所有 Skills
找到 8442 个 Skills
Skills 列表
do-and-judge
Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop
neolabhqtree-of-thoughts
Execute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-judge evaluation specifications and multi-agent evaluation
neolabhqtest-prompt
Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies RED-GREEN-REFACTOR cycle to prompt engineering using subagents for isolated testing
neolabhqreview-pr
Review an existing GitHub pull request and post inline review comments on its diff. Use when the changes are on an opened PR rather than your local working tree.
neolabhqcreate-rule
Use when found gap or repetative issue, that produced by you or implemenataion agent. Esentially use it each time when you say "You absolutly right, I should have done it differently." -> need create rule for this issue so it not appears again.
neolabhqcreate-ideas
Generate ideas in one shot using creative sampling
neolabhqtest-skill
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes
neolabhqcommit
Create well-formatted commits with conventional commit messages and emoji
neolabhq
keyword-research
当用户想要发现、评估或优先处理App Store关键词时使用。也适用于用户提及“关键词研究”、“查找关键词”、“搜索量”、“关键词难度”、“关键词创意”或“我应该定位哪些关键词”。如需将关键词实施到元数据中，请参见metadata-optimization。如需审计当前关键词表现，请参见aso-audit。
eronreddo-in-parallel
Run independent tasks concurrently across multiple files or targets using parallel sub-agents, with per-task model selection and LLM-as-a-judge verification. Use when tasks do not depend on each other and can run side by side.
neolabhqagent-evaluation
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.
neolabhqwrite-tests
Add missing test coverage for your local code changes by generating new test files (covers uncommitted and untracked changes, or the latest commit if everything is committed). Use when you want write tests for new logic or increase test coverage.
neolabhqadd-task
creates draft task file in .specs/tasks/draft/ with original user intent
neolabhqwhy
Iterative Five Whys root cause analysis drilling from symptoms to fundamentals
neolabhqmonetization-strategy
当用户想要设计或优化其应用的变现策略——定价、付费墙、订阅或应用内购买时使用。当用户提到“定价”、“付费墙”、“订阅”、“IAP”、“如何变现”、“收入优化”、“免费试用”或“转化为付费”时也使用。关于留存影响，请参见retention-optimization。关于竞争定价，请参见competitor-analysis。
eronred
unlazy
Enforces completion discipline for substantial autonomous work by writing acceptance gates before execution, decomposing work with the Depth Tree, running approved checks, and re-verifying evidence before reporting. Use when Codex faces a long or multi-part task, work that has returned half-done, an exhaustive audit or build, parallel leaves or pipelines, or explicit triggers such as /unlazy, $unlazy, "tree N", "gates", and "do not stop until it is done".
leonxlnximplement-task
Implement a task step by step with automated LLM-as-Judge verification at the end of each phase
neolabhqreview-local-changes
Review your local uncommitted working-tree changes (git diff plus untracked files) and return actionable improvement suggestions. Use before committing, when nothing has been pushed yet.
neolabhqdo-in-steps
Execute one complex task as ordered, dependent steps run sequentially, passing context from each step to the next, with per-step LLM-as-a-judge verification. Use when later steps depend on the results of earlier ones.
neolabhq
bklit-ui
Bklit UI charts and data visualization for any project using the @bklit shadcn registry. Install, compose, theme, and animate charts correctly. Triggers when working with @bklitui/ui/charts, @bklit components, data visualization, dashboards, or chart theming. Also invoke manually for chart tasks.
bklit
ios-hig-design
遵循 Apple 人机界面指南（Human Interface Guidelines）设计原生 iOS 界面。当用户提到“iPhone 应用”、“iPad 布局”、“SwiftUI”、“UIKit”、“灵动岛”、“安全区域”、“符合 HIG 规范”、“SF Symbols”、“触觉反馈”、“iOS 无障碍”、“让我的 App 更有原生感”或“遵循苹果设计指南”时使用。当构建 iOS 的标签栏（tab bar）、导航栈（navigation stack）、半屏页（sheet）或模态框（modal），实现深色模式，或进行跨屏幕尺寸布局适配时也会触发。覆盖导航模式、无障碍支持、SF Symbols 和平台设计规范。通用 UI 精细化打磨请参考 refactoring-ui；示能/意向设计（affordance design）请参考 design-everyday-things。
wondelaitop-design
打造Awwwards级别获奖级沉浸式网页体验。当用户提及“Awwwards品质”、“让我的网站惊艳”、“滚动动画”、“视差叙事”、“电影级网页设计”、“作品集网站”或“品牌体验”时使用。也可用于将标准落地页提升为令人难忘的数字体验。涵盖戏剧性排版、有目的性的动效、基于滚动的构图以及性能优化的动画。基础UI请参考refactoring-ui，字体选择请参考web-typography。
wondelaijobs-to-be-done
通过分析客户“雇佣”你的产品要完成的“任务”，发现客户的真实需求。当用户提到“客户发现”、“客户为何流失”、“这个产品解决了什么任务”、“与运气竞争”、“产品市场契合度”、“转换行为”、“奶昔时刻”或“功能性与情感性任务”时使用。也适用于调查用户为何选择竞争对手、围绕真实客户需求设计功能、或重新定义价值主张。涵盖JTBD访谈、竞争分析和以任务为导向的路线图。如需产品定位，请参考obviously-awesome。如需快速验证，请参考design-sprint。如需非引导式访谈技巧，请参考mom-test。
wondelaidomain-driven-design
使用限界上下文、聚合和通用语言围绕业务领域建模软件。当用户提到“领域建模”、“限界上下文”、“聚合根”、“通用语言”、“防腐层”、“上下文映射”、“领域事件”、“战略设计”、“代码与业务不匹配”或“如何拆分这个大系统”时使用。在将单体拆分为服务、定义服务边界或使代码结构与业务流程对齐时也触发。涵盖实体与值对象、领域事件和上下文映射策略。有关架构层，请参见clean-architecture。有关复杂性，请参见software-design-philosophy。
wondelai