chrishuffman5

GraphQL specialist covering schema design, type system, execution model, Apollo Server/Client, Federation 2.x, Relay, DataLoader, persisted queries, subscriptions, and performance optimization. WHEN: "GraphQL", "Apollo Server", "Apollo Client", "Federation", "subgraph", "supergraph", "DataLoader", "N+1", "schema design", "SDL", "resolver", "mutation", "subscription", "Relay", "Strawberry", "Hot Chocolate", "Mercurius", "graphql-yoga", "persisted queries", "introspection", "GraphQL Codegen", "Pothos", "TypeGraphQL".

gRPC 1.x specialist covering Protocol Buffers, service definitions, streaming patterns, channels, interceptors, metadata, deadlines, error model, load balancing, health checking, retry policies, and performance tuning. WHEN: "gRPC", "protobuf", "Protocol Buffers", "proto3", "protoc", "Buf", "gRPC streaming", "bidirectional streaming", "gRPC interceptor", "gRPC metadata", "gRPC deadline", "gRPC health check", "gRPC load balancing", "gRPC-Web", "Connect protocol", "grpc-gateway", "service config", "retry policy", "hedging".

REST API design specialist covering OpenAPI 3.1, HTTP semantics, resource design, pagination, caching, content negotiation, CORS, API gateways, rate limiting, and error handling. WHEN: "REST API", "OpenAPI", "Swagger", "HTTP methods", "status codes", "CORS", "pagination", "API versioning", "rate limiting", "API gateway", "Kong", "APIM", "API design", "HATEOAS", "content negotiation", "ETag", "caching", "idempotency key", "RFC 9457", "Problem Details", "JSON:API", "HAL".

Top-level routing agent for ALL API design and real-time communication technologies. Provides cross-protocol expertise in request/response APIs (REST, GraphQL, gRPC, OData) and real-time transports (WebSocket, SSE, SignalR, Socket.IO). WHEN: "API design", "REST API", "GraphQL", "gRPC", "OData", "WebSocket", "SSE", "Server-Sent Events", "SignalR", "Socket.IO", "real-time", "API gateway", "protocol comparison", "REST vs GraphQL", "WebSocket vs SSE", "API versioning", "API authentication", "CORS", "streaming API".

Expert agent for ASP.NET Core Web API across .NET 8, 9, and 10. Covers middleware pipeline, dependency injection, Kestrel, routing, controllers vs Minimal APIs, model binding, filters, configuration, error handling, and deployment. WHEN: "ASP.NET Core", "ASP.NET", ".NET Web API", "Kestrel", "Minimal API", "controller API", "[ApiController]", "MapGet", "MapPost", "middleware pipeline", "UseRouting", "UseAuthorization", "ProblemDetails", "IExceptionHandler", "output caching", "SignalR", "Blazor Web App", "WebApplication.CreateBuilder".

Expert agent for Django web framework across versions 4.2 LTS, 5.2 LTS, and 6.0. Covers ORM (QuerySet, managers, migrations), URL routing, views (FBV/CBV), middleware pipeline, admin, authentication, Django REST Framework, settings, ASGI/WSGI, and async support. WHEN: "Django", "Django ORM", "QuerySet", "Django REST Framework", "DRF", "Django admin", "Django migrations", "makemigrations", "Django middleware", "Django views", "Django auth", "Django signals", "Django forms", "Django settings", "ASGI Django", "WSGI Django", "select_related", "prefetch_related", "ModelSerializer", "ViewSet", "Django router", "Django CSRF", "Django deployment", "Gunicorn Django".

Expert agent for Express.js web framework development across Express 4.x and 5.x. Covers middleware chain, routing, error handling, request/response lifecycle, template engines, security (Helmet, CORS), body parsing, TypeScript setup, testing, and deployment. WHEN: "Express", "express.js", "express middleware", "app.use", "app.get", "app.post", "express router", "middleware ordering", "express error handler", "req.params", "req.query", "req.body", "res.json", "res.send", "express-validator", "supertest", "helmet", "cors middleware", "express rate limit", "multer", "express-session", "passport express", "Express 5", "express TypeScript".

Top-level routing agent for ALL backend web framework and REST API technologies. Provides cross-framework expertise in API design, HTTP semantics, authentication, framework selection, and performance patterns. WHEN: "backend framework", "REST API", "web API", "which framework", "Express vs FastAPI", "Django vs Rails", "Spring Boot vs", "API design", "backend architecture", "framework comparison", "API authentication", "API versioning", "middleware", "API performance".

IAM Access Analyzer via AWS CLI v2 (`aws accessanalyzer`). Analyzers, findings, archive rules, access previews, policy tools.

Private CA via AWS CLI v2 (`aws acm-pca`). Certificate authorities, certificates, audit reports, permissions, policies.

ACM via AWS CLI v2 (`aws acm`). Certificates, import/export, validation, tags, account configuration.

Managed Prometheus via AWS CLI v2 (`aws amp`). Workspaces, alert manager, rule groups, scrapers, logging, resource policies.

Amplify via AWS CLI v2 (`aws amplify`). Apps, branches, domain associations, jobs, deployments, webhooks.

API Gateway via AWS CLI v2 (`aws apigateway`). REST APIs, HTTP APIs, resources, methods, stages, authorizers, API keys, usage plans.

AppConfig via AWS CLI v2 (`aws appconfig`). Feature flags, configuration profiles, deployment strategies, environments, extensions, runtime data retrieval.

Application Auto Scaling via AWS CLI v2 (`aws application-autoscaling`). Scalable targets, scaling policies, scheduled actions, predictive scaling.

gcloud CLI reference: 128 GCP services, all GA commands with full flags, plus the standalone bq CLI. Use for any Google Cloud / GCP command-line task — managing resources, debugging gcloud commands, auth/config/scripting — or whenever a GCP product is named (GKE, Cloud Run, BigQuery, Cloud SQL, Pub/Sub...), even without 'gcloud'.

Access Approval via gcloud (`gcloud access-approval`). Manage Access Approval requests and settings — requests, service-account, settings.

Access Context Manager (VPC Service Controls) via gcloud (`gcloud access-context-manager`). Manage Access Context Manager resources — authorized-orgs, cloud-bindings, levels, perimeters, policies, supported-services.

Managed Service for Microsoft AD via gcloud (`gcloud active-directory`). Manage Managed Microsoft AD resources — domains, operations, peerings.

Agent Registry via gcloud (`gcloud agent-registry`). Manage Agent Registry resources — agents, bindings, endpoints, mcp-servers, operations, services.

AI Platform (legacy) via gcloud (`gcloud ai-platform`). Manage AI Platform jobs and models — jobs, local, models, operations, versions.

Vertex AI via gcloud (`gcloud ai`). Manage entities in Vertex AI — custom-jobs, endpoints, hp-tuning-jobs, index-endpoints, indexes, model-garden, model-monitoring-jobs, models.

AlloyDB for PostgreSQL via gcloud (`gcloud alloydb`). Create and manage AlloyDB databases — backups, clusters, instances, operations, users.

Install a skill from a remote git repository into the local .claude/skills/ directory. Use this skill whenever the user wants to install, add, or set up a new skill — e.g., "install the pdf skill", "add the remotion skill", "set up the xlsx skill". Also trigger when users reference installing skills by name or ask how to get a skill.

Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files

Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

Converts Stitch designs into modular Vite and React components using system-level networking and AST-based validation.

Best practices for Remotion - Video creation in React

Expert guidance for integrating and building applications with shadcn/ui components, including component discovery, installation, customization, and best practices.

Unified entry point for Stitch design work. Handles prompt enhancement (UI/UX keywords, atmosphere), design system synthesis (.stitch/DESIGN.md), and high-fidelity screen generation/editing via Stitch MCP.

Teaches agents to iteratively build websites using Stitch with an autonomous baton-passing loop pattern

Offline SQL Server analysis & recommendations engine: capture read-only system-view/DMV/catalog data from a target instance ONCE, land it as local CSV/Parquet, load it into DuckDB, and run an analysis query library that produces PRIORITIZED, EXPLAINED recommendations across table/schema design, indexing, table sizes & capacity, statistics staleness, query hotspots, waits, configuration, file/autogrowth/tempdb layout, backup & recovery cadence, and identity-exhaustion runway — the PerformanceMonitor 'Lite' pattern. Complements the live diagnostic skills; iterate analysis with zero further load on the source and trend across capture runs. WHEN: "analyze my database", "recommendations to improve the database", "table design review", "what indexes am I missing", "unused/duplicate indexes", "is my schema well designed", "offline database analysis", "DuckDB SQL Server analysis", "database health report", "capacity review", "backup review", "identity running out", "advisor", "prioritized findings".

Comprehensive Microsoft SQL Server expert and router covering the full database-management lifecycle across versions 2016-2025 and the cloud (Azure SQL Database, Azure SQL Managed Instance, SQL on Azure VM, AWS RDS, Google Cloud SQL). Routes to specialized skills for operations, monitoring, HA/clustering, engineering, infrastructure, cloud, security, and offline DuckDB-powered analysis & recommendations (advisor). WHEN: "SQL Server", "MSSQL", "T-SQL", "SSMS", "sqlcmd", "DBA", "database administration", general or cross-cutting SQL Server questions, or when the specific management domain is unclear.

SQL Server cloud offerings and migration: Azure SQL Database (DTU/vCore, elastic pools, serverless, Hyperscale), Azure SQL Managed Instance, SQL Server on Azure VM, AWS RDS for SQL Server, and Google Cloud SQL — including feature-parity differences, geo-replication, auto-failover groups, and migration tooling (Data Migration Assistant, Azure DMS, Managed Instance link, log replay, BACPAC, backup/restore to URL). WHEN: "Azure SQL", "Azure SQL Database", "Managed Instance", "SQL MI", "Hyperscale", "elastic pool", "serverless SQL", "DTU", "vCore", "SQL Server on Azure VM", "SQL IaaS", "AWS RDS SQL Server", "RDS", "Cloud SQL", "geo-replication", "failover group", "DMA", "Azure DMS", "MI link", "cloud migration", "BACPAC", "PaaS SQL", "which Azure SQL".

SQL Server development and performance engineering: T-SQL best practices, indexing strategy (clustered, nonclustered, columnstore, filtered, covering/included), execution plans, query optimization, statistics and the cardinality estimator, parameter sniffing mitigation, partitioning, In-Memory OLTP, temporal tables, data compression, and schema design. WHEN: "T-SQL", "write a query", "index", "covering index", "columnstore", "execution plan", "query plan", "query tuning", "optimize query", "SARGable", "cardinality estimator", "statistics", "parameter sniffing", "OPTION RECOMPILE", "partitioning", "In-Memory OLTP", "temporal table", "stored procedure", "schema design", "data type", "normalization".

SQL Server high availability, clustering, and disaster recovery: Always On Availability Groups (synchronous/asynchronous, contained, distributed, basic, read-scale), Failover Cluster Instances (FCI) on Windows Server Failover Clustering (WSFC), database mirroring and mirroring endpoints, log shipping, replication, quorum and witnesses, listeners, automatic seeding, and failover procedures. WHEN: "Always On", "availability group", "AG", "readable secondary", "FCI", "failover cluster", "WSFC", "quorum", "witness", "database mirroring", "mirroring endpoint", "CREATE ENDPOINT", "log shipping", "replication", "distributor", "listener", "automatic seeding", "failover", "high availability", "disaster recovery", "DR", "RPO", "RTO".

SQL Server instance and platform infrastructure: hardware sizing, memory configuration (max/min server memory, Lock Pages in Memory), MAXDOP and cost threshold for parallelism, NUMA, tempdb configuration, instant file initialization, trace flags, storage layout and disk subsystem, OS settings, deployment on Windows/Linux/containers, and network/protocol/port configuration. WHEN: "max server memory", "min server memory", "MAXDOP", "cost threshold for parallelism", "NUMA", "soft-NUMA", "tempdb configuration", "trace flag", "startup parameter", "instant file initialization", "Lock Pages in Memory", "instance configuration", "sp_configure", "SQL Server on Linux", "mssql-conf", "SQL Server container", "Docker", "storage layout", "sizing", "TCP 1433", "port", "protocol", "SQL Browser".

SQL Server performance monitoring and diagnostics: wait-statistics methodology, Dynamic Management Views (DMVs), Query Store, Extended Events, blocking and deadlock analysis, performance counters, baselining, and health checks. WHEN: "slow", "performance problem", "wait stats", "wait type", "DMV", "Query Store", "Extended Events", "XEvents", "blocking", "deadlock", "high CPU", "PAGEIOLATCH", "CXPACKET", "PLE", "page life expectancy", "baseline", "perfmon counter", "sp_whoisactive", "troubleshoot performance".

SQL Server day-to-day operations and core DBA tasks: backup and recovery strategy, restore testing, recovery models, point-in-time recovery, index and statistics maintenance, DBCC CHECKDB and corruption handling, SQL Agent jobs/alerts/Database Mail, patching and cumulative-update strategy, and space/capacity management. WHEN: "backup", "restore", "recovery model", "point-in-time", "RPO", "RTO", "DBCC CHECKDB", "corruption", "maintenance plan", "Ola Hallengren", "index maintenance", "update statistics", "SQL Agent job", "alert", "Database Mail", "cumulative update", "patch", "disk space", "shrink", "VLF".

Managed PostgreSQL cloud platforms: Amazon RDS for PostgreSQL, Aurora PostgreSQL, Google Cloud SQL, AlloyDB, Azure Database for PostgreSQL Flexible Server, Supabase, Neon, migrations, cloud limits, backups, monitoring, HA, read replicas, and parameter groups.

PostgreSQL SQL engineering and performance: EXPLAIN plans, indexing, statistics, joins, partitioning, schema design, constraints, JSONB, full text, GIN/GiST/BRIN/B-tree indexes, pgvector, extensions, and query tuning.

PostgreSQL replication and high availability: streaming replication, physical standbys, logical replication, publications, subscriptions, replication slots, WAL shipping, failover, Patroni, repmgr, pg_auto_failover, synchronous commit, and disaster recovery.

PostgreSQL infrastructure and instance configuration: memory, shared_buffers, work_mem, WAL, checkpoints, storage, Linux, containers, Kubernetes, connection pooling, pgbouncer, networking, extensions, configuration files, and server sizing.

PostgreSQL performance monitoring and diagnostics: wait events, pg_stat_activity, pg_stat_database, pg_stat_statements, blocking and deadlock analysis, log analysis, baselining, and health checks. Use for slow queries, high CPU, high I/O, lock waits, deadlocks, replication symptoms, query history, and general PostgreSQL troubleshooting.

PostgreSQL operations for backups, restores, PITR, pg_dump, pg_restore, pg_basebackup, pgBackRest, WAL archiving, vacuum, autovacuum, bloat, transaction ID wraparound, maintenance jobs, upgrades, and capacity management.

PostgreSQL security: authentication, pg_hba.conf, SCRAM, SSL/TLS, roles, privileges, grants, default privileges, row-level security, auditing, pgaudit, encryption, secrets, search_path safety, and hardening.

Comprehensive PostgreSQL expert and router covering operations, monitoring, replication/high availability, engineering, infrastructure, cloud, and security across self-managed PostgreSQL, RDS/Aurora, Cloud SQL, Azure Database for PostgreSQL, Supabase, Neon, and common extensions. Use for PostgreSQL, Postgres, psql, pg_dump, pg_restore, SQL tuning, DBA, database administration, or cross-cutting PostgreSQL guidance.

Check the current temperature for a US ZIP code using PowerShell and free REST APIs (zippopotam.us for geocoding, Open-Meteo for weather — no API keys needed). Use this whenever the user asks about the temperature, current weather, how hot or cold it is, or wants weather info for a ZIP code or US location, even if they don't say "gettemp" explicitly.

Check the current temperature for a US ZIP code using PowerShell and free REST APIs (zippopotam.us for geocoding, Open-Meteo for weather — no API keys needed). Use this whenever the user asks about the temperature, current weather, how hot or cold it is, or wants weather info for a ZIP code or US location, even if they don't say "gettemp" explicitly.

Decide what tests to write and how to run them for any implementation task, during planning, before code is written. Use this whenever you are planning, scoping, or designing work on an application, API, UI, library, CLI, database schema, data migration, ETL/pipeline, infrastructure-as-code, or cloud deployment — and you need to produce a test plan. Use it even when no dedicated test framework or tool is available: the point of this skill is that an agent can design, build, and run almost any test from general-purpose primitives (shell, the language's native test runner, the database client, the cloud CLI, `terraform show -json`) without specialized tooling. Trigger on phrases like "what should I test", "test plan", "test strategy", "how do I test this", "add tests", "test coverage for this task", or any planning step for a task that will ship.

Manage a software project as a file-based Rally tree — CLAUDE.md files under the repo's pm/E<NNN>/ (Epic → Feature → User Story → Task). Three invocations: `/pm init` scaffolds a new pm/ tree from a brief (PLAN.md + epic charter + feature/story/task folders); `/pm plan` refines an existing tree (split stories, fix dependencies, re-phase, groom the backlog, re-prioritize, sharpen acceptance criteria); `/pm` executes it (act as PM for a feature, claim a user story, run tasks, tick acceptance criteria, drive git-worktree-per-story, delegate to worker agents, log status, surface blockers). Use it for anything touching a pm/E<NNN> tree or epics/features/stories/tasks-kept-as-files: "scaffold the PM tree", "groom the backlog", "act as pm for F1xxx", "claim a story", "tick the checkboxes". Not for generic or agile project planning, personal to-do lists, status reports, external PM tools (Jira/Trello/Linear), or code scaffolding (`npm init`, app generators).

Update the AI CLI Quick Reference README.md with the latest versions and slash commands for GitHub Copilot CLI, OpenAI Codex CLI, Claude Code CLI, and Gemini CLI. Use this skill whenever the user asks to update, refresh, or check the AI CLI documentation, or mentions checking for new versions or commands of any of these 4 CLIs. Also trigger when the user mentions "document-aiclis", "update readme", "check CLI versions", or "refresh slash commands".