Bases de dades
Gestió i consultes de bases de dades
ontoindex-exploring
ontograph
'Understand architecture, find code, and trace callers or execution flows in an unfamiliar repository.'
gmail
aws-samples
Read, send, draft, delete, and organize Gmail emails
insforge
InsForge
Build applications with InsForge Backend-as-a-Service. Use when developers need to: (1) Set up backend infrastructure (create tables, storage buckets, deploy functions, configure auth/AI) (2) Integrate InsForge SDK into frontend applications (database CRUD, auth flows, file uploads, AI operations, real-time messaging) (3) Deploy frontend applications to InsForge hosting IMPORTANT: Before any backend work, you MUST have the user's Project URL and API Key. If not provided, ask the user first. Key distinction: Backend configuration uses HTTP API calls to the InsForge project URL. Client integration uses the @insforge/sdk in application code.
1k-ui-snapshot-cache
OneKeyHQ
"UI snapshot cache (display-only, main-thread) + unified startup timing schema — cold-start reads from snapshot namespaces (MMKV on native, IndexedDB on web) and the cross-platform [StartupTiming] log taxonomy. Use when adding or debugging a UI snapshot / SWR cache, debugging startup performance regressions, analyzing cold start timeline, or comparing iOS vs Android startup phases. Triggers on: ui snapshot cache, SnapshotCache, swr cache, usePromiseResult cache, cold start, startup optimization, 启动时间, SSR hydration, Balance displayed regression, contextAtomBase, flushColdStartCache, __ONEKEY_CTX_ATOM_SNAPSHOT__, StartupTiming, main_host.did_start, bg_runner.start."
imaging-data-commons
jaechang-hits
"Query NCI Imaging Data Commons (IDC) for cancer radiology and pathology imaging datasets hosted on Google Cloud. Search DICOM collections by modality, anatomical site, cancer type, or collection name. Download images via Google Cloud Storage or IDAT tool. 50TB+ of publicly accessible DICOM images. Requires Google Cloud account for large downloads; small queries work without billing. For local DICOM processing use pydicom-medical-imaging; for whole-slide pathology use histolab."
database-schema-validator
rominirani
Validates SQL schema files for compliance with internal safety and naming policies.
mongodb
hoodini
Work with MongoDB databases using best practices. Use when designing schemas, writing queries, building aggregation pipelines, or optimizing performance. Triggers on MongoDB, Mongoose, NoSQL, aggregation pipeline, document database, MongoDB Atlas.
vercel
hoodini
Deploy and configure applications on Vercel. Use when deploying Next.js apps, configuring serverless functions, setting up edge functions, or managing Vercel projects. Triggers on Vercel, deploy, serverless, edge function, Next.js deployment.
smart-query
zrt-ai-lab
智能数据库查询技能。通过SSH隧道连接线上数据库，支持自然语言转SQL、执行查询、表结构探索。当用户需要查询数据库、问数据、看表结构时使用此技能。
log-analyzer
zrt-ai-lab
全维度日志分析技能。自动识别日志类型（Java应用/MySQL Binlog/Nginx/Trace/告警），提取关键实体（IP、thread_id、trace_id、用户、表名等），进行根因定位、告警分析、异常洞察。支持100M+大文件。触发词：分析日志、日志排查、根因定位、告警分析、异常分析。
better-auth-best-practices
novuhq
Skill for integrating Better Auth - the comprehensive TypeScript authentication framework.
tech-search
SynkraAI
Self-contained deep tech research. WebSearch + WebFetch + Haiku workers. Pipeline: Query > Decompose > Parallel Search (Haiku) > Evaluate > Synthesize > Document. Zero external dependencies. MCPs optional. Salva em docs/research/{YYYY-MM-DD}-{slug}/.
aiox-data-engineer
SynkraAI
Database Architect & Operations Engineer (Dara). Use for database design, schema architecture, Supabase configuration, RLS policies, migrations, query optimization, data modelin...
postkit
varunchopra
PostgreSQL-native identity, configuration, metering, and job queues. SQL functions that work with any language or driver. Use when working with user management, sessions, permissions, access control, login/logout, MFA, password resets, relationship-based access, versioned configuration, prompts, usage tracking, quotas, billing periods, or background jobs in PostgreSQL. Covers authn (user/session management), authz (ReBAC permissions), config (versioned key-value storage), meter (usage tracking with reservations), and queue (job scheduling with retries and dead letters).
tanstack-solid
joncrangle
Specialist in the TanStack ecosystem for SolidJS, including TanStack Start, Query, Router, Table, and Form. Focuses on Solid-specific reactivity patterns.
saleor-django-migration
saleor
Generate Django schema migrations for the Saleor codebase using manage.py makemigrations. Use when (1) a new Django model is created, (2) model fields are added/altered/removed, (3) user explicitly asks to create a migration. This skill covers ONLY synchronous schema migrations (CreateModel, AddField, AlterField, RemoveField, etc.) — NOT data migrations with RunPython or RunSQL. If unsure whether the migration is schema-only, ask the user.
Create database migration
TryGhost
Create a database migration to add a table, add columns to an existing table, add a setting, or otherwise change the schema of Ghost's MySQL database.
code-review-assistant
ArabelaTso
Conduct comprehensive code reviews identifying bugs, security issues, performance problems, code quality concerns, and best practice violations. Use when reviewing pull requests, examining code changes, evaluating new code, assessing code quality, or providing feedback on implementations. Analyzes code for correctness, security vulnerabilities, performance bottlenecks, maintainability issues, test coverage, documentation quality, and adherence to coding standards. Produces structured markdown reviews with categorized findings, severity ratings, specific examples, and actionable recommendations. Triggers when users ask to review code, check pull requests, evaluate implementations, find bugs, or assess code quality.
Confluent ksqlDB Skill
anton-abyzov
ksqlDB stream processing expert. Covers SQL-like queries on Kafka topics, stream and table concepts, joins, aggregations, windowing, materialized views, and real-time data transformations. Activates for ksqldb, ksql, stream processing, kafka sql, real-time analytics, windowing, stream joins, table joins, materialized views.
openspec-continue-change
studyzy
通过创建下一个产出物继续处理 OpenSpec 变更。当用户想要推进其变更、创建下一个产出物或继续其工作流程时使用。
openspec-new-change
studyzy
使用实验性的产出物工作流启动一个新的 OpenSpec 变更。当用户想要通过结构化的分步方法创建新功能、修复或修改时使用。
openspec-new-change
studyzy
使用实验性的产出物工作流启动一个新的 OpenSpec 变更。当用户想要通过结构化的分步方法创建新功能、修复或修改时使用。
openspec-archive-change
studyzy
归档实验性工作流中已完成的变更。当用户想要在实现完成后最终确定并归档变更时使用。
openspec-apply-change
studyzy
实现 OpenSpec 变更中的任务。当用户想要开始实现、继续实现或处理任务时使用。