NoSQL 資料庫

Build React apps with Apollo Client - queries, mutations, cache, and subscriptions

Design and implement NestJS REST API endpoints following the project's layered architecture (Controllers, Use Cases, Repositories). Use this skill when creating or modifying controller files (*.controller.ts), defining API routes, implementing HTTP handlers, setting up Swagger documentation, configuring route guards and decorators, working with request/response DTOs, or structuring API endpoints. This includes files in features/{feature}/controller/, auth/controller/, and any file with @Controller() decorator. Apply when working with API_ENDPOINTS constants, @Get/@Post/@Put/@Patch/@Delete decorators, @ApiTags/@ApiProperty swagger decorators, @Public/@MemberRoles custom decorators, HttpCode/HttpStatus configurations, or Query/Param/Body parameter decorators.

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"

Configure MongoDB connection and test infrastructure. Use when adding MongoDB support to the project. Triggers on "setup mongodb", "add mongodb", "configure database", "mongodb connection".

Provides GraphQL API schema design and implementation expertise. Ensures proper type definitions, query/mutation patterns, pagination strategies, and error handling standards. Specializes in schema-first design, resolver implementation, DataLoader for N+1 prevention, subscription patterns, and federation architecture. Implements Relay cursor connections and Apollo best practices.Use when: designing GraphQL schemas, defining types and interfaces, implementing queries and mutations, creating resolvers, designing pagination with connections and edges, solving N+1 query problems with DataLoader, implementing subscriptions for real-time updates, handling errors and nullability, setting up GraphQL federation, or integrating with Apollo Server/Client or other GraphQL libraries.

Expert in writing data to Logseq DB graphs via HTTP API. Auto-invokes when users want to create pages, add blocks, update content, set properties, or sync conversation notes to their Logseq graph. Provides CRUD operations with safety guidelines.

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.

Access cached codebase documentation via MCP. Use when searching for project architecture, agent definitions, skill documentation, or deployment procedures. Provides 90% token savings vs. reading files directly.

Intelligent command verification for documentation. Discovers all commands in markdown files, validates them using git diff-based cache invalidation, and ensures documentation accuracy with zero token cost after initial setup. Use when asked to verify commands, check documentation, or validate command references.

Manages Linear issues, teams, and projects via CLI. Lists issues, creates tasks, views details, links issues, and runs GraphQL queries. Must use for "my Linear issues", "create Linear task", "link issues in Linear", "Linear API query", or any Linear project management request.

Manages GitHub issue blocking/blocked-by relationships using the native dependencies feature via GraphQL API. Use when showing that one issue must complete before another can proceed, querying dependency relationships, or preventing circular dependencies.

Update existing implementation plans through user feedback with thorough research and validation. This skill should be used when iterating on implementation plans, updating plans based on new requirements, refining technical approaches in existing plans, or when the user wants to modify a previously created plan file. Triggers on requests like "update the plan", "change the implementation approach", "iterate on this plan", or when feedback is provided about an existing plan document.

This skill should be used when the user asks about "feedback loops", "iterate on requirements", "continuous documentation", "refine requirements", "update requirements", "requirements changed", "stakeholder review", "validate requirements", "incorporate feedback", "gather feedback", "requirements review meeting", "backlog refinement feedback", "user research findings", "sprint retrospective feedback", "help me gather feedback", "run a feedback session", "get input on my vision", "get input on my epics", "get input on my stories", "collect user feedback", "document feedback from meeting", "review requirements with stakeholders", or when they need guidance on collecting and incorporating feedback throughout the requirements lifecycle.

Fetch documents from codex knowledge base with cache-first strategy.Delegates to fractary CLI for actual retrieval operations.

Work with MongoDB in Node.js using Mongoose ODM for schema design, CRUD operations, relationships, and advanced queries

Respond to incidents and apply remediations - restart services, scale resources,clear caches, update configurations, rollback deployments, apply fixes, verifyremediation success, document actions taken, track remediation history.

Comprehensive guide for Amplitude MCP queries. Use when analyzing product analytics, user behavior, funnels, retention, experiments, or metrics. Reduces context overhead by documenting query patterns, event taxonomies, and RDC-specific configurations. Triggers on Amplitude, product analytics, user behavior, funnel analysis, retention, experiment analysis, or metric queries.

This skill should be used when the user asks to "list posters", "get poster info", "fetch context document", "get latest poster", "check poster count", "show poster details", "get context for poster", "show enrichment quality", "diagnose enrichment", "show pulse script", "get all poster data", "check what data we have", or mentions Supabase, posters, context documents, enrichment, or database queries. Provides commands and scripts for querying Local Pulse poster data from Supabase.

Analyzes impact of proposed changes on existing systems (brownfield projects) with delta spec validation.Trigger terms: change impact, impact analysis, brownfield, delta spec, change proposal,change management, existing system analysis, integration impact, breaking changes,dependency analysis, affected components, migration plan, risk assessment, brownfield change.Provides comprehensive change analysis for existing systems:- Affected component identification- Breaking change detection- Dependency graph updates- Integration point impact- Database migration analysis- API compatibility checks- Risk assessment and mitigation strategies- Migration plan recommendationsUse when: proposing changes to existing systems, analyzing brownfield integration,or validating delta specifications.

Validates architecture documentation completeness by checking for technology stack, API specifications, database schema, security architecture, and alignment with feature specification. Ensures plan.md is complete before implementation.