vibecoder-guide
VibeCoder(非技術ユーザー)を自然言語開発でガイド。Use when user asks what to do next, how to use the system, needs help, or is stuck. Do NOT load for: technical-user work, direct implementation requests, or reviews.
VibeCoder(非技術ユーザー)を自然言語開発でガイド。Use when user asks what to do next, how to use the system, needs help, or is stuck. Do NOT load for: technical-user work, direct implementation requests, or reviews.
Harness v3 統合実行スキル。Plans.md タスクを1件から全並列チーム実行まで担当。以下で起動: 実装して、実行して、harness-work、全部やって、breezing、チーム実行、parallel。プランニング・レビュー・リリース・セットアップには使わない。
Harness v3 統合実行スキル(Codex ネイティブ版)。Plans.md タスクを1件から全並列チーム実行まで担当。以下で起動: 実装して、実行して、harness-work、全部やって、breezing、チーム実行、parallel。プランニング・レビュー・リリース・セットアップには使わない。
Deploy and serve web projects locally for preview. Automatically detects project type (Node.js or static HTML) and starts the appropriate development server.
跨猫传话/交接的五件套结构(What/Why/Tradeoff/Open/Next)。 Use when: 交接工作给其他猫、传话、写 review 信。 Not for: 自己的任务、不涉及其他猫的工作。 Output: 结构化交接信。
不可逆事故发生后的应急响应:情绪急救 → 止损 → 补偿性劳动 → 教训沉淀。 Use when: 犯了不可挽回的错误、造成了人类伙伴的情绪波动、需要危机处理。 Not for: 可撤销的小失误、日常 bug fix(用 debugging)、预防性确认(用 shared-rules 铁律)。 Output: 情绪修复 + 止损行动 + 教训沉淀(lessons-learned / shared-rules)。
浏览器工作流总路由:为外部网站浏览、登录态流程、浏览器自动化、证据采集选择合适后端。 Use when: 需要操作外部网站、登录页、JS 重页面、没有 webfetch/VL 但需要浏览器、或需要在多种浏览器工具之间路由。 Not for: localhost 页面预览(用 browser-preview)、本地 WebApp 确定性测试(用 webapp-testing)、简单网页抓取/搜索。 Output: 选定浏览器后端 + 执行路径 + 证据/结果。
富媒体消息发送:语音、图片、卡片、清单、代码 diff、交互选择。 Use when: 发语音、发图、发卡片、展示结构化信息、庆祝、给我听听、给我看看、让用户选、确认操作。 Not for: 纯文字聊天、技术讨论、日常回复。 Output: rich block 附着在消息上。
A hello world skill provided by the aif-ext-hello extension. Demonstrates extension-provided skills.
Execute implementation tasks from the current plan. Works through tasks sequentially, marks completion, and preserves progress for continuation across sessions. Use when user says "implement", "start coding", "execute plan", or "continue implementation".
Add project-specific rules and conventions to the configured RULES.md artifact. Each invocation appends new rules. These rules are automatically loaded by /aif-implement before execution. Use when user says "add rule", "remember this", "convention", or "always do X".
Audit and improve SwiftUI runtime performance through code review and Instruments guidance. Use for diagnosing slow rendering, janky scrolling, excessive view updates, or layout thrash in SwiftUI apps.
Context-aware routing to the Anytype iOS design system including icons, typography, colors, and spacing. Use when working with Figma-to-code translation, design assets, or UI components.
Expert guidance on Swift concurrency using the Office Building mental model. Use when working with actors, isolation, Sendable, TaskGroups, or fixing concurrency warnings and data race issues.
Context-aware routing to iOS 26 Liquid Glass implementation patterns. Use when working with glass effects, GlassEffectContainer, morphing transitions, or iOS 26 visual effects.
SwiftUI view structure, composition, and best practices. Use when refactoring SwiftUI views, organizing view files, or extracting subviews.
Context-aware routing to the Anytype iOS localization system. Use when working with .xcstrings files, Loc constants, hardcoded strings, or user-facing text.
Context-aware routing to the Anytype iOS analytics system. Use when adding analytics events, tracking user routes, or working with AnytypeAnalytics and AnalyticsConstants.
Build reproducible scientific documents, presentations, and websites with Quarto supporting R, Python, Julia, and Observable JS. Use when creating reproducible reports with Quarto.
Build reproducible bioinformatics pipelines with Snakemake using rules, wildcards, and automatic dependency resolution. Use when creating Python-based workflows, automating multi-step analyses with make-like dependency tracking, or running pipelines on HPC clusters with SLURM.
Apply type-safe bounds checking patterns using Index/Length types instead of usize. Use when working with arrays, buffers, cursors, viewports, or any code that handles indices and lengths.
Core design principles for the codebase - cognitive load, progressive disclosure, type safety, abstraction worth. Use when designing APIs, modules, or data structures.