Implement comprehensive error handling for actions. Covers the `wrapError()` method for action-level error wrapping, GlobalWrapError for app-wide error transformation, ErrorObserver for logging/monitoring, and the error handling flow (before → reduce → after).

Use the Event class to interact with Flutter's stateful widgets (TextField, ListView, etc.). Covers creating Event objects in state, consuming events with `context.event()`, scrolling lists, changing text fields, and the event lifecycle.

Integrate AsyncRedux with the flutter_hooks package. Covers adding flutter_hooks_async_redux, using the useSelector hook, and combining hooks with AsyncRedux state management.

Handle navigation through actions using NavigateAction. Covers setting up the navigator key, dispatching NavigateAction for push/pop/replace, and testing navigation in isolation.

Add the NonReentrant mixin to prevent an action from dispatching while already in progress. Covers preventing duplicate form submissions, avoiding race conditions, and protecting long-running operations.

Set up observers for debugging and monitoring. Covers implementing actionObservers for dispatch logging, stateObserver for state change tracking, combining observers with globalWrapError, and using observers for analytics.

Add the OptimisticUpdate mixin for instant UI feedback before server confirmation. Covers immediate state changes, automatic rollback on failure, and optionally notifying users of rollback.

Implement local state persistence using Persistor. Covers creating a custom Persistor class, implementing `readState()`, `persistDifference()`, `deleteState()`, using LocalPersist helper, throttling saves, and pausing/resuming persistence with app lifecycle.

Integrate AsyncRedux with the Provider package. Covers using provider_for_redux, the ReduxSelector widget, and choosing between StoreConnector and ReduxSelector approaches.

Add the Retry mixin for automatic retry with exponential backoff on action failure. Covers using Retry alone for limited retries, combining with UnlimitedRetries for infinite retries, and configuring retry behavior.

Create and cache selectors for efficient state access. Covers writing selector functions, caching with `cache1` and `cache2`, the reselect pattern, and avoiding repeated computations in widgets.

Initialize, setup and configure AsyncRedux in a Flutter app. Use it whenever starting a new AsyncRedux project, or when the user requests.

Access store state in widgets using `context.state`, `context.select()`, and `context.read()`. Covers when to use each method, setting up BuildContext extensions, and optimizing widget rebuilds with selective state access.

Design immutable state classes following AsyncRedux best practices. Includes creating the AppState class with a `copy()` method, defining `initialState()`, composing nested state objects, and optionally using the fast_immutable_collections package for IList, ISet, and IMap.

Manage Streams and Timers with AsyncRedux. Covers creating actions to start/stop streams, storing stream subscriptions in store props, dispatching actions from stream callbacks, and proper cleanup with disposeProps().

Creates AsyncRedux (Flutter) synchronous actions that update state immediately by implementing reduce() to return a new state.

Write unit tests for AsyncRedux actions using the Store directly. Covers creating test stores with initial state, using `dispatchAndWait()`, checking state after actions, verifying action errors via ActionStatus, and testing async actions.

Test StoreConnector view-models in isolation. Covers creating view-models with `Vm.createFrom()`, testing view-model properties, testing callbacks that dispatch actions, and verifying state changes from callbacks.

Use advanced wait methods for complex test scenarios. Covers `waitCondition()`, `waitAllActions()`, `waitActionType()`, `waitAllActionTypes()`, `waitAnyActionTypeFinishes()`, and the `completeImmediately` parameter.

Add the Throttle mixin to prevent actions from running too frequently. Covers setting the throttle duration in milliseconds, use cases like price refresh, and how freshness/staleness works.

Implement undo/redo functionality using state observers. Covers recording state history with stateObserver, creating a RecoverStateAction, implementing undo for the full state or partial state, and managing history limits.

Handle user-facing errors with UserException. Covers throwing UserException from actions, setting up UserExceptionDialog, customizing error dialogs with `onShowUserExceptionDialog`, and using UserExceptionAction for non-interrupting error display.

Use `waitCondition()` inside actions to pause execution until state meets criteria. Covers waiting for price thresholds, coordinating between actions, and implementing conditional workflows.

Show loading states and handle action failures in widgets. Covers `isWaiting(ActionType)` for spinners, `isFailed(ActionType)` for error states, `exceptionFor(ActionType)` for error messages, and `clearExceptionFor()` to reset failure states.

Convert PyTorch AT_DISPATCH macros to AT_DISPATCH_V2 format in ATen C++ code. Use when porting AT_DISPATCH_ALL_TYPES_AND*, AT_DISPATCH_FLOATING_TYPES*, or other dispatch macros to the new v2 API. For ATen kernel files, CUDA kernels, and native operator implementations.

Call accessible chromatin regions from ATAC-seq data using MACS3 with ATAC-specific parameters. Use when identifying open chromatin regions from aligned ATAC-seq BAM files, different from ChIP-seq peak calling.

Quality control metrics for ATAC-seq data including fragment size distribution, TSS enrichment, FRiP, and library complexity. Use when assessing ATAC-seq library quality before or after peak calling to identify problematic samples.

End-to-end ATAC-seq workflow from FASTQ files to differential accessibility and TF footprinting. Covers alignment, peak calling with MACS3, QC metrics, and optional TOBIAS footprinting. Use when running end-to-end ATAC-seq analysis from FASTQ to differential accessibility.

Interface with AtCoder for Japanese competitive programming contests

Coordinate Claude Code skills with OpenAI Codex autonomous workflows for end-to-end ATFT-GAT-FAN maintenance.

Enforce lint, formatting, typing, testing, and security hygiene across the ATFT-GAT-FAN codebase.

Manage J-Quants ingestion, feature graph generation, and cache hygiene for the ATFT-GAT-FAN dataset pipeline.

Drive quantitative analysis, factor diagnostics, and reporting for ATFT-GAT-FAN outputs.

Run and monitor ATFT-GAT-FAN training loops, hyper-parameter sweeps, and safety modes on A100 GPUs.

Use this skill when working with Athena Framework for Crystal. Athena is a modular ecosystem of independent, reusable components including: Framework (ATH) for web apps, DependencyInjection (ADI) for IoC containers, Routing (ART) for HTTP routing, Serializer (ASR) for object serialization, Validator (AVD) for validation, Console (ACON) for CLI tools, EventDispatcher (AED) for event-driven architecture, and more. Use for building Crystal web applications, REST APIs, CLI tools, or integrating individual components.

PROACTIVELY USED when reviewing a PR, branch, or Jira story. Handles code review against requirements and provides actionable feedback.

>

Documentation guidance for competition athletes and volunteers in WODsmith. Use when writing, reviewing, or improving athlete-facing documentation including registration, scheduling, workout viewing, leaderboards, check-in, and volunteer coordination.

Create brand-safe content for athletes. Personal branding strategy, engagement optimization, crisis communication, sponsor integration.

>

DevOps expertise for deployment, CI/CD, infrastructure, and automation

Adversarial quality gate agent for code review - finds flaws before users do

Product management expertise for story creation, backlog management, validation, and release coordination

Security audits, vulnerability analysis, and security best practices enforcement

Patterns for Atlas database schema management covering HCL/SQL schema definitions, versioned and declarative migrations, linting analyzers, testing, and project configuration. Use when working with atlas.hcl, .hcl schema files, Atlas CLI commands, or database migrations.

>

Specialized in Atlas ORM and database design for Gravito. Trigger this for schema design, migrations, or complex query building.

Full 9-phase workflow for complex features, epics, and security-critical changes (2-4 hours)

Iterative 3-phase workflow with peer review cycle for changes needing validation (15-30 min)

Orchestrates Atlas workflow tier selection for software development tasks