Database

code-review

by xmx0632

审查 Java 代码，检查规范、潜在问题和优化建议。Code Review 时使用。

migration-upgrader

by k1lgor

Use this when the user wants to migrate between libraries, upgrade major versions, or move from one framework to another. Generate step-by-step migration plans and code updates.

architecture-decision-records

by baotoq

Write and maintain Architecture Decision Records (ADRs) following best practices for technical decision documentation. Use when documenting significant technical decisions, reviewing past architectural choices, or establishing decision processes.

architecture-decision-records

by ma1orek

Write and maintain Architecture Decision Records (ADRs) following best practices for technical decision documentation. Use when documenting significant technical decisions, reviewing past architectural choices, or establishing decision processes.

deepagents-subagents

by evanfang0054

在 Deep Agents 中使用 SubAgentMiddleware 启动子代理进行任务委托、上下文隔离和专门工作。

MemoryMesh 🧠

by tplove2010

async-python-patterns

by mokbhai

Master Python asyncio, concurrent programming, and async/await patterns for high-performance applications. Use when building async APIs, concurrent systems, or I/O-bound applications requiring non-blocking operations.

laravel-boost

by SebastiaanWouters

Laravel MCP with DB queries, schema, routes, logs, artisan, tinker, docs search. Triggers on Laravel development, debugging, or database tasks.

security-reviewer

by k1lgor

Use this when the user asks for a security review, vulnerability check, or wants to know if code is safe. Focus on common issues like injection, broken auth, insecure defaults, and sensitive data exposure.

looker-studio

by munolabs

Skill for creating dashboards and calculated fields in Google Looker Studio (formerly Data Studio). Use when the user: - Needs help with formulas or calculated fields in Looker Studio - Wants to connect Looker Studio to PostgreSQL/Supabase - Needs to create visualizations or dashboards - Asks about function syntax (CASE, IF, DATETIME, etc.) - Wants to convert timezones or format dates - Needs to blend data from multiple sources

efcore-patterns

by baotoq

Entity Framework Core best practices including NoTracking by default, query splitting for navigation collections, migration management, dedicated migration services, and common pitfalls to avoid.

codeeagle

by imyousuf

Query and analyze the codebase using CodeEagle's knowledge graph. Provides structured code data (symbols, interfaces, edges), impact analysis, design review, and general Q&A — all grounded in an indexed knowledge graph. Use this FIRST before reading source files.

choru-ticket

by choru-k

Manage personal projects (no ticket IDs) in Obsidian vault. Supports project/plan workflow plus legacy-folder migration for users with multiple repos.

semantic-search

by cadrianmae

Use semantic search to find relevant code and documentation when user asks about specific functionality, features, or implementation patterns. Automatically invoke when user asks "where is...", "how does... work", "find code that...", or similar conceptual queries. More powerful than grep for concept-based searches. Uses odino CLI with BGE embeddings for fully local semantic search.

occlusion-hypersoc

by k-marian-deepak

Build, extend, and maintain Occlusion — a HyperSOC security automation platform (React + TypeScript + React Flow frontend, FastAPI + Celery + PostgreSQL backend, Ollama/CrewAI AI agents, Keycloak SSO). Use this skill whenever the user asks to: build or modify any part of the Occlusion platform (UI components, workflow canvas, case management, settings pages, API endpoints, database schema, AI agents, auth, Docker/infra config); fix light/dark theme contrast or color token issues; extend the integration library; add version-control features to workflows; implement shift handover; scaffold new FastAPI routers or Celery tasks; or connect Occlusion to MediSense AI shared infrastructure. Also trigger for any question about the full stack, tech choices, or architecture of this project.

konditional

by amichne

Use this skill when integrating Konditional into a codebase — whether you are a new user defining your first typed namespace or an enterprise team migrating from string-key flag systems. Covers namespace declaration, context modeling, evaluation, remote config loading, gradual rollout, shadow migration, and OpenFeature interoperability.

schema-architect

by Await-d

"Design database table schemas from any relationship description, including full index strategy analysis. Use this skill whenever the user wants to figure out how to structure a database — regardless of how they phrase it. Trigger on: (1) natural language describing entities and how they relate ('users can place multiple orders', '一个用户可以有多个订单'), (2) questions like 'what tables do I need for X' or '怎么建表' or '表结构怎么设计', (3) TypeScript/Go/Python interfaces or API JSON responses to reverse-engineer a schema from, (4) mermaid/PlantUML ER diagrams to turn into table definitions, (5) any mention of '数据库设计', '建表', '表结构', 'schema design', 'data model', 'ER diagram', (6) system descriptions with entities like users/orders/products/roles that need to be stored, (7) requirements docs or feature specs implying data persistence needs, (8) any mention of query performance, index design, or '索引' alongside schema design. Also trigger on vague phrasing: 'how do I store this?', 'how should I design this?', '帮我设计数据库', '怎么设计这个系统的表'. Do NOT trigger for: writing SQL queries against an existing schema, adding columns to existing tables, database migration scripts, choosing between databases (MySQL vs PostgreSQL), explaining SQL concepts, Redis/cache key design, GraphQL schema (unless also wanting SQL tables), or Prisma schema conversion to SQL (that's a mechanical translation, not a design task)."

Tool Documentation Quick Reference

by cadrianmae

This skill should be used when the user asks for "quick reference", "show me examples for [tool]", "common commands for pandoc", "how do I use pandoc", "pandoc cheatsheet", "show pandoc examples", "tool-lookup", or needs fast offline access to command-line tool commands without detailed explanations. Load when user wants working examples at a glance, not troubleshooting or in-depth documentation.

prompt-engineering-patterns

by ian-pascoe

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

data-engineer

by k1lgor

Use this for SQL queries, database schema design, ETL pipelines, data transformations (pandas/Spark), and data validation.

Gemini Extension Authoring

by chen-ye

This skill should be used when the user asks to "create a gemini extension", "author a gemini extension", "package a gemini hook", "publish a gemini extension", or asks about "extension structure", "gemini-extension.json", or "hooks.json".

api-design-principles

by Krosebrook

Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.

fastapi-templates

by Krosebrook

Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.

gam-researcher-agent

by starwreckntx

Automated context retrieval from Transmission Packet archive using iterative research loop. Implements GAM "Read Path" to complement manual "Write Path" (Memorizer).