测试与 QA
测试、调试、验证和质量工作流
Skills 列表
amazon-product-photography
Plan shoot-ready Amazon product photography, listing image sets, infographics, lifestyle scenes, and production briefs. Use when a seller asks for an Amazon photo shot list, creative direction, image-pack plan, photography budget, DIY-versus-done-for-you decision, or handoff to a photographer or image-generation workflow. Do not use for listing copy or image-only performance auditing.
nexscope-ai
optimize-web
Optimizes Unity 6 WebGL and WebGPU builds for smaller download size, faster initial load, and efficient browser runtime performance. Use when the user's web build is too large, stutters in a specific browser, consumes excessive battery, needs CDN/server compression configured, or needs guidance on resource stripping, shader variant reduction, KTX textures, quality settings, or web profiling.
unity-technologiesvalidate-urp-render-graph-renderer-feature
Use when the user wants to review or validate a Unity 6+ URP ScriptableRendererFeature that uses the Render Graph API. Checks for correctness issues - resource wiring, material binding, execution structure, descriptor usage, global resource exposure, and Render Graph best practices.
unity-technologieslocalization
Sets up and configures Unity Localization, including locales, String/Asset Tables, CJK font support, and Addressables workflows. Use when the user wants to add languages to a project, translate UI text, support Asian (CJK) languages with TMP fonts, or mentions i18n, l10n, multilingual support, or making a game support multiple languages.
unity-technologiesurp-postprocessing
Sets up, configures, and debugs URP post-processing effects using the Volume framework. Use when the user asks about bloom, tonemapping, color adjustments, depth of field, vignette, motion blur, or other Volume overrides in a URP project.
unity-technologieslevelplay-unity-integration
Adds ads and monetization to a Unity game using the LevelPlay Mediation SDK (installed via the Ads Mediation UPM package). Use when a developer asks about adding ads to a Unity game, implementing rewarded, interstitial, or banner ads, setting up ad mediation, configuring ad networks, installing or updating the Ads Mediation package, troubleshooting LevelPlay namespace errors, resolving Android gradle or iOS CocoaPods dependency issues for ads, configuring ATT or privacy settings for ad compliance, tracking impression-level revenue (ILRD), initializing the LevelPlay SDK, or setting up ad unit IDs. Also use when a developer wants to monetize their Unity game with ads, asks how to get started with LevelPlay, ads, or mediation, or needs help with any part of the LevelPlay integration workflow including platform-specific setup for iOS or Android. Also use when upgrading the LevelPlay or IronSource SDK version, migrating from deprecated IronSource.Agent APIs, or migrating a game from Unity Ads to LevelPlay.
unity-technologies
brand-naming
Full brand naming workflow for founders, agencies, and businesses. Use this skill whenever the user says "help me name this brand", "brand naming", "I need a name for", "name ideas for", "what should I call my brand/company/product", "naming a startup", "brand name suggestions", "help with naming", or shares a brand brief and asks for name options. Also triggers when the user shares existing name options and asks for feedback, evaluation, ranking, or scoring of those names. Auto-detects whether to run the full generation workflow or the evaluation workflow based on what the user provides. Always use this skill for any brand or product naming task — even if the user just casually mentions needing a name.
arnabbagxd
angular-testing
使用 Vitest 或 Jasmine 配合 TestBed 和现代测试模式，为 Angular v20+ 应用编写单元测试和集成测试。适用于测试信号组件、OnPush 变更检测、使用 inject() 的服务以及 HTTP 交互。在创建测试、测试基于信号的组件、模拟依赖或设置测试基础设施时触发。不适用于使用 Cypress 或 Playwright 的端到端测试，也不适用于测试非 Angular 的 JavaScript/TypeScript 代码。
analogjsangular-tooling
在 Angular v20+ 项目中有效使用 Angular CLI 和开发工具。用于项目设置、代码生成、构建、测试和配置。触发条件包括创建新项目、生成组件/服务/模块、配置构建、运行测试或优化生产构建。不适用于 Nx 工作区命令、自定义 Webpack 配置或非 Angular CLI 构建系统（如独立 Vite 或直接使用 esbuild）。
analogjs
solid
在编写代码、实现功能、重构、规划架构、设计系统、审查代码或调试时使用此技能。该技能通过SOLID原则、TDD、整洁代码实践和专业软件设计，将初级水平的代码转变为高级工程师质量的软件。
ramziddin
solana-dev
当用户要求“构建 Solana dApp”、“编写 Anchor 程序”、“创建代币”、“调试 Solana 错误”、“设置钱包连接”、“测试 Solana 程序”、“部署到 devnet”或“解释 Solana 概念”（如租金、账户、PDA、CPI 等）时使用。也可用于通过公共 RPC + curl 快速查询链上信息——例如“<钱包>的余额是多少”、“查询交易 <sig>”、“<账户>的代币余额”、“在主网/devnet 上检查此地址”。端到端的 Solana 开发手册，涵盖钱包连接、Anchor/Pinocchio 程序、Codama 客户端生成、Surfpool/LiteSVM/Mollusk 测试、安全清单以及针对公共集群的 JSON-RPC curl 查询。优先使用 @solana/kit v7 插件客户端（createClient + .use()）、通过 @solana/kit-plugin-wallet + @solana/react 进行钱包连接、将 web3.js v3（Kit 内部、RC）作为旧代码库的迁移目标，以及使用 Surfpool 进行本地网络和集成测试。
solana-foundation
write-pr-description
Writes the body of a pull request - the summary, the repository template sections, and reviewer guidance such as a recommended reading order and focus areas. Use whenever drafting or revising a PR description, filling in a repository's PR template, refreshing a description that no longer matches the branch, or preparing a branch for review. Use it even when the user only says "open a PR", "put this up for review", or "write this up" without naming the description.
warpdotdev
swift-concurrency-pro
审查 Swift 并发代码的正确性、现代 API 使用情况以及常见的 async/await 陷阱。在阅读、编写或审查 Swift 并发代码时使用。
twostraws
using-n8n-skills-official
Use when working with n8n workflows in any capacity. The always-on protocol for the n8n-skills plugin, loaded by the SessionStart hook every session. Routes to the right skill, summarizes every n8n MCP tool (closing the deferred-description gap), and lists the cross-cutting rules.
n8n-ion8n-code-nodes-official
Use when the user reaches for a Code node, mentions writing JavaScript or Python in n8n, or any custom logic comes up in workflow design. Triggers on "Code node", "Code", "JavaScript", "Python", "custom logic", "transform data", "$input", "$json transformation", "loop in code", "write a function", or any time the obvious answer seems to be "just put it in code."
n8n-ion8n-workflow-lifecycle-official
Use when starting, designing, organizing, finishing, or shipping an n8n workflow. Covers visual layout (sticky notes), descriptions that capture the *why*, node names, validation, testing, folders/projects, and publishing. Triggers on create_workflow_from_code, update_workflow, validate_workflow, publish_workflow, archive_workflow, "design", "lay out", "organize", "structure", "sticky", "describe this workflow", "ship", "deploy", "publish", "name this workflow", or any folder/project organization request.
n8n-io
tend
Tend the Allium garden. Use when the user wants to write, edit, update, add to, improve, clarify, refine, restructure, fix or migrate Allium specs. Covers adding entities, rules, triggers, surfaces and contracts, fixing syntax or validation errors, renaming or refactoring within specs, migrating specs to a new language version, and translating requirements into well-formed specifications. Pushes back on vague requirements.
juxt
testing-dags
Complex DAG testing workflows with debugging and fixing cycles. Use for multi-step testing requests like "test this dag and fix it if it fails", "test and debug", "run the pipeline and troubleshoot issues". For simple test requests ("test dag", "run dag"), the airflow entrypoint skill handles it directly. This skill is for iterative test-debug-fix cycles.
astronomer
spice-sim
Add or run an ngspice-backed Zener testbench with `pcb sim`.
diodeincauthoring-dags
Workflow and best practices for writing Apache Airflow DAGs. Use when creating a new DAG, write pipeline code, handling questions about DAG patterns and conventions or extending an existing DAG with a follow-up/downstream task. ANY request shaped like 'add a DAG named X', 'write a pipeline', 'add a task that runs after Y', or 'extend the DAG'. For testing and debugging DAGs, see the testing-dags skill.
astronomerallium
给你的AI代理比提示更有用的东西。通过清晰性实现速度。
juxt
test
Generate tests and coverage plans. Triggers: "test", "generate tests and coverage plans.", "test skill".
boshu2converter
Convert AgentOps skill formats. Triggers: "converter", "convert agentops skill formats.", "converter skill".
boshu2
swift-testing-expert
Swift Testing 专家指导：测试结构、#expect/#require 宏、特质和标签、参数化测试、测试计划、并行执行、异步等待模式以及 XCTest 迁移。在编写新的 Swift 测试、现代化 XCTest 套件、调试不稳定测试或提高 Apple 平台或 Swift 服务器项目的测试质量和可维护性时使用。
avdlee