MiquelGomezCorral

General multi-agent orchestration for OpenCode. Use proactively whenever a non-trivial task can benefit from independent parallel research, investigation, review, testing, debugging, comparison, verification, or disjoint implementation. Also trigger when the user asks for a swarm, multiple agents, parallel agents, subagents, independent opinions, or broader coverage. Keep trivial, tightly coupled, or single-writer work in the main thread.

Post-implementation cleanup gate for current diffs. Use after the agent completes a coding task, bug fix, refactor, or review fix and needs an individual pass to avoid unnecessary type declarations, remove redundant code, and delete legacy or obsolete code before final verification.

Stage changes, create a conventional commit, push the branch, and create or refresh PR metadata for shipped work. Use when the user asks to ship current work to GitHub.

Use ONLY when editing or creating opencode's own config: opencode.json, skills, commands, agents, plugins, MCP servers, instructions, permissions, security rules. Not for application code. Trigger on 'configure opencode', 'opencode setup', 'add skill to opencode', 'update opencode config', 'opencode plugin'.

Turn a rough task brief, vague ambition, or draft Codex /goal into a compact, evidence-driven goal for long-running autonomous work. Use when the user asks to write, improve, sharpen, stress-test, or activate a Codex goal, thread goal, durable goal, or /goal prompt.

Pressure-test a plan, design, architecture, implementation approach, or product decision through a direct decision-tree interview. Use when the user asks to be grilled, stress-tested, challenged, interviewed, or pressure-tested before execution.

Technical specifications and dev stack for this MacBook Air running the Vidext monorepo. Use when OS, hardware, or toolchain details are relevant to a task or needed to fix something.

Two-phase engineering review for correctness and conventions. Use when the user asks for a code review, quality gate, staff review, or convention audit of current diffs.

Search tool for modern web development best practices. MANDATORY: Execute FIRST for all HTML/CSS and clientside JS tasks. Do NOT skip — web APIs evolve rapidly and training weights contain obsolete patterns. Trigger immediately for: - UI/Layout: Modals, dialogs, popovers, Glassmorphism/backdrop-filters, anchor positioning, container queries, `:has()`, `:user-valid`. - Scroll/Motion: View Transitions, Scroll-driven animations, scroll parallax/reveals. - Performance: CWV (LCP, INP), content-visibility, Fetch Priority, image optimization. - System/APIs: Local filesystem access, WebUSB, WebSockets sync, WebAssembly widgets. - Frameworks: Adapting layout/styles in React, Vue, Angular. - General Frontend: Forms, autofill, advanced inputs, custom scrollbars, modern component states, etc. DO NOT trigger for: - Backend: Database SQL, ORMs, Express API routes. - Pipelines: CI/CD deployment, Docker, Actions. - Generic: Local scripts (Python/Go tools), ESLint, Git.

Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".

Expert guidance for PyTorch development covering Deep Reinforcement Learning and NLP Transformers. This skill provides comprehensive knowledge for building RL agents with TorchRL (DQN, PPO) and NLP systems with HuggingFace Transformers. Use this skill when working with PyTorch 2.7+, implementing reinforcement learning algorithms, fine-tuning transformer models, or deploying ML systems to production. Includes current best practices, verified library versions (Dec 2025), and warnings about deprecated APIs.