GoogleCloudPlatform/devrel-demos

circuit-breaker-reporter

Orchestrates parallel worker subagents with real-time telemetry reporting and automated hard circuit-breaking via manage_subagents upon fatal worker errors.

Langue du texte source : anglais

multi-step-workflow-reporter

Orchestrates parallel worker subagents executing a 4-step workflow, streaming mid-flight milestone progress reports back to the parent orchestrator via send_message. Use when running multi-step pipeline tasks with live progress reporting.

Langue du texte source : anglais

batch-executing-test-suites

Orchestrates parallel test suite execution across isolated workspace branches by registering a custom test_suite_runner subagent via define_subagent and dispatching parallel workers via invoke_subagent. Use when batch executing test suites and analyzing test…

Langue du texte source : anglais

generating-mock-images

Generates mock flower and plant images for an e-commerce website, presenting them for user review. Use when generating mock product images for flower and plant stores or managing generated mock image assets.

Langue du texte source : anglais

making-forms-demo

Interviews the user for critical implementation details needed to generate a Web Form. Manages FORM namespace in `user_prefs.json`. Use when making Web Forms.

Langue du texte source : anglais

knowledge-catalog-governance

Enforces data governance by verifying Knowledge Catalog Aspects before recommending BigQuery tables.

Langue du texte source : anglais

adding-easter-egg

Ensures the game has a fun easter egg that turns the screen black and white, sepia or gameboy monotone colours. Use when creating or modifying a game.

Langue du texte source : anglais

building-platformer-games

Ensures platformer games have polished movement, responsive controls, and balanced jump mechanics. Use ONLY when the game type is "platformer".

Langue du texte source : anglais

creating-a-game

Guides the creation of a new game and is the high-level orchestrator skill that MUST be invoked first. Use when tasked with creating a new game.

Langue du texte source : anglais

ensuring-arcade-visuals

Arcade game must have a retro asthetic. Use when creating or modifying a game to ensure that the game looks retro and maintains a consistent look and feel with all games.

Langue du texte source : anglais

handling-user-input

Game will always use the same control scheme/buttons and mapping of the gamepad and keyboard. Use when creating or modifying a game.

Langue du texte source : anglais

helping-the-user

Helps the user make or modify a game. Use when the user wants to create a new game or modify an existing one.

Langue du texte source : anglais

improving-game-quality

Ensures games created have a good quality user experience and follow best practices. Use when creating or modifying a game.

Langue du texte source : anglais

messaging-game-over

Ensures games created have a lose condition and send a message to the parent iframe in a standardized manner. Use when creating or modifying a game.

Langue du texte source : anglais

playing-the-game

Starts the local Vite server for the game and loads the game into a Chrome browser so the user can play it. Use when the user wants to test changes or play the game.

Langue du texte source : anglais

banana-bread

Focuses on on-demand recipe and detailed instructions for baking a perfect banana bread, including ingredient ratios, step-by-step baking workflow, and kitchen tools.

Langue du texte source : anglais

cheese-bread

Focuses on on-demand recipe and detailed instructions for baking delicious cheese bread (Pão de Queijo style or similar), detailing ingredient ratios, baking temperature, and step-by-step techniques.

Langue du texte source : anglais

drawings

Ultra-conservative preservation and restoration of sketches and line art.

Langue du texte source : anglais

paintings

Restoration protocol for fine art paintings.

Langue du texte source : anglais

photography

Ultra-conservative preservation and restoration of historical and modern photographs.

Langue du texte source : anglais

ping-pong-pairing

Enforces a strict, turn-based TDD ping-pong cycle by defining and orchestrating two specialized subagents (Player One and Player Two).

Langue du texte source : anglais

auditing-parity

Compares a modernized Next.js application against its legacy Express counterpart using runtime side-by-side verification. Use when ensuring functional and business logic parity between two systems.

Langue du texte source : anglais

orchestrating-greenfield-migration

Manages the end-to-end modernization of legacy Express monoliths into Next.js architectures. Orchestrates subagents for auditing, scaffolding, and verification. Use when starting or managing a greenfield rewrite project.

Langue du texte source : anglais

adversarial-verification

Systematically probe a modernized Next.js application for logic flaws, security vulnerabilities, or missing features. Use this to find bugs or cases where the migration failed to match legacy behavior.

Langue du texte source : anglais

auditing-api-contracts

Analyzes Express route definitions and controller logic to document API endpoints, payloads, and response structures. Use when reverse-engineering an existing Express application's API surface.

Langue du texte source : anglais

auditing-business-logic

Analyzes authentication flows, authorization rules, middleware logic, and side-effects. Use when extracting business rules, Passport configurations, or mailer logic from an Express application.

Langue du texte source : anglais

auditing-data-models

Analyzes legacy ORM models (Mongoose, Sequelize) to extract schemas, validations, and relationships. Use when reverse-engineering a legacy data layer for a modern rewrite.

Langue du texte source : anglais

auditing-ui-archeology

Analyzes legacy UI templates (Pug, EJS, HTML) to extract a comprehensive inventory of components, layouts, and conditional logic. Use when reverse-engineering a legacy frontend for a modern rewrite.

Langue du texte source : anglais

generating-api-tests

Reads API_Contracts.md and generates failing Vitest integration tests for the expected Next.js Route Handlers. Use when generating API tests for TDD.

Langue du texte source : anglais

generating-database-seeder

Generates and executes a database seeder script to populate MongoDB with sample data based on modern Zod schemas. Use this to prepare an environment for functional parity testing.

Langue du texte source : anglais

scaffolding-api-routes

Reads API_Contracts.md artifacts and rebuilds the legacy Express routes as modern Next.js Route Handlers or Server Actions. Use when following a legacy audit artifact to scaffold out a new Express API routes.

Langue du texte source : anglais

scaffolding-data-layer

Reads Data_Models.md artifacts and generates the equivalent modern ORM schema or native MongoDB/Zod layer. Use when following a legacy audit artifact to scaffold out the data access layer for a Next.js app.

Langue du texte source : anglais

scaffolding-nextjs-foundation

Generates a new Next.js application with Tailwind, TypeScript, and modern dependencies based on audit specifications. Use when beginning the scaffolding phase of a greenfield codebase rewrite.

Langue du texte source : anglais

scaffolding-test-foundation

Installs and configures Vitest for a modern Next.js Application. Use this for setting up the environment to run Vitest.

Langue du texte source : anglais

scaffolding-ui-and-pages

Translates a UI_Component_Inventory.md artifact into modern ShadCN + Tailwind components AND fully scaffolded Next.js pages. Use when building the frontend design system and routing infrastructure.

Langue du texte source : anglais

gcp-agent-eval-engine-runner

Boilerplate for a production evaluation runner that performs parallel inference, captures reasoning traces via SSE, and integrates with the Vertex AI Gen AI Evaluation service.

Langue du texte source : anglais

gcp-agent-eval-metric-configurator

Provides templates for configuring Vertex AI Gen AI Evaluation metrics like GROUNDING, TOOL_USE_QUALITY, and ResponseMatch for specific agent domains.

Langue du texte source : anglais

gcp-agent-shadow-deployer

Implements the "Dark Canary" pattern for Cloud Run, allowing agents to be evaluated in production without serving user traffic.

Langue du texte source : anglais

gcp-agent-tool-trajectory-evaluator

Provides custom Python metrics for configuring Vertex AI Gen AI Evaluation to measure Trajectory Precision, Recall, and Order Match.

Langue du texte source : anglais

adk-memory-bank-initializer

Helps developers implement the long-term memory layer by providing the boilerplate code for the VertexAiMemoryBankService and the save_session_to_memory_callback.

Langue du texte source : anglais