NoSQL 資料庫

AI-powered RCA Copilot for root cause analysis and incident explanation. Use when: (1) Building incident context retrieval from Neptune and DynamoDB, (2) Implementing evidence ranking and root cause candidate generation, (3) Creating natural language incident explanations, (4) Generating recommended remediation actions. Triggers: "explain incident", "find root cause", "diagnose data issue", "what caused the alert", "RCA for incident".

Write HashiCorp-compliant Terraform infrastructure code for Azure with automated style validation. Optimized for azurerm and azapi providers. Use when implementing Terraform resources, modules, or configurations. Triggers include "write terraform", "create tf module", "terraform code", "implement infrastructure as code", or working with .tf files. ALWAYS uses Terraform MCP tools to query provider documentation before implementation.

Personal copy editor and content enhancer for Obsidian vault notes. Use when the user requests editing, enhancement, copyediting, critique, or improvement of markdown files. Typical triggers include "edit this file", "clean up these notes", "enhance this draft", "give me feedback on", "polish this content", "expand my shorthand", or "add links to this". Handles diverse content types including technical documentation, research notes, essays, Substack posts, administrative notes, and personal writing. Always preserves original content and appends enhanced version below a separator line.

Master MongoDB aggregation pipeline for complex data transformations. Learn pipeline stages, grouping, filtering, and data transformation. Use when analyzing data, creating reports, or transforming documents.

Master MongoDB schema design and data modeling patterns. Learn embedding vs referencing, relationships, normalization, and schema evolution. Use when designing databases, normalizing data, or optimizing queries.

Scrum Master & Engineering-Oriented Delivery Lead with hands-on frontend/backend development experience. Interprets Technical Design Documents, reviews UX/UI designs, and understands product requirements to ensure delivery clarity. Breaks features into well-scoped Scrum stories (max 3 story points, Fibonacci estimation). Stories are sliced for incremental value, minimal risk, fast feedback. For every ticket provides: clear description, explicit acceptance criteria, expected behavior, constraints, and test case expectations (happy path + edge cases). Ensures stories are implementation-ready, testable, aligned with technical/product goals. Enables team to execute efficiently while maintaining high quality and predictable velocity. Use when creating sprint stories, planning sprints, estimating work, or breaking down features into tickets.

Persistent state management using AgentDB (DuckDB) for workflow analytics and checkpoints.Provides read-only analytics cache synchronized from TODO_*.md files, enabling:- Complex dependency graph queries- Historical workflow metrics- Context checkpoint storage/recovery- State transition analysisUse when: Data gathering and analysis for workflow state trackingTriggers: "analyze workflow", "query state", "checkpoint", "workflow metrics"

Implements Anthropic's Evaluator-Optimizer pattern where one LLM generates solutions and another provides evaluative feedback in an iterative loop. Use when quality can be demonstrably improved through articulated feedback cycles. Evaluates across 5 dimensions (functionality, performance, code quality, security, documentation) with up to 5 improvement iterations.

Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.

Use when working with database models or migrations. Contains schema documentation and relationship patterns.

Use the qashier-cli tool to manage Google OAuth authentication, switch between staging/production environments, and extract Firestore documents. Invoke when user mentions qashier-cli, authentication issues, environment switching, Firestore data extraction, or needs to verify auth status.

AWS CLI v2 quick-reference for experienced developers. Covers compute (Lambda, ECS, EKS), storage (S3, DynamoDB, Aurora), networking (VPC, SSM tunneling), security (IAM, Secrets Manager), and GitHub Actions CI/CD. Use when asked to "write aws commands", "debug aws access", "set up cross-account roles", "configure aws cli", "assume role", "S3 bucket operations", or "deploy to ECS".

Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results. Use when user needs: (1) Topic-specific documentation (features/components/concepts), (2) Library/framework documentation, (3) GitHub repository analysis, (4) Documentation discovery with automated agent distribution strategy

Generate PRISMA 2020 flow diagrams for systematic reviews. Use when: (1) Conducting systematic literature reviews, (2) Documenting screening process, (3) Reporting study selection for publications, (4) Demonstrating PRISMA compliance, (5) Creating transparent review methodology documentation.

Specialist in Rekordbox MIDI Learn integration, including MIDI mapping workflow, CSV file format, Rekordbox function reference, official documentation, and real-world DDJ controller examples. Use when working on Rekordbox MIDI controllers, CSV generation/import/export, function mapping, or debugging Rekordbox MIDI integration.

Analyze, review, and provide recommendations for distributed system designs. Use when:(1) Reviewing existing system architectures for gaps or improvements,(2) Analyzing system designs for scalability, reliability, or performance issues,(3) Providing recommendations on load balancing, caching, databases, sharding, replication, messaging, rate limiting, authentication, resilience, or monitoring,(4) Assessing trade-offs in system design decisions,(5) Creating system design review documents with gaps and recommendations.Triggers: "review my system design", "analyze this architecture", "what are the gaps", "system design recommendations", "scalability review", "reliability analysis".

Maintain living documentation with single source of truth approach, journal reconciliation, and worklog.db integration

This skill provides complete coverage of Google Gemini embeddings API (gemini-embedding-001) for building RAG systems, semantic search, document clustering, and similarity matching. Use when implementing vector search with Google's embedding models, integrating with Cloudflare Vectorize, or building retrieval-augmented generation systems. Covers SDK usage (@google/genai), fetch-based Workers implementation, batch processing, 8 task types (RETRIEVAL_QUERY, RETRIEVAL_DOCUMENT, SEMANTIC_SIMILARITY, etc.), dimension optimization (128-3072), and cosine similarity calculations. Prevents 8+ embedding-specific errors including dimension mismatches, incorrect task types, rate limiting issues (100 RPM free tier), vector normalization mistakes, text truncation (2,048 token limit), and model version confusion. Includes production-ready RAG patterns with Cloudflare Vectorize integration, chunking strategies, and caching patterns. Token savings: ~60%. Production tested.Keywords: gemini embeddings, gemini-embedding-001, g

Consulta la documentación oficial de MakerKit (next-supabase-turbo) bajo demanda. Usa cuando necesites información sobre patrones, configuración o APIs de MakerKit que no esté en el código local. Incluye índice completo de 150 páginas.

Reconcile worklog database with documentation - promotes learnings to docs with proper frontmatter and validates after sync