
Use when designing database schemas, normalization strategies, indexing plans, query optimization, and migration workflows for relational, document, or hybrid data stores.
Top-level design routing and critique skill for choosing the right system, web, mobile, or desktop design path, running audit-first diagnosis, and keeping downstream execution aligned to one clear contract.
Use when building FastAPI 0.115+ applications with Pydantic v2 models, async endpoints, dependency injection, OpenAPI documentation, background tasks, and security patterns.
Canonical dual-path skill for iOS simulator testing, mobile-mcp guidance, build automation, and accessibility-driven UI verification.
Use when working with Prisma 6+ for schema design, database migrations, client queries, relation modeling, edge deployment, and type-safe database access in TypeScript and Node.js applications.
Use when writing production Rust (2024 edition): ownership and borrowing patterns, async with tokio, error handling with thiserror/anyhow, comprehensive testing, and disciplined use of unsafe.
Use when building Spring Boot 3.4+ applications with Java records, virtual threads, Spring Security 6, Spring Data JPA, reactive WebFlux patterns, and production-grade testing strategies.
Orchestrate safe, design-first Google Stitch generation and editing by sequencing frontend-design, canonical design-system sync, prompt enhancement, Stitch MCP tool selection, and implementation handoff.
Use when writing, reviewing, or refactoring modern Swift, including strict concurrency, actors, SwiftUI with @Observable, structured concurrency, protocol-oriented design, and SPM modules.
API design best practices covering REST, GraphQL, gRPC patterns, versioning strategies, pagination, error contracts, and OpenAPI specifications for robust service interfaces.
Use when conducting code reviews, building review checklists, calibrating review depth, providing structured feedback, or establishing team review practices. Covers review methodology, feedback patterns, automated checks, and batch review strategies.
Use when investigating latest vendor behavior, comparing tools or platforms, verifying claims beyond the repo, or gathering external evidence before implementation.
Build or refresh the canonical design-system state for a repo, including DESIGN.md, overlays, token language, and platform-specific adaptation notes across web, mobile, and desktop.
Use when building or maintaining Docker Compose development environments: multi-service orchestration, volume mounts for hot reload, custom networking, debugging containers, health checks, and production-parity configuration.
Establish the design-engine execution order, canonical design-state model, and the repo-first constraints for serious frontend or mobile design work.
Adapt the design engine to mobile and Flutter surfaces using Foundry's normalized mobile-pattern dataset and implementation-first constraints.
Select a non-generic visual direction from Foundry's normalized design datasets and align it to the product's domain, audience, and platform.
Canonical dual-path skill for iOS simulator testing, mobile-mcp guidance, build automation, and accessibility-driven UI verification.
Use when building MCP servers with spec-compliant tools, structured outputs, resource providers, transport configuration, and server testing.
Use when building web applications with Next.js 15+. Invoke for App Router, Server Components, Server Actions, caching strategies, Partial Prerendering, parallel routes, middleware, and deployment.
Use when performing OWASP-aligned security reviews, including vulnerability analysis, secure code review, threat modeling, and SAST/DAST integration.
Use when turning a non-trivial request into a Git-tracked spec pack, maintaining traceability during execution, and updating specs before code when requirements or architecture change.
Use when building or refactoring Python data layers with SQLAlchemy 2.0+ declarative models, async sessions, Alembic migrations, relationship loading strategies, and ORM testing patterns.
Create or refresh a Stitch-compatible design-system context by maintaining docs/foundation/DESIGN.md as the canonical source and mirroring it to a Stitch-facing design file when Stitch flows need persistent visual consistency.
Use when writing, reviewing, or refactoring modern Swift, including strict concurrency, actors, SwiftUI with @Observable, structured concurrency, protocol-oriented design, and SPM modules.
System design and architecture guidance covering distributed systems, scalability, reliability, CAP theorem, load balancing, and caching strategies for production infrastructure.
Use when running browser QA in a real web session with Playwright MCP, deterministic navigation, screenshots, console evidence, network evidence, accessibility snapshots, or failure reproduction.
Diagnose visual and UX weaknesses in an existing interface and return prioritized, concrete remediation guidance.
Use when creating architecture documentation including C4 model diagrams, Architecture Decision Records, system context views, deployment diagrams, and quality attribute specifications.
Top-level design routing and critique skill for choosing the right system, web, mobile, or desktop design path, running audit-first diagnosis, and keeping downstream execution aligned to one clear contract.
Use when building Django 5.1+ REST APIs with Django REST Framework 3.15+, covering serializers, viewsets, permissions, filtering, pagination, and async support.
Establish the design-engine execution order, canonical design-state model, and the repo-first constraints for serious frontend or mobile design work.
Turn canonical design state plus overlays into a compact, high-signal screen brief for Stitch, frontend implementation, or Flutter/mobile work.
Build or refresh the canonical design-system state for a repo, including DESIGN.md, overlays, token language, and platform-specific adaptation notes.
Integration testing patterns for verifying component interactions across test boundaries, databases, APIs, test containers, and fixture management. Use when testing how components work together.
Use when running retrospectives, analyzing team metrics, performing root-cause analysis, and driving incremental process improvement.
Use when building NestJS 11+ applications with TypeScript decorators, dependency injection, modular architecture, guards, interceptors, pipes, microservices, and GraphQL integration.
Use when designing system prompts, crafting few-shot examples, implementing chain-of-thought reasoning, extracting structured output from LLMs, or building tool-use patterns for agent systems.
Design and implement secret and credential management strategies including vault integration, environment variable handling, rotation policies, secret scanning, and zero-trust credential distribution.
Orchestrate safe, design-first Google Stitch generation and editing by sequencing frontend-design, canonical design-system sync, prompt enhancement, Stitch MCP tool selection, and implementation handoff.
Convert final Stitch screen artifacts into minimal, repo-native frontend changes by reusing local components, preserving validated logic, and documenting any intentional drift from the design source.
Use when writing production TypeScript 5.9+ code: strict configuration, advanced type-level programming, discriminated unions, branded types, and patterns that prepare codebases for TS 6/7 evolution.
Design browser-first interfaces with strong visual direction, component architecture, responsive layout strategy, accessibility, and implementation-aware handoff for real web products.
Canonical dual-path skill for Android emulator testing, mobile-mcp guidance, adb control, UI-tree verification, and evidence capture.
Use when conducting code reviews, building review checklists, calibrating review depth, providing structured feedback, or establishing team review practices. Covers review methodology, feedback patterns, automated checks, and batch review strategies.
Use when investigating latest vendor behavior, comparing tools or platforms, verifying claims beyond the repo, or gathering external evidence before implementation.
Design desktop-first interfaces with multi-pane structure, keyboard-first productivity, high-information-density clarity, and implementation-aware handoff for desktop-grade app surfaces.
Use when building FastAPI 0.115+ applications with Pydantic v2 models, async endpoints, dependency injection, OpenAPI documentation, background tasks, and security patterns.
Translate design-engine output into repo-native implementation work, preferring real components, Flutter widgets, and existing tokens over pasted generated markup.
Select a non-generic visual direction from Foundry's normalized design datasets and align it to the product's domain, audience, and platform.
Use when defining git branching, commit conventions, merge or rebase policy, release flow, or monorepo collaboration patterns.
Use when writing, refactoring, or reviewing modern Kotlin (2.1+) code across JVM, Android, iOS, and multiplatform targets. Covers coroutines, Flow, Compose patterns, KMP architecture, DSL design, and production testing. Replaces kotlin-pro.
Use when building interactive Playwright suites for browser automation, visual regression, accessibility audits, network interception, and collaborative test workflows.
Convert final Stitch screen artifacts into minimal, repo-native frontend changes by reusing local components, preserving validated logic, and documenting any intentional drift from the design source.
Compatibility wrapper for explicit `stitch` requests.
Use when writing production TypeScript 5.9+ code: strict configuration, advanced type-level programming, discriminated unions, branded types, and patterns that prepare codebases for TS 6/7 evolution.
Use when running browser QA in a real web session with Playwright MCP, deterministic navigation, screenshots, console evidence, network evidence, accessibility snapshots, or failure reproduction.
Canonical dual-path skill for Android emulator testing, mobile-mcp guidance, adb control, UI-tree verification, and evidence capture.
Use when building or maintaining Expo applications: SDK 52+ features, EAS Build and Submit pipelines, OTA updates with expo-updates, native module integration via config plugins, push notifications with expo-notifications, and cross-platform testing.
Establish the design-engine execution order, canonical design-state model, and the repo-first constraints for serious frontend or mobile design work.
Canonical dual-path skill for iOS simulator testing, mobile-mcp guidance, build automation, and accessibility-driven UI verification.
Use when writing, refactoring, or reviewing modern Java (21+) code. Covers records, sealed classes, pattern matching, virtual threads, structured concurrency, and production testing with JUnit 5. Replaces java-pro.
Use when writing, refactoring, or reviewing modern Kotlin (2.1+) code across JVM, Android, iOS, and multiplatform targets. Covers coroutines, Flow, Compose patterns, KMP architecture, DSL design, and production testing. Replaces kotlin-pro.
Orchestrate safe, design-first Google Stitch generation and editing by sequencing frontend-design, canonical design-system sync, prompt enhancement, Stitch MCP tool selection, and implementation handoff.
Use when building web applications with Svelte 5 and SvelteKit. Invoke for rune-based reactivity ($state, $derived, $effect), file-based routing, form actions, server-side rendering, load functions, and deployment.
Use when running browser QA in a real web session with Playwright MCP, deterministic navigation, screenshots, console evidence, network evidence, accessibility snapshots, or failure reproduction.
Use when investigating latest vendor behavior, comparing tools or platforms, verifying claims beyond the repo, or gathering external evidence before implementation.
Use when turning a non-trivial request into a Git-tracked spec pack, maintaining traceability during execution, and updating specs before code when requirements or architecture change.
Create or refresh a Stitch-compatible design-system context by maintaining docs/foundation/DESIGN.md as the canonical source and mirroring it to a Stitch-facing design file when Stitch flows need persistent visual consistency.
Use when designing, optimizing, or debugging CI/CD pipelines: GitHub Actions workflows, GitLab CI configurations, pipeline caching strategies, matrix builds, deployment gates, artifact management, and release automation.
Use when creating or updating skills, evaluating skill performance, or benchmarking instruction quality. Covers skill authoring, edits, eval design, and iterative improvement of skill behavior.
Use when writing, reviewing, or refactoring modern C#/.NET code, including minimal APIs, records, async streams, pattern matching, DI lifetimes, and memory-efficient performance tuning.
Build or refresh the canonical design-system state for a repo, including DESIGN.md, overlays, token language, and platform-specific adaptation notes across web, mobile, and desktop.
Use when building or maintaining Docker Compose development environments: multi-service orchestration, volume mounts for hot reload, custom networking, debugging containers, health checks, and production-parity configuration.
Adapt the design engine to mobile and Flutter surfaces using Foundry's normalized mobile-pattern dataset and implementation-first constraints.
Build or refresh the canonical design-system state for a repo, including DESIGN.md, overlays, token language, and platform-specific adaptation notes.
Use when designing or managing Kubernetes deployments: Deployment and StatefulSet configurations, Service and Ingress routing, Helm chart authoring, resource requests and limits, health checks, rolling updates, and production hardening.
Use when building web applications with Next.js 15+. Invoke for App Router, Server Components, Server Actions, caching strategies, Partial Prerendering, parallel routes, middleware, and deployment.
Create or refresh a Stitch-compatible design-system context by maintaining docs/foundation/DESIGN.md as the canonical source and mirroring it to a Stitch-facing design file when Stitch flows need persistent visual consistency.
Use when building web applications with Svelte 5 and SvelteKit. Invoke for rune-based reactivity ($state, $derived, $effect), file-based routing, form actions, server-side rendering, load functions, and deployment.
System design and architecture guidance covering distributed systems, scalability, reliability, CAP theorem, load balancing, and caching strategies for production infrastructure.
Use when writing technical documentation including API references, operational runbooks, onboarding guides, decision logs, and changelog standards.
Use when running browser QA in a real web session with Playwright MCP, deterministic navigation, screenshots, console evidence, network evidence, accessibility snapshots, or failure reproduction.
Research the relevant codebase surface and produce a structured implementation plan before writing code.
Top-level design routing and critique skill for choosing the right system, web, mobile, or desktop design path, running audit-first diagnosis, and keeping downstream execution aligned to one clear contract.
Use when running retrospectives, analyzing team metrics, performing root-cause analysis, and driving incremental process improvement.
Use when building FastAPI 0.115+ applications with Pydantic v2 models, async endpoints, dependency injection, OpenAPI documentation, background tasks, and security patterns.
Adapt the design engine to mobile and Flutter surfaces using Foundry's normalized mobile-pattern dataset and implementation-first constraints.
Build or refresh the canonical design-system state for a repo, including DESIGN.md, overlays, token language, and platform-specific adaptation notes.
Use when defining git branching, commit conventions, merge or rebase policy, release flow, or monorepo collaboration patterns.
Canonical dual-path skill for iOS simulator testing, mobile-mcp guidance, build automation, and accessibility-driven UI verification.
Use when running retrospectives, analyzing team metrics, performing root-cause analysis, and driving incremental process improvement.
Use when designing or managing Kubernetes deployments: Deployment and StatefulSet configurations, Service and Ingress routing, Helm chart authoring, resource requests and limits, health checks, rolling updates, and production hardening.
Use when building NestJS 11+ applications with TypeScript decorators, dependency injection, modular architecture, guards, interceptors, pipes, microservices, and GraphQL integration.
Use when building web applications with Next.js 15+. Invoke for App Router, Server Components, Server Actions, caching strategies, Partial Prerendering, parallel routes, middleware, and deployment.
Guide authorized penetration testing engagements using PTES methodology. Covers reconnaissance, vulnerability scanning, exploitation, post-exploitation, and professional reporting. Requires explicit authorization before any testing activity.
Use when working with Prisma 6+ for schema design, database migrations, client queries, relation modeling, edge deployment, and type-safe database access in TypeScript and Node.js applications.
Use when writing production Python 3.12–3.14 code: modern typing with PEP 695/696 syntax, async service patterns, packaging with pyproject.toml, pytest-based testing, and standard-library-first design.
Use when building user interfaces with React 19+. Invoke for Server Components, the use() hook, Suspense, Actions, concurrent features, ref callbacks, and component architecture.
Design and implement secret and credential management strategies including vault integration, environment variable handling, rotation policies, secret scanning, and zero-trust credential distribution.
Use when writing technical documentation including API references, operational runbooks, onboarding guides, decision logs, and changelog standards.
Orchestrate safe, design-first Google Stitch generation and editing by sequencing frontend-design, canonical design-system sync, prompt enhancement, Stitch MCP tool selection, and implementation handoff.
Use when building web applications with Svelte 5 and SvelteKit. Invoke for rune-based reactivity ($state, $derived, $effect), file-based routing, form actions, server-side rendering, load functions, and deployment.
Systematic debugging methodology covering root cause analysis, bisection, logging strategies, debugger workflows, and post-mortem documentation. Use when diagnosing complex or elusive bugs.
Plan and implement delivery pipeline or runtime deployment changes with verification and rollback awareness.
Unit testing best practices covering test design, mocking strategies, coverage analysis, TDD workflow, and assertion patterns. Use when writing, reviewing, or improving unit tests.
Design browser-first interfaces with strong visual direction, component architecture, responsive layout strategy, accessibility, and implementation-aware handoff for real web products.
Define or refine reusable design tokens, components, and rules so the interface system becomes more coherent and scalable.
Run a bounded autonomous iteration loop that keeps executing, verifying, and tightening scope until the task is done or blocked.
Use when designing, optimizing, or debugging CI/CD pipelines: GitHub Actions workflows, GitLab CI configurations, pipeline caching strategies, matrix builds, deployment gates, artifact management, and release automation.
Use when investigating latest vendor behavior, comparing tools or platforms, verifying claims beyond the repo, or gathering external evidence before implementation.
Design desktop-first interfaces with multi-pane structure, keyboard-first productivity, high-information-density clarity, and implementation-aware handoff for desktop-grade app surfaces.
Use when building FastAPI 0.115+ applications with Pydantic v2 models, async endpoints, dependency injection, OpenAPI documentation, background tasks, and security patterns.
Select a non-generic visual direction from Foundry's normalized design datasets and align it to the product's domain, audience, and platform.
Use when building or refactoring Python data layers with SQLAlchemy 2.0+ declarative models, async sessions, Alembic migrations, relationship loading strategies, and ORM testing patterns.
Use when building MCP servers with spec-compliant tools, structured outputs, resource providers, transport configuration, and server testing.
Use when performing OWASP-aligned security reviews, including vulnerability analysis, secure code review, threat modeling, and SAST/DAST integration.
Use when building user interfaces with React 19+. Invoke for Server Components, the use() hook, Suspense, Actions, concurrent features, ref callbacks, and component architecture.
Use when creating or updating skills, evaluating skill performance, or benchmarking instruction quality. Covers skill authoring, edits, eval design, and iterative improvement of skill behavior.
Transform rough UI intent into compact, Stitch-ready prompts that encode visual direction, component structure, design-system context, and constrained change scope.
Systematic debugging methodology covering root cause analysis, bisection, logging strategies, debugger workflows, and post-mortem documentation. Use when diagnosing complex or elusive bugs.
Unit testing best practices covering test design, mocking strategies, coverage analysis, TDD workflow, and assertion patterns. Use when writing, reviewing, or improving unit tests.
Research the relevant codebase surface and produce a structured implementation plan before writing code.
Use when creating architecture documentation including C4 model diagrams, Architecture Decision Records, system context views, deployment diagrams, and quality attribute specifications.
Use when conducting code reviews, building review checklists, calibrating review depth, providing structured feedback, or establishing team review practices. Covers review methodology, feedback patterns, automated checks, and batch review strategies.
Use when designing database schemas, normalization strategies, indexing plans, query optimization, and migration workflows for relational, document, or hybrid data stores.
Use when investigating latest vendor behavior, comparing tools or platforms, verifying claims beyond the repo, or gathering external evidence before implementation.
Use when building or maintaining Docker Compose development environments: multi-service orchestration, volume mounts for hot reload, custom networking, debugging containers, health checks, and production-parity configuration.
Use when building FastAPI 0.115+ applications with Pydantic v2 models, async endpoints, dependency injection, OpenAPI documentation, background tasks, and security patterns.
Translate design-engine output into repo-native implementation work, preferring real components, Flutter widgets, and existing tokens over pasted generated markup.
Use when defining git branching, commit conventions, merge or rebase policy, release flow, or monorepo collaboration patterns.
Integration testing patterns for verifying component interactions across test boundaries, databases, APIs, test containers, and fixture management. Use when testing how components work together.
Use when running retrospectives, analyzing team metrics, performing root-cause analysis, and driving incremental process improvement.
Use when building NestJS 11+ applications with TypeScript decorators, dependency injection, modular architecture, guards, interceptors, pipes, microservices, and GraphQL integration.
Use when building interactive Playwright suites for browser automation, visual regression, accessibility audits, network interception, and collaborative test workflows.
Use when working with Prisma 6+ for schema design, database migrations, client queries, relation modeling, edge deployment, and type-safe database access in TypeScript and Node.js applications.
Use when creating or updating skills, evaluating skill performance, or benchmarking instruction quality. Covers skill authoring, edits, eval design, and iterative improvement of skill behavior.
Use when building Spring Boot 3.4+ applications with Java records, virtual threads, Spring Security 6, Spring Data JPA, reactive WebFlux patterns, and production-grade testing strategies.
Use when writing production TypeScript 5.9+ code: strict configuration, advanced type-level programming, discriminated unions, branded types, and patterns that prepare codebases for TS 6/7 evolution.
Convert final Stitch screen artifacts into minimal, repo-native frontend changes by reusing local components, preserving validated logic, and documenting any intentional drift from the design source.
API design best practices covering REST, GraphQL, gRPC patterns, versioning strategies, pagination, error contracts, and OpenAPI specifications for robust service interfaces.
Use when designing, optimizing, or debugging CI/CD pipelines: GitHub Actions workflows, GitLab CI configurations, pipeline caching strategies, matrix builds, deployment gates, artifact management, and release automation.
Systematic debugging methodology covering root cause analysis, bisection, logging strategies, debugger workflows, and post-mortem documentation. Use when diagnosing complex or elusive bugs.
Compatibility wrapper for explicit `stitch` requests.
Turn a product goal into a concrete screen direction, then implement or hand off the resulting UI specification.
Turn a product goal into a concrete screen direction, then implement or hand off the resulting UI specification.
Translate design-engine output into repo-native implementation work, preferring real components, Flutter widgets, and existing tokens over pasted generated markup.
Translate design-engine output into repo-native implementation work, preferring real components, Flutter widgets, and existing tokens over pasted generated markup.
Translate design-engine output into repo-native implementation work, preferring real components, Flutter widgets, and existing tokens over pasted generated markup.
Build or refresh the canonical design-system state for a repo, including DESIGN.md, overlays, token language, and platform-specific adaptation notes across web, mobile, and desktop.
Define or refine reusable design tokens, components, and rules so the interface system becomes more coherent and scalable.
Build or refresh the canonical design-system state for a repo, including DESIGN.md, overlays, token language, and platform-specific adaptation notes across web, mobile, and desktop.
Build or refresh the canonical design-system state for a repo, including DESIGN.md, overlays, token language, and platform-specific adaptation notes across web, mobile, and desktop.
Design desktop-first interfaces with multi-pane structure, keyboard-first productivity, high-information-density clarity, and implementation-aware handoff for desktop-grade app surfaces.
Use when writing, refactoring, or reviewing modern Kotlin (2.1+) code across JVM, Android, iOS, and multiplatform targets. Covers coroutines, Flow, Compose patterns, KMP architecture, DSL design, and production testing. Replaces kotlin-pro.
Design desktop-first interfaces with multi-pane structure, keyboard-first productivity, high-information-density clarity, and implementation-aware handoff for desktop-grade app surfaces.
Use when building Django 5.1+ REST APIs with Django REST Framework 3.15+, covering serializers, viewsets, permissions, filtering, pagination, and async support.
Turn canonical design state plus overlays into a compact, high-signal screen brief for Stitch, frontend implementation, or Flutter/mobile work.
Use when building Django 5.1+ REST APIs with Django REST Framework 3.15+, covering serializers, viewsets, permissions, filtering, pagination, and async support.
Use when building Django 5.1+ REST APIs with Django REST Framework 3.15+, covering serializers, viewsets, permissions, filtering, pagination, and async support.
Use when building Django 5.1+ REST APIs with Django REST Framework 3.15+, covering serializers, viewsets, permissions, filtering, pagination, and async support.
Use when conducting code reviews, building review checklists, calibrating review depth, providing structured feedback, or establishing team review practices. Covers review methodology, feedback patterns, automated checks, and batch review strategies.
Canonical dual-path skill for Android emulator testing, mobile-mcp guidance, adb control, UI-tree verification, and evidence capture.
Canonical dual-path skill for Android emulator testing, mobile-mcp guidance, adb control, UI-tree verification, and evidence capture.
Canonical dual-path skill for Android emulator testing, mobile-mcp guidance, adb control, UI-tree verification, and evidence capture.
API design best practices covering REST, GraphQL, gRPC patterns, versioning strategies, pagination, error contracts, and OpenAPI specifications for robust service interfaces.
API design best practices covering REST, GraphQL, gRPC patterns, versioning strategies, pagination, error contracts, and OpenAPI specifications for robust service interfaces.
API design best practices covering REST, GraphQL, gRPC patterns, versioning strategies, pagination, error contracts, and OpenAPI specifications for robust service interfaces.
Use when creating architecture documentation including C4 model diagrams, Architecture Decision Records, system context views, deployment diagrams, and quality attribute specifications.
Use when creating architecture documentation including C4 model diagrams, Architecture Decision Records, system context views, deployment diagrams, and quality attribute specifications.
Use when creating architecture documentation including C4 model diagrams, Architecture Decision Records, system context views, deployment diagrams, and quality attribute specifications.
Use when designing, optimizing, or debugging CI/CD pipelines: GitHub Actions workflows, GitLab CI configurations, pipeline caching strategies, matrix builds, deployment gates, artifact management, and release automation.
Use when designing, optimizing, or debugging CI/CD pipelines: GitHub Actions workflows, GitLab CI configurations, pipeline caching strategies, matrix builds, deployment gates, artifact management, and release automation.
Use when designing, optimizing, or debugging CI/CD pipelines: GitHub Actions workflows, GitLab CI configurations, pipeline caching strategies, matrix builds, deployment gates, artifact management, and release automation.
Use when conducting code reviews, building review checklists, calibrating review depth, providing structured feedback, or establishing team review practices. Covers review methodology, feedback patterns, automated checks, and batch review strategies.
Use when conducting code reviews, building review checklists, calibrating review depth, providing structured feedback, or establishing team review practices. Covers review methodology, feedback patterns, automated checks, and batch review strategies.
Use when writing, reviewing, or refactoring modern C#/.NET code, including minimal APIs, records, async streams, pattern matching, DI lifetimes, and memory-efficient performance tuning.
Use when writing, reviewing, or refactoring modern C#/.NET code, including minimal APIs, records, async streams, pattern matching, DI lifetimes, and memory-efficient performance tuning.
Use when writing, reviewing, or refactoring modern C#/.NET code, including minimal APIs, records, async streams, pattern matching, DI lifetimes, and memory-efficient performance tuning.
Use when writing, reviewing, or refactoring modern C#/.NET code, including minimal APIs, records, async streams, pattern matching, DI lifetimes, and memory-efficient performance tuning.
Use when writing, reviewing, or refactoring modern C#/.NET code, including minimal APIs, records, async streams, pattern matching, DI lifetimes, and memory-efficient performance tuning.
Use when designing database schemas, normalization strategies, indexing plans, query optimization, and migration workflows for relational, document, or hybrid data stores.
Use when designing database schemas, normalization strategies, indexing plans, query optimization, and migration workflows for relational, document, or hybrid data stores.
Use when designing database schemas, normalization strategies, indexing plans, query optimization, and migration workflows for relational, document, or hybrid data stores.
Use when designing database schemas, normalization strategies, indexing plans, query optimization, and migration workflows for relational, document, or hybrid data stores.
Investigate a failure systematically, confirm the root cause, and verify the fix path.
Investigate a failure systematically, confirm the root cause, and verify the fix path.
Use when investigating latest vendor behavior, comparing tools or platforms, verifying claims beyond the repo, or gathering external evidence before implementation.
Plan and implement delivery pipeline or runtime deployment changes with verification and rollback awareness.
Top-level design routing and critique skill for choosing the right system, web, mobile, or desktop design path, running audit-first diagnosis, and keeping downstream execution aligned to one clear contract.
Top-level design routing and critique skill for choosing the right system, web, mobile, or desktop design path, running audit-first diagnosis, and keeping downstream execution aligned to one clear contract.
Diagnose visual and UX weaknesses in an existing interface and return prioritized, concrete remediation guidance.
Capture or refresh the project's canonical design context in `docs/foundation/DESIGN.md` so downstream design, implementation, and QA skills stop relying on vague taste or one-off prompts.
Capture or refresh the project's canonical design context in `docs/foundation/DESIGN.md` so downstream design, implementation, and QA skills stop relying on vague taste or one-off prompts.
Capture or refresh the project's canonical design context in `docs/foundation/DESIGN.md` so downstream design, implementation, and QA skills stop relying on vague taste or one-off prompts.
Use when building or maintaining Docker Compose development environments: multi-service orchestration, volume mounts for hot reload, custom networking, debugging containers, health checks, and production-parity configuration.
Use when building or maintaining Docker Compose development environments: multi-service orchestration, volume mounts for hot reload, custom networking, debugging containers, health checks, and production-parity configuration.
Use when building or maintaining Expo applications: SDK 52+ features, EAS Build and Submit pipelines, OTA updates with expo-updates, native module integration via config plugins, push notifications with expo-notifications, and cross-platform testing.
Use when building or maintaining Expo applications: SDK 52+ features, EAS Build and Submit pipelines, OTA updates with expo-updates, native module integration via config plugins, push notifications with expo-notifications, and cross-platform testing.
Use when building or maintaining Expo applications: SDK 52+ features, EAS Build and Submit pipelines, OTA updates with expo-updates, native module integration via config plugins, push notifications with expo-notifications, and cross-platform testing.
Use when building or maintaining Expo applications: SDK 52+ features, EAS Build and Submit pipelines, OTA updates with expo-updates, native module integration via config plugins, push notifications with expo-notifications, and cross-platform testing.
Use when a task needs a public UI-design entrypoint that locks visual direction, captures a style contract, and routes into design-system, web, mobile, or desktop execution without generic AI aesthetics.
Use when a task needs a public UI-design entrypoint that locks visual direction, captures a style contract, and routes into design-system, web, mobile, or desktop execution without generic AI aesthetics.
Use when a task needs a public UI-design entrypoint that locks visual direction, captures a style contract, and routes into design-system, web, mobile, or desktop execution without generic AI aesthetics.
Use when a task needs a public UI-design entrypoint that locks visual direction, captures a style contract, and routes into design-system, web, mobile, or desktop execution without generic AI aesthetics.
Use when a task needs a public UI-design entrypoint that locks visual direction, captures a style contract, and routes into design-system, web, mobile, or desktop execution without generic AI aesthetics.
Establish the design-engine execution order, canonical design-state model, and the repo-first constraints for serious frontend or mobile design work.
Establish the design-engine execution order, canonical design-state model, and the repo-first constraints for serious frontend or mobile design work.
Adapt the design engine to mobile and Flutter surfaces using Foundry's normalized mobile-pattern dataset and implementation-first constraints.
Turn canonical design state plus overlays into a compact, high-signal screen brief for Stitch, frontend implementation, or Flutter/mobile work.
Turn canonical design state plus overlays into a compact, high-signal screen brief for Stitch, frontend implementation, or Flutter/mobile work.
Select a non-generic visual direction from Foundry's normalized design datasets and align it to the product's domain, audience, and platform.
Select a non-generic visual direction from Foundry's normalized design datasets and align it to the product's domain, audience, and platform.
Build or refresh the canonical design-system state for a repo, including DESIGN.md, overlays, token language, and platform-specific adaptation notes.
Build or refresh the canonical design-system state for a repo, including DESIGN.md, overlays, token language, and platform-specific adaptation notes.
Use when defining git branching, commit conventions, merge or rebase policy, release flow, or monorepo collaboration patterns.
Use when defining git branching, commit conventions, merge or rebase policy, release flow, or monorepo collaboration patterns.
Use when writing production Go 1.24+ code: generics with constraints, structured concurrency via errgroup and context, comprehensive error handling with wrapped sentinels, and performance-profiled service design.
Use when writing production Go 1.24+ code: generics with constraints, structured concurrency via errgroup and context, comprehensive error handling with wrapped sentinels, and performance-profiled service design.
Use when writing production Go 1.24+ code: generics with constraints, structured concurrency via errgroup and context, comprehensive error handling with wrapped sentinels, and performance-profiled service design.
Use when writing production Go 1.24+ code: generics with constraints, structured concurrency via errgroup and context, comprehensive error handling with wrapped sentinels, and performance-profiled service design.
Use when writing production Go 1.24+ code: generics with constraints, structured concurrency via errgroup and context, comprehensive error handling with wrapped sentinels, and performance-profiled service design.
Execute a scoped change end-to-end, using the smallest set of skills and checks required to finish correctly.
Integration testing patterns for verifying component interactions across test boundaries, databases, APIs, test containers, and fixture management. Use when testing how components work together.
Integration testing patterns for verifying component interactions across test boundaries, databases, APIs, test containers, and fixture management. Use when testing how components work together.
Integration testing patterns for verifying component interactions across test boundaries, databases, APIs, test containers, and fixture management. Use when testing how components work together.
Canonical dual-path skill for iOS simulator testing, mobile-mcp guidance, build automation, and accessibility-driven UI verification.
Use when designing or managing Kubernetes deployments: Deployment and StatefulSet configurations, Service and Ingress routing, Helm chart authoring, resource requests and limits, health checks, rolling updates, and production hardening.
Use when writing, refactoring, or reviewing modern Java (21+) code. Covers records, sealed classes, pattern matching, virtual threads, structured concurrency, and production testing with JUnit 5. Replaces java-pro.
Use when writing, refactoring, or reviewing modern Java (21+) code. Covers records, sealed classes, pattern matching, virtual threads, structured concurrency, and production testing with JUnit 5. Replaces java-pro.
Use when writing, refactoring, or reviewing modern Java (21+) code. Covers records, sealed classes, pattern matching, virtual threads, structured concurrency, and production testing with JUnit 5. Replaces java-pro.
Use when writing, refactoring, or reviewing modern Java (21+) code. Covers records, sealed classes, pattern matching, virtual threads, structured concurrency, and production testing with JUnit 5. Replaces java-pro.
Use when running retrospectives, analyzing team metrics, performing root-cause analysis, and driving incremental process improvement.
Use when writing, refactoring, or reviewing modern Kotlin (2.1+) code across JVM, Android, iOS, and multiplatform targets. Covers coroutines, Flow, Compose patterns, KMP architecture, DSL design, and production testing. Replaces kotlin-pro.
Use when writing, refactoring, or reviewing modern Kotlin (2.1+) code across JVM, Android, iOS, and multiplatform targets. Covers coroutines, Flow, Compose patterns, KMP architecture, DSL design, and production testing. Replaces kotlin-pro.
Use when designing or managing Kubernetes deployments: Deployment and StatefulSet configurations, Service and Ingress routing, Helm chart authoring, resource requests and limits, health checks, rolling updates, and production hardening.
Design mobile-first interfaces with strong small-screen hierarchy, thumb-reachable interaction design, native-feeling flow structure, and implementation-aware handoff for Flutter or other app surfaces.
Use when performing OWASP-aligned security reviews, including vulnerability analysis, secure code review, threat modeling, and SAST/DAST integration.
Use when designing or managing Kubernetes deployments: Deployment and StatefulSet configurations, Service and Ingress routing, Helm chart authoring, resource requests and limits, health checks, rolling updates, and production hardening.
Run a bounded autonomous iteration loop that keeps executing, verifying, and tightening scope until the task is done or blocked.
Use when building MCP servers with spec-compliant tools, structured outputs, resource providers, transport configuration, and server testing.
Use when building MCP servers with spec-compliant tools, structured outputs, resource providers, transport configuration, and server testing.
Design mobile-first interfaces with strong small-screen hierarchy, thumb-reachable interaction design, native-feeling flow structure, and implementation-aware handoff for Flutter or other app surfaces.
Design mobile-first interfaces with strong small-screen hierarchy, thumb-reachable interaction design, native-feeling flow structure, and implementation-aware handoff for Flutter or other app surfaces.
Design mobile-first interfaces with strong small-screen hierarchy, thumb-reachable interaction design, native-feeling flow structure, and implementation-aware handoff for Flutter or other app surfaces.
Use when building NestJS 11+ applications with TypeScript decorators, dependency injection, modular architecture, guards, interceptors, pipes, microservices, and GraphQL integration.
Use when building NestJS 11+ applications with TypeScript decorators, dependency injection, modular architecture, guards, interceptors, pipes, microservices, and GraphQL integration.
Use when building web applications with Next.js 15+. Invoke for App Router, Server Components, Server Actions, caching strategies, Partial Prerendering, parallel routes, middleware, and deployment.
Use when building web applications with Next.js 15+. Invoke for App Router, Server Components, Server Actions, caching strategies, Partial Prerendering, parallel routes, middleware, and deployment.
Use when implementing observability and monitoring: OpenTelemetry instrumentation, structured logging, metrics design, distributed tracing, alerting strategies, SLO/SLI definitions, dashboards, and incident response runbooks.
Use when implementing observability and monitoring: OpenTelemetry instrumentation, structured logging, metrics design, distributed tracing, alerting strategies, SLO/SLI definitions, dashboards, and incident response runbooks.
Use when implementing observability and monitoring: OpenTelemetry instrumentation, structured logging, metrics design, distributed tracing, alerting strategies, SLO/SLI definitions, dashboards, and incident response runbooks.
Use when implementing observability and monitoring: OpenTelemetry instrumentation, structured logging, metrics design, distributed tracing, alerting strategies, SLO/SLI definitions, dashboards, and incident response runbooks.
Use when performing OWASP-aligned security reviews, including vulnerability analysis, secure code review, threat modeling, and SAST/DAST integration.
Use when performing OWASP-aligned security reviews, including vulnerability analysis, secure code review, threat modeling, and SAST/DAST integration.
Guide authorized penetration testing engagements using PTES methodology. Covers reconnaissance, vulnerability scanning, exploitation, post-exploitation, and professional reporting. Requires explicit authorization before any testing activity.
Guide authorized penetration testing engagements using PTES methodology. Covers reconnaissance, vulnerability scanning, exploitation, post-exploitation, and professional reporting. Requires explicit authorization before any testing activity.
Guide authorized penetration testing engagements using PTES methodology. Covers reconnaissance, vulnerability scanning, exploitation, post-exploitation, and professional reporting. Requires explicit authorization before any testing activity.
Guide authorized penetration testing engagements using PTES methodology. Covers reconnaissance, vulnerability scanning, exploitation, post-exploitation, and professional reporting. Requires explicit authorization before any testing activity.
Use when building interactive Playwright suites for browser automation, visual regression, accessibility audits, network interception, and collaborative test workflows.
Use when building interactive Playwright suites for browser automation, visual regression, accessibility audits, network interception, and collaborative test workflows.
Consolidated QA capability with three modes: harness, web, and mobile.
Use when building interactive Playwright suites for browser automation, visual regression, accessibility audits, network interception, and collaborative test workflows.
Use when working with Prisma 6+ for schema design, database migrations, client queries, relation modeling, edge deployment, and type-safe database access in TypeScript and Node.js applications.
Use when working with Prisma 6+ for schema design, database migrations, client queries, relation modeling, edge deployment, and type-safe database access in TypeScript and Node.js applications.
Use when designing system prompts, crafting few-shot examples, implementing chain-of-thought reasoning, extracting structured output from LLMs, or building tool-use patterns for agent systems.
Use when designing system prompts, crafting few-shot examples, implementing chain-of-thought reasoning, extracting structured output from LLMs, or building tool-use patterns for agent systems.
Use when writing production Python 3.12–3.14 code: modern typing with PEP 695/696 syntax, async service patterns, packaging with pyproject.toml, pytest-based testing, and standard-library-first design.
Use when writing production Python 3.12–3.14 code: modern typing with PEP 695/696 syntax, async service patterns, packaging with pyproject.toml, pytest-based testing, and standard-library-first design.
Use when writing production Python 3.12–3.14 code: modern typing with PEP 695/696 syntax, async service patterns, packaging with pyproject.toml, pytest-based testing, and standard-library-first design.
Use when writing production Python 3.12–3.14 code: modern typing with PEP 695/696 syntax, async service patterns, packaging with pyproject.toml, pytest-based testing, and standard-library-first design.
Consolidated QA capability with three modes: harness, web, and mobile.
Consolidated QA capability with three modes: harness, web, and mobile.
Use when building user interfaces with React 19+. Invoke for Server Components, the use() hook, Suspense, Actions, concurrent features, ref callbacks, and component architecture.
Use when building user interfaces with React 19+. Invoke for Server Components, the use() hook, Suspense, Actions, concurrent features, ref callbacks, and component architecture.
Audit a change set for correctness, regression risk, missing tests, and security issues.
Audit a change set for correctness, regression risk, missing tests, and security issues.
Use when writing production Rust (2024 edition): ownership and borrowing patterns, async with tokio, error handling with thiserror/anyhow, comprehensive testing, and disciplined use of unsafe.
Use when writing production Rust (2024 edition): ownership and borrowing patterns, async with tokio, error handling with thiserror/anyhow, comprehensive testing, and disciplined use of unsafe.
Design and implement secret and credential management strategies including vault integration, environment variable handling, rotation policies, secret scanning, and zero-trust credential distribution.
Design and implement secret and credential management strategies including vault integration, environment variable handling, rotation policies, secret scanning, and zero-trust credential distribution.
Design and implement secret and credential management strategies including vault integration, environment variable handling, rotation policies, secret scanning, and zero-trust credential distribution.
Use when creating or updating skills, evaluating skill performance, or benchmarking instruction quality. Covers skill authoring, edits, eval design, and iterative improvement of skill behavior.
Use when creating or updating skills, evaluating skill performance, or benchmarking instruction quality. Covers skill authoring, edits, eval design, and iterative improvement of skill behavior.
Use when turning a non-trivial request into a Git-tracked spec pack, maintaining traceability during execution, and updating specs before code when requirements or architecture change.
Use when turning a non-trivial request into a Git-tracked spec pack, maintaining traceability during execution, and updating specs before code when requirements or architecture change.
Use when turning a non-trivial request into a Git-tracked spec pack, maintaining traceability during execution, and updating specs before code when requirements or architecture change.
Use when building Spring Boot 3.4+ applications with Java records, virtual threads, Spring Security 6, Spring Data JPA, reactive WebFlux patterns, and production-grade testing strategies.
Use when building or refactoring Python data layers with SQLAlchemy 2.0+ declarative models, async sessions, Alembic migrations, relationship loading strategies, and ORM testing patterns.
Use when building or refactoring Python data layers with SQLAlchemy 2.0+ declarative models, async sessions, Alembic migrations, relationship loading strategies, and ORM testing patterns.
Use when building or refactoring Python data layers with SQLAlchemy 2.0+ declarative models, async sessions, Alembic migrations, relationship loading strategies, and ORM testing patterns.
Compatibility wrapper for explicit `stitch` requests.
Compatibility wrapper for explicit `stitch` requests.
Orchestrate safe, design-first Google Stitch generation and editing by sequencing frontend-design, canonical design-system sync, prompt enhancement, Stitch MCP tool selection, and implementation handoff.
Create or refresh a Stitch-compatible design-system context by maintaining docs/foundation/DESIGN.md as the canonical source and mirroring it to a Stitch-facing design file when Stitch flows need persistent visual consistency.
Convert final Stitch screen artifacts into minimal, repo-native frontend changes by reusing local components, preserving validated logic, and documenting any intentional drift from the design source.
Convert final Stitch screen artifacts into minimal, repo-native frontend changes by reusing local components, preserving validated logic, and documenting any intentional drift from the design source.
Transform rough UI intent into compact, Stitch-ready prompts that encode visual direction, component structure, design-system context, and constrained change scope.
Transform rough UI intent into compact, Stitch-ready prompts that encode visual direction, component structure, design-system context, and constrained change scope.
Transform rough UI intent into compact, Stitch-ready prompts that encode visual direction, component structure, design-system context, and constrained change scope.
Use when building web applications with Svelte 5 and SvelteKit. Invoke for rune-based reactivity ($state, $derived, $effect), file-based routing, form actions, server-side rendering, load functions, and deployment.
Use when writing, reviewing, or refactoring modern Swift, including strict concurrency, actors, SwiftUI with @Observable, structured concurrency, protocol-oriented design, and SPM modules.
Use when writing, reviewing, or refactoring modern Swift, including strict concurrency, actors, SwiftUI with @Observable, structured concurrency, protocol-oriented design, and SPM modules.
Use when writing, reviewing, or refactoring modern Swift, including strict concurrency, actors, SwiftUI with @Observable, structured concurrency, protocol-oriented design, and SPM modules.
Systematic debugging methodology covering root cause analysis, bisection, logging strategies, debugger workflows, and post-mortem documentation. Use when diagnosing complex or elusive bugs.
Use when writing technical documentation including API references, operational runbooks, onboarding guides, decision logs, and changelog standards.
Use when writing technical documentation including API references, operational runbooks, onboarding guides, decision logs, and changelog standards.
Add or harden verification so the target behavior is covered by repeatable tests and focused checks.
Add or harden verification so the target behavior is covered by repeatable tests and focused checks.
Use when writing production TypeScript 5.9+ code: strict configuration, advanced type-level programming, discriminated unions, branded types, and patterns that prepare codebases for TS 6/7 evolution.
Unit testing best practices covering test design, mocking strategies, coverage analysis, TDD workflow, and assertion patterns. Use when writing, reviewing, or improving unit tests.
Unit testing best practices covering test design, mocking strategies, coverage analysis, TDD workflow, and assertion patterns. Use when writing, reviewing, or improving unit tests.
Unit testing best practices covering test design, mocking strategies, coverage analysis, TDD workflow, and assertion patterns. Use when writing, reviewing, or improving unit tests.
Use when running browser QA in a real web session with Playwright MCP, deterministic navigation, screenshots, console evidence, network evidence, accessibility snapshots, or failure reproduction.
Design browser-first interfaces with strong visual direction, component architecture, responsive layout strategy, accessibility, and implementation-aware handoff for real web products.
Design browser-first interfaces with strong visual direction, component architecture, responsive layout strategy, accessibility, and implementation-aware handoff for real web products.
Design browser-first interfaces with strong visual direction, component architecture, responsive layout strategy, accessibility, and implementation-aware handoff for real web products.
Compatibility wrapper for explicit `stitch` requests.
Execute a scoped change end-to-end, using the smallest set of skills and checks required to finish correctly.
Use when writing production Rust (2024 edition): ownership and borrowing patterns, async with tokio, error handling with thiserror/anyhow, comprehensive testing, and disciplined use of unsafe.
Capture or refresh the project's canonical design context in `docs/foundation/DESIGN.md` so downstream design, implementation, and QA skills stop relying on vague taste or one-off prompts.
Use when implementing observability and monitoring: OpenTelemetry instrumentation, structured logging, metrics design, distributed tracing, alerting strategies, SLO/SLI definitions, dashboards, and incident response runbooks.
Design desktop-first interfaces with multi-pane structure, keyboard-first productivity, high-information-density clarity, and implementation-aware handoff for desktop-grade app surfaces.
Use when building Spring Boot 3.4+ applications with Java records, virtual threads, Spring Security 6, Spring Data JPA, reactive WebFlux patterns, and production-grade testing strategies.
System design and architecture guidance covering distributed systems, scalability, reliability, CAP theorem, load balancing, and caching strategies for production infrastructure.
Use when building MCP servers with spec-compliant tools, structured outputs, resource providers, transport configuration, and server testing.
Transform rough UI intent into compact, Stitch-ready prompts that encode visual direction, component structure, design-system context, and constrained change scope.
System design and architecture guidance covering distributed systems, scalability, reliability, CAP theorem, load balancing, and caching strategies for production infrastructure.
Use when designing system prompts, crafting few-shot examples, implementing chain-of-thought reasoning, extracting structured output from LLMs, or building tool-use patterns for agent systems.
Consolidated QA capability with three modes: harness, web, and mobile.
Consolidated QA capability with three modes: harness, web, and mobile.
Use when building Spring Boot 3.4+ applications with Java records, virtual threads, Spring Security 6, Spring Data JPA, reactive WebFlux patterns, and production-grade testing strategies.
Use when writing production TypeScript 5.9+ code: strict configuration, advanced type-level programming, discriminated unions, branded types, and patterns that prepare codebases for TS 6/7 evolution.
Use when writing production Rust (2024 edition): ownership and borrowing patterns, async with tokio, error handling with thiserror/anyhow, comprehensive testing, and disciplined use of unsafe.
Create or refresh a Stitch-compatible design-system context by maintaining docs/foundation/DESIGN.md as the canonical source and mirroring it to a Stitch-facing design file when Stitch flows need persistent visual consistency.
Capture or refresh the project's canonical design context in `docs/foundation/DESIGN.md` so downstream design, implementation, and QA skills stop relying on vague taste or one-off prompts.
System design and architecture guidance covering distributed systems, scalability, reliability, CAP theorem, load balancing, and caching strategies for production infrastructure.
Design mobile-first interfaces with strong small-screen hierarchy, thumb-reachable interaction design, native-feeling flow structure, and implementation-aware handoff for Flutter or other app surfaces.
Turn canonical design state plus overlays into a compact, high-signal screen brief for Stitch, frontend implementation, or Flutter/mobile work.
API design best practices covering REST, GraphQL, gRPC patterns, versioning strategies, pagination, error contracts, and OpenAPI specifications for robust service interfaces.
Adapt the design engine to mobile and Flutter surfaces using Foundry's normalized mobile-pattern dataset and implementation-first constraints.
Systematic debugging methodology covering root cause analysis, bisection, logging strategies, debugger workflows, and post-mortem documentation. Use when diagnosing complex or elusive bugs.
Use when creating architecture documentation including C4 model diagrams, Architecture Decision Records, system context views, deployment diagrams, and quality attribute specifications.
Use when building web applications with Svelte 5 and SvelteKit. Invoke for rune-based reactivity ($state, $derived, $effect), file-based routing, form actions, server-side rendering, load functions, and deployment.
Use when writing technical documentation including API references, operational runbooks, onboarding guides, decision logs, and changelog standards.
Use when designing system prompts, crafting few-shot examples, implementing chain-of-thought reasoning, extracting structured output from LLMs, or building tool-use patterns for agent systems.
Use when building user interfaces with React 19+. Invoke for Server Components, the use() hook, Suspense, Actions, concurrent features, ref callbacks, and component architecture.
Canonical dual-path skill for Android emulator testing, mobile-mcp guidance, adb control, UI-tree verification, and evidence capture.