awos-recruitment

This skill should be used when the user asks to "create a SwiftUI view", "build an iOS app", "set up an Xcode project", "review Apple platform code", "add a widget", "create a watchOS app", "build for visionOS", "fix SwiftUI layout", or when generating any Swift code targeting Apple platforms (iOS, iPadOS, macOS, tvOS, watchOS, visionOS). Provides modern SwiftUI-first best practices covering UI patterns, app lifecycle, navigation, project structure, and platform-specific guidance. Covers Apple platform frameworks and app structure, not the language itself — for Swift language fundamentals use `swift-development` alongside it. Always generates Swift unless the project explicitly requires Objective-C.

AWS DynamoDB best practices for table design and data modeling. Use when designing DynamoDB schemas, choosing partition/sort keys, creating secondary indexes, modeling relationships, handling time series data, or optimizing query patterns. Triggers on tasks involving DynamoDB table creation, key design, GSI/LSI configuration, single-table design, adjacency lists, write sharding, or capacity planning. Does not cover DynamoDB SDK/API reference or CloudFormation/Terraform resource definitions.

AWS Lambda best practices for function design, configuration, and operations. Use when designing Lambda functions, choosing memory/timeout settings, planning concurrency and scaling, setting up monitoring, processing streams, or securing Lambda workloads. Triggers on tasks involving Lambda function creation, handler design, cold start optimization, idempotency, event source mapping, reserved/provisioned concurrency, or deciding whether Lambda is the right compute choice. Does not cover language-specific SDK patterns, CloudFormation/Terraform resource definitions, or Lambda@Edge.

This skill should be used when the user asks to "build a genomics pipeline", "pick an nf-core pipeline", "which aligner/variant caller should I use", "analyze RNA-seq", "analyze single-cell RNA-seq", "annotate variants", "interpret variants with ACMG criteria", "detect CNVs", "call structural variants", or when choosing tools, file formats, and QC thresholds for NGS data. Provides opinionated tool defaults (aligners, variant callers, annotators), genomics file-format and reproducibility conventions, an nf-core pipeline selection table, and detailed references for RNA-seq (bulk and single-cell), variant annotation with clinical interpretation, and CNV/SV analysis. It does not teach Nextflow DSL2, Snakemake, or WDL authoring — for writing workflow code by hand, use those frameworks' own documentation.

Provides Chroma Python client patterns — collection creation and configuration, add/upsert/query, metadata and document filtering syntax, and embedding function integration. Use when the user asks to "set up ChromaDB", "create a Chroma collection", "add embeddings to ChromaDB", "query ChromaDB", "search vectors", "semantic search with ChromaDB", "filter ChromaDB results", "ChromaDB metadata filtering", "configure Chroma", "use ChromaDB persistent client", "delete from ChromaDB", or when writing any code that interacts with the chromadb Python package. Does not cover the JavaScript client, Chroma Cloud, choosing an embedding model, or general RAG architecture.

FastAPI best practices and conventions. Use when writing, reviewing, or refactoring FastAPI applications — route handlers, Pydantic schemas, dependency injection, project structure, async patterns, testing, or API documentation. Triggers on tasks involving FastAPI routers, endpoints, request validation, response models, or application configuration. Does not cover general Python syntax or typing — see modern-python-development for that.

Provides up-to-date FastMCP API patterns for tools, resources, prompts, server composition, authentication, and deployment. Use when the user asks to "create an MCP server", "build an MCP tool", "add an MCP resource", "define MCP prompts", "set up FastMCP", "run an MCP server", "expose tools via MCP", "mount MCP sub-servers", "configure MCP transport", "add authentication to MCP", "test an MCP server", "use the MCP client", or when writing any Python code that uses the fastmcp package. Does not cover the MCP protocol spec, the TypeScript MCP SDK, or configuring MCP servers in Claude Code settings.

Use when GitHub Actions checks fail, workflow runs are red, or user asks to fix CI. Triggers on "fix CI", "actions failing", "checks are red", "pipeline broke", "workflow failed". User may provide a run URL, job ID, or just ask to fix. Commits fixes locally and stops; pass --push to let it push and re-check CI.

Use when the user wants to watch the current GitHub repo for pull requests that need their review — new PRs, explicit review requests, re-requests after new commits — e.g. "watch for incoming reviews", "check PRs needing my review", or to set up a recurring check. GitHub-only (gh CLI). Not for reviewing one specific known PR (invoke pr-review directly).

Jetpack Compose-first Kotlin patterns for Google/Android platforms: phone, tablet/foldable, Wear OS, Android TV/Google TV, Android Auto, Android Automotive, and AOSP devices (Meta Quest, Fire TV, Fire Tablet). Use whenever the user asks to "build an Android app", "create a Composable" or "add a screen", "set up an Android project", "review/refactor Android code", "build for Wear OS / TV / Auto / Automotive / Quest / Fire", "set up Room, DataStore, or local storage" (including migrations and encryption), "add in-app purchases / subscriptions / Play Billing", "write Android tests" (ViewModel, Composable, Room), "configure Android Lint", or when generating any Kotlin code that targets Android — even if they only mention Jetpack, Compose, or ViewModel. Covers UI, lifecycle, navigation, concurrency, storage, networking, media, billing, testing, Lint, and per-platform guidance. Pairs with `kotlin-development` for language fundamentals. Always generates Kotlin unless the project explicitly requires Java.

This skill should be used when the user asks to "write Kotlin code", "create a Kotlin class", "set up a Kotlin project", "review Kotlin code", "refactor Kotlin", "use Kotlin coroutines", "fix Kotlin style", "set up Detekt", "configure ktlint", "add static analysis to a Kotlin project", "set up Kotlin linting (Detekt, ktlint)", or when generating any Kotlin source code. Provides modern Kotlin 2.1+ best practices covering null safety, coroutines, data modeling, error handling, idiomatic patterns, and static analysis (Detekt, ktlint). Covers the language and stdlib only; the one framework-specific part is an optional Android/Compose lint section. For Android app code (Compose UI, lifecycle, platform APIs) use google-app-development alongside it.

Production patterns for LangGraph StateGraph workflows deployed on AWS Bedrock AgentCore. Use when building agentic AI workflows with LangGraph, deploying agents to AgentCore Runtime, adding interrupt-based human-in-the-loop review, or checkpointing workflows that run for days. Covers graph design, interrupt() HITL, checkpointing, 3-tier model routing with fallback chains, confidence calibration, Cedar policy enforcement, cost-aware pipeline design, Bedrock Foundation Models and Guardrails, MCP tools via AgentCore Gateway, and observability with LangSmith and CloudWatch. Not for insurance underwriting domain rules — see underwriting.

Provides modern Python 3.12+ best practices covering syntax, type hints, error handling, project structure, and idiomatic patterns. Use when the user asks to "write Python code", "create a Python module", "set up a Python project", "review Python code", "refactor Python", "add type hints", "fix Python style", or when generating any Python source code. Does not cover any specific library or framework — see the fastmcp, chromadb, pytest-best-practices and fastapi-best-practices skills for those.

Provides modern Python 3.12+ best practices covering syntax, type hints, error handling, project structure, and idiomatic patterns. Use when the user asks to "write Python code", "create a Python module", "set up a Python project", "review Python code", "refactor Python", "add type hints", "fix Python style", or when generating any Python source code. Does not cover any specific library or framework — see the fastmcp, chromadb, pytest-best-practices and fastapi-best-practices skills for those.

Provides patterns for building TypeScript CLI tools distributed via npx - package structure, the bin entry point and shebang, ESM-ready tsconfig, argument parsing, output and exit codes, local testing, and npm publishing. Use when the user asks to "create an npx package", "build a CLI tool with TypeScript", "set up a Node.js CLI", "publish an npm package", "configure package.json bin field", "add CLI argument parsing", or "create an executable npm package", or when writing TypeScript code for a command-line tool distributed via npx. Does not cover general TypeScript style, type design, or non-CLI project layout - see the typescript skill for those.

Postgres performance optimization and best practices. Use when writing or reviewing SQL queries, designing schemas, configuring connection pooling, fixing N+1 queries, creating indexes, implementing row-level security, diagnosing slow queries with EXPLAIN ANALYZE, or optimizing database performance. Postgres only — for DynamoDB use aws-dynamodb-best-practices; does not cover ORM- or migration-tool-specific APIs.

Applies code-review feedback to the user's own pull request or merge request — triages every reviewer comment in a fresh subagent, drafts a fix or reply per item, and after the user approves the plan, edits, replies, resolves, commits, and pushes. Use when working through review feedback — "address the PR comments", "address the MR comments", "reply to CodeRabbit/Codex feedback", "resolve these review threads", "apply this review". Public mode (default) works against GitHub or GitLab. Local mode — "apply this review locally", "apply the review for myself", "apply it but don't post" — applies a local review file to the working tree and posts nothing. This is the author's side; to review someone else's PR, use pr-review.

Authors a human-voice code review of someone else's pull request or merge request and posts it as a draft (pending) review for the user's approval — "review this PR", "do a code review on PR #N", "review this MR", "leave review comments". Also reviews the user's own branch when the request says "review my branch", "review locally", "review for myself", "just my branch", or "don't post": the review goes to a file and nothing is posted. Works on GitHub and GitLab. Finds issues by orchestrating the code-review and pr-review-toolkit plugins, drafts with no severity badges, and gates every post on the user's approval. This is the reviewer's side; to respond to feedback on a PR the user authored, use pr-comments-address.

Pytest conventions for Python test suites — fixtures and scopes, parametrization, mocking with pytest-mock, built-in fixtures (`tmp_path`, `monkeypatch`, `capsys`, `caplog`), markers, exception testing, and async tests. Use when writing, reviewing, or refactoring Python tests, `conftest.py` fixtures, or pytest configuration in `pytest.ini` / `pyproject.toml`. Does not cover general Python syntax or typing — see modern-python-development — nor FastAPI `TestClient` and app-level test setup — see fastapi-best-practices.

Performance optimization for React applications — rendering, re-renders, data-fetching waterfalls, bundle size, and the JavaScript hot paths inside components. Use when the user mentions slow or janky renders, unnecessary re-renders, memoization (React.memo / useMemo / useCallback), lazy loading, code splitting, bundle size, request waterfalls, duplicate or repeated API requests, request deduplication, caching fetched data in localStorage, scroll or touch event listeners, laggy scrolling or typing, or asks to review, profile, or speed up React code. Not a general React authoring guide — for folder and layer structure use react-feature-sliced-design, for language and typing questions use typescript-development.