Loading...
Loading...
Found 52 Skills
Use this skill when building real-time or near-real-time data pipelines. Covers Kafka, Flink, Spark Streaming, Snowpipe, BigQuery streaming, materialized views, and batch-vs-streaming decisions. Common phrases: "real-time pipeline", "Kafka consumer", "streaming vs batch", "low latency ingestion". Do NOT use for batch integration patterns (use integration-patterns-skill) or pipeline orchestration (use data-orchestration-skill).
Design high-level functional and technical specifications by defining scope, modules, contracts, boundaries, responsibilities, architecture models, constraints, and verification criteria.
Plan technical execution for software systems by organizing phases, dependencies, sequencing, infrastructure foundations, MVP scope, coordination points, and incremental architecture delivery.
Strategies for managing LLM context windows effectively in AI agents. Use when building agents that handle long conversations, multi-step tasks, tool orchestration, or need to maintain coherence across extended interactions.
Building and training neural networks with PyTorch. Use when implementing deep learning models, training loops, data pipelines, model optimization with torch.compile, distributed training, or deploying PyTorch models.
TypeScript and JavaScript development standards for modern web and Node.js development. Covers strict TypeScript configuration, type safety patterns, ESM modules, async/await, testing with Jest/Vitest, and security best practices. Use when working with .ts, .tsx, .js, .mjs files, package.json, tsconfig.json, or when asking about TypeScript/JavaScript best practices.
Transform user stories and specifications into precise, verifiable Gherkin acceptance criteria using Given/When/Then syntax with Happy Path, Sad Path, and edge case scenarios. Use when asking for acceptance criteria, Gherkin scenarios, BDD criteria, test scenarios, or AC generation.
Use when the user wants to implement a development plan from docs/plans/<FR-N>.md against the target codebase. Drives the task loop — reads the plan, implements each `[ ]` task as a vertical slice (code + test + typecheck + lint), commits per task with conventional commits, marks `[x]` in the same commit, then finalizes by proposing a PR. Triggers on "execute the plan", "implement docs/plans/FR-001.md", "run the dev loop on FR-001", "ship FR-001", "/execute FR-N".
Design state machines, orchestration workflows, saga patterns, and resilience strategies for distributed systems, AI agents, and complex async processes. Use when asking for a workflow, state machine, orchestration design, saga, HITL checkpoint, or process resilience strategy.
Write, rewrite, or normalize structured `*.spec.md` specification files for agent-driven development. Use this whenever the user asks for a spec, requirements, acceptance criteria, implementation-ready documentation, feature definition before coding, or wants an existing idea/codebase turned into an actionable spec, even if they do not explicitly say "spec".
Use when the user wants to bring UI designs into a project for a PRD requirement. Identifies the screens/states a requirement needs, helps the user generate them via Stitch or Claude Design (or import existing exports), and places HTML + screenshot pairs under docs/designs/<FR-N>-<slug>.{html,png} so implementation can reference them. Triggers on "import these designs", "add screens for FR-001", "set up the designs for this requirement", "vibe design this screen", "/designs FR-N".
Use when the user wants to author, refine, or audit a Product Requirements Document for AI coding agents. Walks through an 8-phase pipeline (Socratic discovery → PRD draft → acceptance criteria → adversarial review → task decomposition → AI-readiness gate → test generation → handoff). Triggers on "write a PRD", "spec this feature", "draft requirements", "prepare X for Claude/Cursor/Copilot/Windsurf/Aider to build", "audit my PRD", "is this PRD AI-ready", "score this spec".