con un clic
opencode
opencode contiene 46 skills recopiladas de Zakarialabib, con cobertura ocupacional por repositorio y páginas de detalle dentro del sitio.
Skills en este repositorio
Continuously improves the project by checking docs (web, Context7, opencode), using LSPs for code context, monitoring skills/plugins/scripts, and adapting best practices.
Continuity management — preserves context, maintains thermal maps, and serializes states across sessions
Read diffs carefully, identify risks, and produce review feedback that is specific and actionable.
Write accurate docs, keep references current, and capture verified behavior only.
Branching, rebasing, commit hygiene, and review-friendly history for agency delivery.
Use the language server for precise navigation, symbol lookup, refactoring, and diagnostics.
Unit, integration, and regression testing fundamentals for reliable delivery.
Generates workflow YAML on-the-fly for any task using phase templates and keyword analysis. Eliminates the need for pre-defined templates.
Cross-project conventions, architecture decisions, and pattern library for agency workflow consistency.
Agency delivery methodology: spec-first → architect → build → verify. Use on every client feature, API, or UI component.
Multi-step project delivery pipeline orchestration — decompose, delegate, verify, ship.
Convert frontend code (Vite, React, etc.) to a Stitch Design by chaining static HTML extraction, design system extraction, and file upload. **ALWAYS** use this skill when the user's intent is to move existing web apps or React components into Stitch (e.g., requests to "save", "migrate", or "upload"). You must use this skill even for simple "save" operations, as it is the only way to ensure the design system is extracted and assets are properly linked.
Manage design systems in Stitch using MCP tools. Includes retrieval of assets, creating/updating design systems in Stitch, and applying them to screens.
Ensure OpenCode configuration integrity — audits agent files, opencode.json, and skill definitions
Database schema design, SQL optimization, and ORM architecture patterns
Deep domain research and knowledge synthesis — autonomously ingest, synthesize, and structure new technical domains
Pest testing patterns for Laravel/PHP — writing and running tests using Pest 4.x
Security scanning and vulnerability assessment — standardized code security review playbook
Stack detection, context, and cross-stack orchestration — auto-detects Tauri/React/Laravel stack and pulls relevant documentation
Jetpack Compose UI development patterns, component design, state management, and Material 3 theming for Android applications.
ADB-powered debugging, UI inspection, crash analysis, and device diagnostics for Android applications.
Android app deployment workflows covering Play Store releases, CI/CD pipelines, code signing, and Tauri mobile distribution.
Gradle build configuration, dependency management, build variants, and optimization for Android projects using Kotlin DSL and version catalogs.
Comprehensive Android development skill covering Kotlin, Jetpack Compose, Gradle build systems, Clean Architecture, and modern Android development best practices. Serves as the root skill for all Android sub-skills.
Android testing strategies covering unit tests, instrumented tests, UI tests with Compose, and integration testing for Tauri mobile apps.
Write, rewrite, evaluate, and self-improve agent prompts dynamically. Each agent can call this skill to optimize its own context, role, constraints, and output quality over time.
Consolidate digital signage, SignSync, Media OS, SaaS signage, restaurant POS signage, CCTV/media nexus, Tauri desktop, and research documentation into a domain-first, source-traced Media OS knowledge base.
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When OpenCode needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
Professional PDF toolkit with four production lines: (1) Report - structured documents via ReportLab (reports, proposals, contracts, white papers) (2) Creative - visual design via JSON Blueprint → design_engine.py → Playwright snapshot (posters, infographics, invitations, dashboards). The LLM acts as Art Director outputting ONLY JSON spatial blueprints; convert.blueprint compiles to pixel-perfect PDF. (3) Academic - scholarly work via LaTeX/Tectonic (papers, theses, math-heavy documents) (4) Process - manipulate existing PDFs (extract, merge, split, fill forms, convert) Auto-routes based on document type. Includes ATS/creative/academic resume sub-paths.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
UI/UX design intelligence and implementation guidance for building polished interfaces. Use when the user asks for UI design, UX flows, information architecture, visual style direction, design systems/tokens, component specs, copy/microcopy, accessibility, or to generate/critique/refine frontend UI (HTML/CSS/JS, React, Next.js, Vue, Svelte, Tailwind, Laravel, Livewire, PHP). Includes workflows for (1) generating new UI layouts and styling, (2) improving existing UI/UX, (3) producing design-system tokens and component guidelines, and (4) turning UX recommendations into concrete code changes.
Scaffold Laravel 13 features with consistent structure across routes, controllers, form requests, actions/services, models, policies, API resources, migrations, and tests. Use when adding a new Laravel 13 feature, CRUD flow, endpoint, admin module, or refactor target that should follow clean Laravel 13 layering instead of ad hoc file creation.
Presentation creation, editing, and analysis for .pptx files: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes. Academic/paper-based presentations use the embedded Beamer module at end of this file (PDF output only).
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
Professional chart and diagram creation skill. Covers all types of visual data representation and structural diagrams: - **Data charts**: bar charts, line charts, pie charts, scatter plots, heatmaps, radar charts, candlestick charts, boxplots, histograms, area charts, waterfall charts, regression plots, distribution plots, and statistical visualizations. - **Structural diagrams**: flowcharts, mind maps, tree diagrams, org charts, architecture diagrams, network/relationship graphs, ER diagrams, class diagrams, Gantt charts, swimlane diagrams, and sequence diagrams. - **Dashboards**: data dashboards, KPI panels, multi-chart compositions, and interactive visualizations. - **Design quality**: professional color systems, anti-overlap rules, layout optimization, scene-based framework routing (matplotlib, seaborn, ECharts, D3.js, Mermaid, Playwright+CSS), and publication-ready output. Applies when the user wants to create, generate, draw, plot, visualize, or improve any chart, graph, diagram, or dashbo
Coding workflow with planning, implementation, verification, and testing for clean software development.
Create consistent releases and changelogs for Laravel and PHP projects
Multi search engine integration with 8 domestic (CN) search engines. Supports advanced search operators, time filters, site search, and WeChat article search. No API keys required.
Enable OpenCode to analyze its own configuration effectiveness and propose stratigraphic improvements. Invoke when user types /reflect or /upgrade-config.
Security-first skill vetting for AI agents. Use before installing any skill from opencode, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.