Loading...
Loading...
Found 17 Skills
PDF data extraction tool. Use it when users mention "PDF extraction", "PDF to Markdown", "PDF parsing", "extract PDF content", "PDF to JSON", "RAG PDF". OpenDataLoader PDF is currently the top-ranked PDF parser in benchmark tests, supporting local mode (fast, deterministic) and hybrid AI mode (for complex tables, scanned documents, formulas), with output formats including Markdown, JSON (with bounding boxes), and HTML. It is suitable for scenarios where structured data needs to be extracted from PDFs for RAG/LLM pipelines, or where batch processing of PDF documents is required.
Use when designing GraphQL schemas, implementing Apollo Federation, or building real-time subscriptions. Invoke for schema design, resolvers with DataLoader, query optimization, federation directives.
GraphQL API design. Covers schema, queries, mutations, and resolvers. Use when building or consuming GraphQL APIs. USE WHEN: user mentions "GraphQL", "schema definition", "resolvers", "mutations", "queries", "DataLoader", "N+1 problem", asks about "how to design GraphQL API", "GraphQL schema", "GraphQL authentication", "GraphQL pagination", "Apollo Server" DO NOT USE FOR: REST APIs - use `rest-api` instead; tRPC - use `trpc` instead; GraphQL code generation - use `graphql-codegen` instead
Use when implementing GraphQL resolvers with resolver functions, context management, DataLoader batching, error handling, authentication, and testing strategies.
Strawberry GraphQL library for Python with FastAPI integration, type-safe resolvers, DataLoader patterns, and subscriptions. Use when building GraphQL APIs with Python, implementing real-time features, or creating federated schemas.
TRIGGER when: user asks about querying or mutating Steedos data via GraphQL (POST /graphql); asks about auto-generated GraphQL operations ({object}, {object}__findOne, {object}__count, {object}__insert, {object}__update, {object}__delete); asks about __expand for lookup expansion, _display for formatted values, _permissions for record permissions, _related_* for related records, or DataLoader batching; asks about filters/pagination/sorting in a GraphQL query against Steedos; asks about Apollo Playground at /graphql. SKIP: user wants REST API CRUD — use steedos-server-api or steedos-builder6-api; user wants to call a server function — use steedos-object-functions + steedos-server-api; user is building a generic GraphQL server unrelated to Steedos. Steedos GraphQL API auto-generated from object metadata at /graphql. Covers all CRUD queries/mutations, lookup expansion, display formatting, record permissions, related records, filters, pagination, and authentication.
GraphQL gives clients exactly the data they need - no more, no less. One endpoint, typed schema, introspection. But the flexibility that makes it powerful also makes it dangerous. Without proper controls, clients can craft queries that bring down your server. This skill covers schema design, resolvers, DataLoader for N+1 prevention, federation for microservices, and client integration with Apollo/urql. Key insight: GraphQL is a contract. The schema is the API documentation. Design it carefully.
Spring for GraphQL - building GraphQL APIs with Spring Boot. Covers queries, mutations, subscriptions, @BatchMapping, DataLoader, and security. USE WHEN: user mentions "spring graphql", "@QueryMapping", "@MutationMapping", "@SubscriptionMapping", "@BatchMapping", "GraphQL Spring Boot", "N+1 GraphQL" DO NOT USE FOR: REST APIs - use standard Spring MVC, standalone GraphQL - use `graphql-java` skill
Code instrumentation for timing workloads. Two scenarios: (1) Training loop — inject manual timing to report per-iteration latency, throughput (samples/sec), and data load time. (2) Standalone kernel/op — write CUDA event timing code with warmup, per-iteration statistics, and anti-pattern avoidance. Also covers NVTX annotation for labeling profiler timelines. NOT for: running or analyzing profiler tools (nsys, ncu, Nsight Systems, Nsight Compute), writing kernels (Triton, CuTe, CUDA), applying optimizations (CUDA Graphs, gradient checkpointing, fusion), or interpreting roofline/SOL% metrics. Triggers: "measure throughput", "benchmark this function", "time my training loop", "samples per second", "NVTX annotate", "instrument my dataloader", "data load time", "kernel timing", "how do I time".
Refactor PyTorch code to improve maintainability, readability, and adherence to best practices. Identifies and fixes DRY violations, long functions, deep nesting, SRP violations, and opportunities for modular components. Applies PyTorch 2.x patterns including torch.compile optimization, Automatic Mixed Precision (AMP), optimized DataLoader configuration, modular nn.Module design, gradient checkpointing, CUDA memory management, PyTorch Lightning integration, custom Dataset classes, model factory patterns, weight initialization, and reproducibility patterns.
GraphQL schema and federation expert specializing in resolver optimization, subscriptions, and API gateway patterns
GraphQL query language and runtime for APIs enabling clients to request exactly the data they need with strongly-typed schemas and single endpoint architecture.