其他技能

Add or define specific fields in a collection's readSchema. Use when fields are missing from materialization field selection, pruned by complexity limit, need type refinement, need to be protected from future inference changes, or need to be required for downstream consumers. Use when user says "missing fields", "pruned fields", "field not showing up", "complexity limit", "define field in read schema", "restrict field type", or "protect field from inference".

中文简介正在准备中。当前显示原文说明。

Create an Estuary derivation that maintains a sliding time window of events (e.g. "transfers in the last 24h", "failed logins in the last 5 minutes") using internal SQLite state and readDelay for time-based expiration. Derivations add complexity and cost — confirm the user wants a derivation before reaching for this. Use when user says "windowing derivation", "derivation for last-24h events", "rolling-window derivation", "sliding-window transformation", "fraud-detection derivation", "rate-limit derivation", or "time-window derivation".

中文简介正在准备中。当前显示原文说明。

スプリントレトロスペクティブを実行する。KPT整理→改善アクション→CLAUDE.md/rules/agentsへの自動フィードバックで組織を進化させる

中文简介正在准备中。当前显示原文说明。

在授权渗透测试中挖掘 Web 缓存投毒与缓存欺骗（web cache poisoning / cache deception）。当目标前有缓存层（CDN/反代/Varnish）且缓存键未覆盖某些影响响应的输入（unkeyed header/参数/解析差异）时使用——典型场景：X-Forwarded-Host 反射进响应被缓存、unkeyed 参数、缓存键规范化差异、静态扩展名欺骗缓存私有页。适用目标类型 Web / CDN。触发场景包括用户说"测下缓存投毒""X-Forwarded-Host 能不能毒缓存""缓存欺骗看一下""unkeyed 输入有没有"。输出：投毒/欺骗可行性 + 被缓存证据的 finding（含 killed 记录）。

中文简介正在准备中。当前显示原文说明。

渗透测试的攻击面识别与研判总线：拿到一个目标或功能点时，先用它判断"这里可能是哪类漏洞、该用哪个 hunt skill"，并覆盖没有专用 hunt skill 的横切类别——跨组件攻击链、业务逻辑漏洞、安全配置错误、信息泄露。当用户说"从哪下手""这个功能可能有什么问题""帮我看看攻击面""该测哪类漏洞""怎么把几个小问题串成大的"时使用；也在每次渗透开局做侦察分诊时使用。输出：识别出的可疑信号 + 路由到的 hunt skill 清单 + 横切类别的研判结论。

中文简介正在准备中。当前显示原文说明。

Social authentication and OAuth/SSO for Flutter supporting Google Sign-In, Apple Sign-In, Facebook Login, and LINE Login. Use when implementing social login, OAuth flows, sign-in with Google/Apple/Facebook/LINE, SSO integration, third-party authentication, platform credential configuration (SHA-1 fingerprint for Android, Service ID for Apple, App ID for Facebook, Channel ID for LINE), native auth flows, minimal viable examples, error handling patterns, or troubleshooting authentication failures, token handling, and sign-in errors (ApiException, PlatformException).

中文简介正在准备中。当前显示原文说明。

Declarative routing and navigation for Flutter using GoRouter and AutoRoute. Use when implementing navigation guards, nested routes, type-safe routing, or deep link handling.

中文简介正在准备中。当前显示原文说明。

Integrates RevenueCat in-app purchases and subscriptions into Flutter apps using `purchases_flutter` (v10.x). Use when implementing paywalls, checking entitlements via `CustomerInfo`, configuring `PurchasesConfiguration` for iOS or Android, displaying paywalls with `purchases_ui_flutter`, handling purchase errors via `PurchasesErrorHelper`, restoring purchases, integrating RevenueCat with Riverpod or Bloc, presenting the Customer Center, handling web purchase redemption, or calling `Purchases.logIn` for cross-device purchase sync.

中文简介正在准备中。当前显示原文说明。

<One-line description of when to use this skill. Keep it under 160 characters.>

中文简介正在准备中。当前显示原文说明。

사용자가 HWP나 HWPX 양식 파일을 주면서 "이 양식으로 앱을 만들어 달라", "양식을 전산화하자", "이 서식에 입력하고 출력하고 통계 내는 웹앱"이라고 할 때 사용한다. 양식의 칸을 그대로 데이터베이스로 옮기지 않고, 칸을 분류해 이용자 명부와 연결하고, 판정을 거쳐 앱과 HWP 출력을 만드는 절차다. 사회복지 기관의 일지, 명단, 대장, 보고서 서식에 쓴다. Use when a Korean social-welfare practitioner hands over an HWP/HWPX form and wants an app built from it. For app ideas without a form file, use welfare-app-assess instead.

中文简介正在准备中。当前显示原文说明。

サイレント失敗を検出し、堅牢なエラーハンドリングを確保する。PRレビューでのエラーハンドリング検査時に使用。

中文简介正在准备中。当前显示原文说明。

スキルを作成/更新し、SKILL.md・agents・references・scripts・assetsを設計する。スキル連携や低トークン化の設計が必要なとき、または「metakota」で始まる明示的な指示があるときに使う。

中文简介正在准备中。当前显示原文说明。

解释火山 AI 音视频互动的产品能力、适用边界与最新官方文档；生成或修改 VoiceChat/Aibot 配置；并帮助用户搭建、运行和分阶段排查最小 InteractAI VoiceChat Web Demo。

中文简介正在准备中。当前显示原文说明。

Reverse engineer native, managed, Electron, packaged, firmware or browser targets with REA. Skip for ordinary source repo analysis.

中文简介正在准备中。当前显示原文说明。

Survive a /clear or context limit. Save writes a verified handoff; after the clear, restore state, verify and continue. Works in every harness.

中文简介正在准备中。当前显示原文说明。

Fabric mode for many similar workers claiming items from one shared pool. Arrives in 5.4.1. Until then this skill routes to fabric-multigraph. Use when the user asks for a swarm or for many parallel workers on one list of items.

中文简介正在准备中。当前显示原文说明。

Fabric mode for a repeat-until-done cycle (CI green, review rounds). Arrives in 5.4.1; until then routes to loop-templates and its flow-loop template.

中文简介正在准备中。当前显示原文说明。

Creates, revises, and reviews technical articles using formal encyclopedic language, numbered Markdown sections, manual tables of contents, coherent taxonomies, practical examples, and source-qualified references. Use for technical or engineering articles and knowledge-base entries, especially Markdown files under content/articles, docs/articles, or articles.

中文简介正在准备中。当前显示原文说明。

New or updated sprint plan from the current milestone, completed work, and available capacity.

中文简介正在准备中。当前显示原文说明。

Fast, concise sprint snapshot — burndown and emerging risks for situational awareness. 'How is the sprint going?'

中文简介正在准备中。当前显示原文说明。

Milestone progress review — completeness, quality metrics, risk, go/no-go recommendation. At checkpoints or before a deadline.

中文简介正在准备中。当前显示原文说明。

What should I do next? Use when stuck or you don't know what to do.

中文简介正在准备中。当前显示原文说明。

Pre-release checklist — build verification, certification requirements, store metadata, launch readiness.

中文简介正在准备中。当前显示原文说明。

Turns the PRDs and architecture into epics, one per architectural module. Use when the user wants to break the application into epics or plan the work before writing stories. Not for splitting one epic into stories.

中文简介正在准备中。当前显示原文说明。