architecture
01Command Claude Code
Defines the System Architecture — stack, DBs, infra.
Command Claude Code
Defines the System Architecture — stack, DBs, infra.
Command Claude Code
Runs tasks — delegates coding to sub-agents, tracks progress.
Command Claude Code
Defines the Product — what, why, and for who.
Command Claude Code
Builds the Product Roadmap — features and their order.
Command Claude Code
Creates the Functional Spec — what the feature does for the user.
Command Claude Code
Breaks the Tech Spec into a task list for engineers.
Command Claude Code
Creates the Technical Spec — how the feature will be built.
Command Claude Code
Verifies spec completion — checks acceptance criteria, marks Status as Completed.
MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
MCP server "awslabs.aws-documentation-mcp-server" as configured in provectus/awos-recruitment. Runs locally from the awslabs.aws-documentation-mcp-server@latest Python package. Needs 3 environment variables to run.
MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
MCP server "posthog", hosted remotely at mcp.posthog.com, as configured in provectus/awos-recruitment.
Agent Claude Code
Designs and builds agentic AI workflows for insurance underwriting on AWS Bedrock AgentCore. Combines underwriting domain knowledge with LangGraph and AgentCore implementation expertise. Produces pipeline specifications before writing code. Use when creating automated submission processing pipelines, extraction…
Agent Claude Code
Builds or changes AWS infrastructure with Terraform through a Research → Ground Truth → Design (with security and cost review) → Implement → Validate workflow, using the AWS knowledge, Terraform Registry, and AWS API MCP servers. Use proactively when a task creates or modifies Terraform for AWS resources and needs the…
Agent Claude Code
Spec-coverage auditor for AWOS projects. Invoked once per feature by the Feature Testing & Regression slice in tasks.md, after every implementation slice is done. Maps each acceptance criterion in functional-spec.md to the tests that already cover it, writes one acceptance-level test for each criterion that has none…
Skill Claude CodeCodex
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…
Skill Claude CodeCodex
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…
Skill Claude CodeCodex
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…
Skill Claude CodeCodex
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…
Skill Claude CodeCodex
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…
Skill Claude Code
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…
Skill Claude Code
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.
Skill Claude CodeCodex
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…
Skill Claude CodeCodex
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…
Skill Claude CodeCodex
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…
Skill Claude CodeCodex
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…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: