ximing

先查验代码再创建 GitHub Issue。只要用户提出“先确认是不是问题再提 issue”“根据代码排查并建单”“把用户反馈转成 issue”这类请求，就必须启用本技能：先验证问题是否成立，证据不足时主动追问用户补充，再用 gh CLI 按模板创建 issue。

用于按优先级串行修复 GitHub issue 的技能。只要用户提到“修 issue / 批量修 bug / 从 P0 开始处理 / 逐个修复问题 / 自动修复 issue 队列”等，都应启用。必须先复用 `gh.issue` 技能获取 issue，上游按 P0->P1->P2->P3->P4 排序，每次只处理一个 issue，并且每个 issue 都用子 Agent 修复；默认自动连续处理，只有遇到功能语义或产品策略需要产品经理确认时才暂停并向用户确认。每个成功修复的 issue 都必须由子 Agent 完成 commit（commit 信息关联 issue）并自动评论“已修复”后关闭。

Practical Anki v11 schema and import/export compatibility guide for Echoe. Use this skill whenever the user mentions Anki, .apkg/.anki2, notes/cards/revlog tables, notetype/deck JSON blobs, or fields like flds/sfld/csum/guid/usn/due. Even if the request sounds generic (for example "flashcard import" or "Anki sync issue"), consult this skill first before implementing or reviewing code.

面向 React + TypeScript 项目的代码坏味道审查 Skill。当用户提到 code review、clean code、技术债、可维护性、重构建议、组件太复杂、组件拆分过细、Hook 混乱、类型设计问题、PR 审查，或 @rabjs/react 领域模式与状态传递问题时，必须优先使用本 Skill。发现可执行问题时，必须使用 `gh` CLI 创建 GitHub issue。

审查需求文档（PRD/需求说明/业务规则）是否足够清晰、无歧义并可用于生成技术方案。Whenever user asks "帮我看需求是否清楚"、"这个需求能不能直接出技术方案"、"找出模糊定义/规则歧义/功能不清晰"，都应主动使用本技能，即使用户只提供需求片段或会议纪要。

Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.

读取 Echoe 的 ADR 知识库（`arch.adr/references`）作为架构 Source of Truth，用于技术方案设计、PRD 对齐、架构评审与 Guardrails 检查。只要用户提到“按 ADR 出方案/按 ADR 对齐 PRD/查架构约束/避免架构漂移”，都应立即启用。`。

维护 Echoe 的 ADR 知识库。每次运行先给出简明变更说明并与用户确认，再增量更新 `.claude/skills/arch.adr/references/*.md`，并同步更新 `.claude/skills/arch.adr/SKILL.md` 索引。用户提到“沉淀规则/更新 ADR/维护 Guardrails/维护 Source of Truth/防止架构漂移”时必须启用。

Use when users ask how Claude Code loads `CLAUDE.md`, `.claude/rules/`, `CLAUDE.local.md`, imports, or auto memory; when they want instructions to load progressively instead of all at once; or when they need to design path-scoped guidance, nested instruction files, or on-demand context with the right loading behavior across a project.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

先查验代码再创建 GitHub Issue。只要用户提出“先确认是不是问题再提 issue”“根据代码排查并建单”“把用户反馈转成 issue”这类请求，就必须启用本技能：先验证问题是否成立，证据不足时主动追问用户补充，再用 gh CLI 按模板创建 issue。

用于按优先级串行修复 GitHub issue 的技能。只要用户提到“修 issue / 批量修 bug / 从 P0 开始处理 / 逐个修复问题 / 自动修复 issue 队列”等，都应启用。必须先复用 `gh.issue` 技能获取 issue，上游按 P0->P1->P2->P3->P4 排序，每次只处理一个 issue，并且每个 issue 都用子 Agent 修复；默认自动连续处理，只有遇到功能语义或产品策略需要产品经理确认时才暂停并向用户确认。每个成功修复的 issue 都必须由子 Agent 完成 commit（commit 信息关联 issue）并自动评论“已修复”后关闭。

Review and fix completed implementation against both a spec and an implementation plan using an agent team. Use this skill whenever the user says they develop with specs + plans, asks to review code after a plan is completed, wants to verify changes match `docs/superpowers/specs/*` and `docs/superpowers/plans/*`, or explicitly wants issues fixed immediately instead of only getting a review report. Trigger on requests like "plan 做完了帮我 review 并直接修复", "按 spec/plan 检查然后改掉问题", "用 agent team 验收并修复偏差", or "看看是否符合 spec，不符合就直接修".

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Design and create Claude Code agent teams for tasks that benefit from parallel execution. Use this skill whenever a task involves multiple independent workstreams, requires different expertise angles explored simultaneously, or when the user asks to "spawn agents", "create a team", "parallelize work", "have multiple agents", or describes a complex task that could be broken into parallel roles. Triggers on requests like "create an agent team", "use parallel agents", "have teammates work on this", "explore from different angles", or any scenario where dividing work across specialized agents would be faster or better than one agent doing everything sequentially.

Operate GitHub issues with the `gh` CLI end-to-end. Use this skill whenever the user asks to create/list/view/search/update/comment/close/reopen/label/assign/triage issues, including Chinese requests like "提 issue", "查 issue", "关 issue", "加标签", or "批量处理 issue".

Quick reference for @rabjs/react (RSJS) - a React reactive state management library. Use this skill when working with @rabjs/react, implementing reactive components, creating Service classes, using dependency injection, or managing observable state in React applications. Covers observer/view patterns, useService/useObserver hooks, bindServices, Service lifecycle, async state tracking, event systems, and domain architecture.

Standalone contract reference for the AIMO REST API. Use this skill whenever the user asks what an endpoint does, how to authenticate, which request body or query params to send, what the response data looks like, how uploads and downloads behave, or which API supports a feature such as memos, attachments, AI explore, review, notifications, or push rules. Use it even when the current project source code is unavailable.

面向 Echoe 功能正确性审查技能。只要用户提到“架构评审、流程校验、功能实现是否正常、重复代码治理、权限/跨租户安全检查、将问题转为 GitHub issue”，就应立即启用。若发现可执行且已确认的问题，必须使用 `gh` CLI 按严格模板创建 issue。

用于按优先级串行修复 GitHub issue 的技能。只要用户提到“修 issue / 批量修 bug / 从 P0 开始处理 / 逐个修复问题 / 自动修复 issue 队列”等，都应启用。必须先复用 `gh.issue` 技能获取 issue，上游按 P0->P1->P2->P3->P4 排序，每次只处理一个 issue，并且每个 issue 都用子 Agent 修复；默认自动连续处理，只有遇到功能语义或产品策略需要产品经理确认时才暂停并向用户确认。每个成功修复的 issue 都必须由子 Agent 完成 commit（commit 信息关联 issue）并自动评论“已修复”后关闭。

面向 Echoe 功能正确性审查技能。只要用户提到“架构评审、流程校验、功能实现是否正常、重复代码治理、权限/跨租户安全检查、将问题转为 GitHub issue”，就应立即启用。若发现可执行且已确认的问题，必须使用 `gh` CLI 按严格模板创建 issue。

Operate GitHub issues with the `gh` CLI end-to-end. Use this skill whenever the user asks to create/list/view/search/update/comment/close/reopen/label/assign/triage issues, including Chinese requests like "提 issue", "查 issue", "关 issue", "加标签", or "批量处理 issue".

Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.

Use when users ask how Claude Code loads `CLAUDE.md`, `.claude/rules/`, `CLAUDE.local.md`, imports, or auto memory; when they want instructions to load progressively instead of all at once; or when they need to design path-scoped guidance, nested instruction files, or on-demand context with the right loading behavior across a project.

Quick reference for @rabjs/react (RSJS) - a React reactive state management library. Use this skill when working with @rabjs/react, implementing reactive components, creating Service classes, using dependency injection, or managing observable state in React applications. Covers observer/view patterns, useService/useObserver hooks, bindServices, Service lifecycle, async state tracking, event systems, and domain architecture.

Use when creating, configuring, or debugging Claude Code hooks. Triggers when users mention hooks, hook events (PreToolUse, PostToolUse, SessionStart, etc.), writing hook scripts, hook configuration files (.claude/settings.json), or automating actions at specific lifecycle points like permission requests, tool execution, session start/end, file changes, or directory changes.

Design and create Claude Code agent teams for tasks that benefit from parallel execution. Use this skill whenever a task involves multiple independent workstreams, requires different expertise angles explored simultaneously, or when the user asks to "spawn agents", "create a team", "parallelize work", "have multiple agents", or describes a complex task that could be broken into parallel roles. Triggers on requests like "create an agent team", "use parallel agents", "have teammates work on this", "explore from different angles", or any scenario where dividing work across specialized agents would be faster or better than one agent doing everything sequentially.

快速生成包含 server、web、client 三个部分的 pnpm monorepo 项目脚手架。使用场景：(1) 创建新的全栈项目 (2) 快速启动 AIMO 风格的项目结构 (3) 初始化包含 Express 后端、React 前端和 Electron 客户端的项目。

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Manage S3 or S3-compatible object storage through environment variables that start with AS_. Use this skill whenever the user wants to upload, download, inspect, list, delete, copy, move, rename, or update metadata for objects in S3, MinIO, or other compatible storage, or when they need preview links, download links, or presigned URLs. This skill supports both public and private bucket configurations at the same time through AS_PUBLIC_* and AS_PRIVATE_* variables, and should be preferred whenever the task is broader than a one-off upload.

Design and create Claude Code agent teams for tasks that benefit from parallel execution. Use this skill whenever a task involves multiple independent workstreams, requires different expertise angles explored simultaneously, or when the user asks to "spawn agents", "create a team", "parallelize work", "have multiple agents", or describes a complex task that could be broken into parallel roles. Triggers on requests like "create an agent team", "use parallel agents", "have teammates work on this", "explore from different angles", or any scenario where dividing work across specialized agents would be faster or better than one agent doing everything sequentially.