opencode-config

Sincroniza automáticamente los cambios de configuración de OpenCode al repositorio remoto en GitHub de forma silenciosa.

Browser automation skill for Chrome/Chromium using agent-browser. Use when the user needs to open sites, click elements, fill forms, take screenshots, extract page data, test web apps, log in, or automate browser flows in Chrome/Chromium. Triggers include requests to open a website, submit a form, click a button, take a screenshot, scrape a JS-rendered page, or interact with a site programmatically. Do not use for Chrome DevTools-first debugging of a live Chrome session, selected-element inspection, console/network/Lighthouse/performance/memory analysis (use chrome-devtools-mcp), Firefox/WebKit/Edge or cross-browser verification (use playwright-mcp), API-only testing without a browser, direct HTTP requests, or static scraping that does not need JavaScript rendering.

Audit, enhance, and restructure a project's AI agent configuration files (AGENTS.md, CLAUDE.md, .cursorrules). Use when setting up a new project for AI-assisted development, when agent behavior is poor, or when asked to tune agent config, improve AGENTS.md, set up CLAUDE.md, configure this project for AI coding, sharpen agent rules, or tune agent md. DO NOT use for: editing application code, creating skills (use skill-creator), security audits (use security-auditor), or general documentation.

Use when designing new high-level system architecture, reviewing existing designs, or making architectural decisions. Invoke to create architecture diagrams, write Architecture Decision Records (ADRs), evaluate technology trade-offs, design component interactions, and plan for scalability. Use for system design, architecture review, microservices structuring, ADR authoring, scalability planning, and infrastructure pattern selection — distinct from code-level design patterns or database-only design tasks.

Analyzes code diffs and files to identify bugs, security vulnerabilities (SQL injection, XSS, insecure deserialization), code smells, N+1 queries, naming issues, and architectural concerns, then produces a structured review report with prioritized, actionable feedback. Use when reviewing pull requests, conducting code quality audits, identifying refactoring opportunities, or checking for security issues. Invoke for PR reviews, code quality checks, refactoring suggestions, review code, code quality. Complements specialized skills (security-reviewer, test-master) by providing broad-scope review across correctness, performance, maintainability, and test coverage in a single pass.

Fetch official library docs via Context7 MCP. Use for Tailwind CSS docs (grid, responsive variants), React, Next.js, Vue, MCP, OpenCode, or any npm library. Always use before external web search. DO NOT use for: general web search, non-library code questions, internal/proprietary API documentation, or when the user already has the docs locally.

Use when building high-performance async Python APIs with FastAPI and Pydantic V2. Invoke to create REST endpoints, define Pydantic models, implement authentication flows, set up async SQLAlchemy database operations, add JWT authentication, build WebSocket endpoints, or generate OpenAPI documentation. Trigger terms: FastAPI, Pydantic, async Python, Python API, REST API Python, SQLAlchemy async, JWT authentication, OpenAPI, Swagger Python.

Use when building cross-platform applications with Flutter 3+ and Dart. Invoke for widget development, Riverpod/Bloc state management, GoRouter navigation, platform-specific implementations, performance optimization.

Use when building game systems, implementing Unity/Unreal Engine features, or optimizing game performance. Invoke to implement ECS architecture, configure physics systems and colliders, set up multiplayer networking with lag compensation, optimize frame rates to 60+ FPS targets, develop shaders, or apply game design patterns such as object pooling and state machines. Trigger keywords: Unity, Unreal Engine, game development, ECS architecture, game physics, multiplayer networking, game optimization, shader programming, game AI.

GitHub operations via gh CLI. Use for pull requests/PRs, GitHub code search, or drafting exact gh commands (owner/repo, gh pr list, gh search). Always use instead of WebFetch for github.com. DO NOT use for: local-only git operations, non-GitHub remotes (GitLab, Bitbucket), or reading repository file content that is already available locally.

Port and process management via port-whisperer CLI. Use when asked about port conflicts, orphaned dev servers, zombie processes, what's running on a port, killing a process on a port, cleaning up dev processes, or diagnosing "port already in use" errors. Triggers: "what's on port 3000", "kill port", "orphaned process", "zombie", "port conflict", "clean up dev servers", "what's running", "ports". DO NOT use for: network diagnostics, firewall rules, remote server management, or non-port-related process management.

Pre-deployment security audit for production releases and PR checks. Use BEFORE deploying to production/staging or when asked for a changed-only audit. Triggers: "deploy to production", "release", "pre-release", "security check", "merge to main", "audit before deploy", "security audit", "PR security audit", "changed-only audit". DO NOT use for: local dev, sandbox, feature branch testing. Requires fixing CRITICAL vulnerabilities before proceeding. Supports monorepos with scoped audits per app/package.

Create/scaffold agent skills (SKILL.md outline, file layout/folder structure, quick scaffold). Use when asked to create or scaffold a skill, to package steps into a reusable skill, run evals to test a skill, benchmark skill performance, optimize a skill's description for better triggering accuracy, or when the user says "use the skill-creator skill" / "skill-creator". DO NOT use for: general coding tasks, non-skill file creation, editing files unrelated to skill development, or modifying existing application code.