MongoDB, scaling strategies, migration planning. Use for database DECISIONS. For PostgreSQL implementation use postgresql skill.

Analyze feature flows for completeness, preconditions, and branch coverage using reusable flow-analyzer tools.

Automated post-phase validation workflow for GSD phases with deterministic gates and HITL controls.

Full workflow orchestration with config-driven routing and phase-based execution

Complete OpenCode knowledge base with live documentation access. Use for questions about OpenCode CLI, skills, plugins, tools, agents, SDK, or configuration. Automatically searches official docs via Context7 API with local fallback.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when navigating websites, interacting with web pages, filling forms, testing web applications, or extracting information.

PostgreSQL implementation - schema design, data types, indexing, partitioning, JSONB, performance optimization, extensions (pgvector, postgis). Use for PostgreSQL CODE. For database selection decisions use database-architect skill.

Analyze GitHub repositories for architecture, patterns, and code quality. Use when user asks to analyze, review, or understand a GitHub repository.

shadcn-svelte component library - install Button, Card, Dialog, Form, Table components with shadcn design tokens. Use for pre-built accessible UI components. For raw Tailwind CSS use tailwind skill. For UX design principles use frontend-design skill.

Design, create, audit, and optimize OpenCode skills using a quality-first workflow with dry-run, quality gates, and structured references. Use when users ask to build or improve a skill. Do not trigger for generic OpenCode Q&A or unrelated coding tasks.

Svelte CLI (sv) - project scaffolding, add-ons installation, dev/build commands. Use when creating new Svelte/SvelteKit projects or adding features via CLI. For Svelte code questions use svelte skill. For SvelteKit routing use svelte-kit skill.

SvelteKit framework - file-based routing, load functions, server endpoints, form actions, hooks, adapters, SSR/SSG, and deployment. Use for SvelteKit-specific features. For Svelte reactivity/components use svelte skill. For project scaffolding use svelte-cli skill.

Svelte MCP server - AI-assisted Svelte development with documentation access, svelte-autofixer analysis, and playground links. Use specifically for MCP server features. For Svelte code use svelte skill. For SvelteKit use svelte-kit skill.

Svelte core concepts - reactivity ($state, $derived, $effect), components, stores, transitions, and animations. Use for Svelte language questions. For SvelteKit routing/server features use svelte-kit skill. For CLI/scaffolding use svelte-cli skill.

Enforce Test-Driven Development discipline. Write failing test first, then minimal code, then refactor. Use when writing production code or implementing features. Do not use for debugging, documentation, or configuration tasks.

UI/UX design principles for developers - visual hierarchy, spacing, contrast, accessibility (WCAG), component states, interaction patterns, forms, mobile UX. Use for design decisions and UX guidance. For Tailwind CSS use tailwind skill. For shadcn components use shadcn-svelte skill.

Tailwind CSS v4 utility classes - @theme, @utility, @plugin, grid, container queries, flexbox, spacing, responsive design. Use for CSS-only styling with Tailwind utilities. For pre-built components use shadcn-svelte skill. For UX principles use frontend-design skill.

Enforce systematic debugging to find root causes. Always investigate before fixing. Prevents symptom fixes and random changes. Use when debugging errors or investigating failures. Do not use when already investigated or for TDD/test-first development.

Implements a sophisticated multi-paradigm data transformation pipeline with configurable ETL stages, supporting both batch and streaming modalities across heterogeneous data sources with automatic schema inference and adaptive type coercion mechanisms.

Cleans, validates, and transforms CSV files for analysis. Use when user says "clean this CSV", "fix my data", "prepare this spreadsheet for analysis", "validate this dataset", or uploads a .csv file that needs processing.

Plans and creates sprint tasks in Linear from project context. Use when user says "plan this sprint", "create sprint tasks", "help me plan the next sprint", or "break this down into tickets". Works with Linear MCP for task creation.

Generate OpenCode commands, skills, agents, or plugins when users ask to create/build/scaffold OpenCode components or tooling workflows. Use when deciding between command vs skill vs agent vs plugin. Do not trigger for general OpenCode Q&A or troubleshooting.

Demonstrates helper script integration with sequential execution

Demonstrates the absolute basics of an OpenCode skill