區塊鏈

Use this skill when exploring codebase architecture or planning new features requiring models/enums.AUTO-ACTIVATE when user mentions (FR/EN): - modèle, model, models, enum, enums, schema, Prisma schema - architecture, domain, domaine, existe, exists, available, disponible - créer, create, ajouter, add, nouveau, new, nouvelle feature - quel modèle, what model, which model,quel enum - 121 modèles, 87 enums, Planning, Leave, Business RulesThis skill provides INSTANT lookup (500 tokens vs 15k for full ERD) for 121 models and 87 enums.

Follow these patterns when designing guardrails validation contracts in OptAIC. Use for signal bounds, dataset schemas, portfolio constraints, PIT validation, and other domain-specific validation rules. Covers the "Law vs Police" architecture where Definitions contain contracts and the Engine enforces them.

Design and build reusable, composable UI components following the single responsibility principle with clear prop interfaces and proper state management. Use this skill when creating or modifying React components, Vue components, Svelte components, web components, or any modular UI building blocks. Use this skill when implementing component composition patterns, defining component props and interfaces, managing local component state, or creating component documentation. Use this skill when working with component files in components/, widgets/, views/, or pages/ directories. Use this skill when refactoring large components into smaller composable pieces, establishing component naming conventions, or designing component APIs for reusability across different contexts.

Manage the content pipeline and idea backlog. Use when checking pipeline status, evaluating pillar distribution, reviewing idea statuses, or planning content calendar. Includes idea template, pillar definitions, and frontmatter schemas.

Use this skill when integrating Cloudflare Zero Trust Access authentication with Cloudflare Workers applications. Provides Hono middleware setup, manual JWT validation patterns, service token authentication, CORS handling with Access, and multi-tenant configurations. Prevents 8 common errors including CORS preflight blocking (45 min saved), key cache race conditions (20 min), missing JWT headers (30 min), and dev/prod team mismatches (15 min). Saves ~58% tokens (3,250 tokens) and 2.5 hours per implementation. Covers user authentication flows, service-to-service auth, geographic restrictions, role-based access control, and Access policy configuration.Keywords: Cloudflare Access, Zero Trust, Cloudflare Zero Trust Access, Access authentication, JWT validation, access jwt, service tokens, hono cloudflare access, hono-cloudflare-access middleware, workers authentication, protect worker routes, admin authentication, access policy, identity providers, azure ad access, google workspace access, okta access, github a

This skill should be used when the user asks to "write a spec", "create a specification", "define acceptance criteria", "break down a feature", "write user stories", or needs guidance on structuring feature requirements. Provides patterns for effective spec writing and task decomposition.

Design and implement RESTful API endpoints following best practices for URL structure, HTTP methods, status codes, and versioning. Use this skill when creating or modifying API routes, controllers, or endpoint handlers. When working on files like routes.py, api.py, controllers/, endpoints/, or any file defining HTTP endpoints. When designing URL patterns, choosing HTTP methods (GET, POST, PUT, PATCH, DELETE), implementing pagination, filtering, or sorting. When adding rate limiting headers or API versioning strategies.

Define database models with clear naming, proper data types, validation, relationships, and constraints to ensure data integrity. Use this skill when creating or modifying ORM model files, database schema definitions, model class files, or entity files. Use this when defining model relationships (has-many, belongs-to, many-to-many), setting up database constraints (NOT NULL, UNIQUE, foreign keys), adding timestamps and indexes, implementing model-level validations, or choosing appropriate data types for fields. Use this when working on files in directories like models/, entities/, app/models/, or any file that defines database table structures and relationships.

Production-tested integration patterns for connecting React frontends to Cloudflare Worker backendswith Hono, Clerk authentication, and D1 databases. Prevents common frontend-backend connection issues,CORS errors, auth token failures, and race conditions.Use when: connecting frontend to backend, implementing auth flow, setting up API calls,troubleshooting CORS, fixing race conditions, auth tokens not passing, frontend-backend connection errors,401 errors, integrating Clerk with Workers, setting up full-stack Cloudflare app, vite cloudflare plugin setup.Prevents: CORS errors, 401 Unauthorized, auth token mismatches, race conditions with auth loading,environment variable confusion, frontend calling wrong endpoints, JWT verification errors, D1 connection issues.Keywords: frontend backend integration, Cloudflare Workers, Hono, Clerk auth, JWT verification, CORS, React API client,race conditions, auth loading, connection issues, full-stack integration, vite plugin, @cloudflare/vite-plugin,D1 database,

Master product strategy, market analysis, competitive positioning, and long-term product vision. Define business models and craft go-to-market strategies that drive success.

Specialized agent for BarqNet backend development. Focuses on Go backend API development, PostgreSQL database management, authentication systems, JWT tokens, OpenVPN integration, and production-ready backend architecture. Use this skill when working on server-side code, API endpoints, database migrations, or backend infrastructure.

Guide users through discovering and defining system architecture through structured conversation. Triggers on "I want to build", "design a system", "architect", "planning a new project", "how should I build X".

MoAI-ADK's foundational principles - TRUST 5, SPEC-First TDD, delegation patterns, token optimization, progressive disclosure, modular architecture, agent catalog, command reference, and execution rules for building AI-powered development workflows

Use when creating or modifying Tamagui UI components in packages/ui. Enforces design token usage, theme compatibility, and cross-platform considerations.

Guide developers through property-based testing including property definition, shrinking, and framework-specific implementation

Linux VM bootstrap verification skill. MUST BE USED when setting up new VMs or verifying environment.Supports modes: check (warn-only), install (operator-confirmed), strict (CI-ready).Enforces Linux-only + mise as canonical; honors preference brew→npm (with apt fallback).Verifies required tools: mise, node, pnpm, python, poetry, gh, railway, bd, tmux, jq, rg.Handles optional tools as warnings: tailscale, playwright, docker, bv.Never prints/seeds secrets; never stores tokens in repo/YAML; Railway vars only for app runtime env.Safe on dirty repos (refuses and points to dirty-repo-bootstrap skill, or snapshots WIP branch).Keywords: vm, bootstrap, setup, mise, toolchain, linux, environment, provision, verify, new vm

Recursive meta-skill that detects workflow patterns and automatically generates Claude Code agent definitions. Use when user invokes /create-agent or patterns warrant new agent.

Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens. | Sử dụng khi: AI, LLM, vision, embedding, phân tích hình ảnh, Gemini API.

Database management with Prisma (schema, migrations, optimization). TRIGGERS: 'Prisma', 'schema', 'migration', 'database', 'query optimization', 'modelo de dados'. Use when modifying database schema, creating migrations, optimizing queries, troubleshooting database issues, data modeling.

Review test cases for UserInfo Endpoint. Covers access token validation, Bearer token handling, sub claim consistency, scope-based claims, and signed responses per OIDC Core 1.0 Section 5.3.