Coding / 软件开发

Use when: tao service moi Document Service (boilerplate). Keywords: document service, spring boot, application.properties.

Guides building games that run in the browser. Covers picking a rendering framework (2D vs 3D), deciding between WebGPU and WebGL, working within sandbox limits like tab throttling and blocked audio, packaging assets for fast delivery, and shipping as an installable PWA. Use when designing or troub…

Automated Agent Skill for Core Layout Refactoring — WebAuthn Security Bridge. Ensures industry-best continuous operation.

Use when working with Orion project skills, especially Rust crates under orion-crates such as orion-error and orion-variate. This collection routes to nested Orion-specific skills for structured error handling, variable/config modeling, common crate workflows, and source-accurate implementation gui…

Final quality pass before shipping. Fixes alignment, spacing, consistency, and detail issues that separate good from great.

Persistent project context for AI coding agents using linked markdown plans

You are an AI assistant specialized in generating TypeScript code for Next.js 14 applications using Tailwind CSS. Your task is to analyze design screenshots and create corresponding TypeScript code that implements the design using Next.js 14 and Tailwind CSS, adhering to the latest best practices a…

Create or update framework adapters with complete metadata, mappings, templates, and generation rules.

Intelligently upscale and enhance videos to cinematic quality using a multi-model backend (Topaz, SeedVR2).

Generate production-ready React forms from a screenshot, PDF, HTML, or text description. The output is a validated FormEngine JSON schema plus a runnable App.tsx — portable data, not throwaway JSX.

Python coding conventions and best practices. Use when writing, reviewing, or refactoring Python code, or when working with Python scripts and projects.

Refactor Agent - Identify refactoring opportunities and technical debt

Test-driven development for Spring Boot using JUnit 5, Mockito, MockMvc, Testcontainers, and JaCoCo. Use when adding features, fixing bugs, or refactoring.

Use when building UIs with @vanduo-oss/framework — the zero-build "Vanilla" HTML/CSS/JS engine of the Vanduo design system (data-attribute components + an imperative window.Vanduo runtime). Covers install (CDN/ESM/IIFE), the runtime API, the --vd-* token model, security, and caveats.

Ensure that the seccomp profile is set to docker/default in your pod definitions (Manual)

Create, deploy, and manage web apps accessible at subdomains of your configured base domain

Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.

Framework-agnostic E2E testing principles, spec-driven test generation, and maintenance workflows

Create a pull request with cleanup, fmt, and test gates

Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.

Use whenever writing or reviewing Laravel PHP code (Laravel 13+). Prefer PHP attributes over class properties for models, jobs, commands, controllers, form requests, tests, factories, API resources, and container bindings. Trigger on $fillable, $table, $queue, $tries, $signature, $redirect, $errorB…

ProductionOS — dual-target AI engineering operating system for repo-wide audits, upgrade plans, code reviews, strategic product reviews, security sweeps, UX audits, and recursive quality improvement.

Implement OpenAI Harness Engineering practices in any repository — AGENTS.md, PLANS.md, deterministic smoke/test/lint harness commands, strict architecture boundaries, observability from day 1, and entropy-control audits for reliable autonomous agent runs.

Reviews user-modified code (diffs/PRs), provides best-practice recommendations, analyzes cost-effectiveness of the approach, and outputs a code score. Use when the user asks to review their changes, 审查/评审修改的代码, 代码评审, or wants 最佳实践/性价比/代码评分.

Database operations including querying, schema exploration, and data analysis. Activates for tasks involving PostgreSQL, MySQL, MariaDB, SQLite, MongoDB, Redis, Elasticsearch, or ClickHouse databases.

// QA Bug Report - .cursorrules prompt file // Specialized prompt for creating standardized QA bug reports with clear reproduction steps // and detailed environmental context for efficient bug resolution.

Run the agent-framework check MCP tool and report summarized lint/type-check/editor-diagnostic results. Use when the user invokes $agent-framework-check.

Write Pandas code to this project's standards — vectorised operations, Pandas-native types, and Pandera schemas. Use when importing or using pandas — transforming DataFrames or Series, handling missing values, or type-hinting tabular data.

Manages git worktree-based sandboxes with the wt CLI tool, both locally and on remote hosts over SSH. Use when the user wants to create, enter, run commands in, list, remove, or manage isolated worktree sandboxes, configure remote hosts, or troubleshoot wt issues.

任意の自動コンパクションではなく、タスクフェーズを通じてコンテキストを保持するための論理的な間隔での手動コンパクションを提案します。