AI Skills Directory

Electron desktop apps with React, TypeScript, and Vite. Use for IPC, window/tray, PTY terminals, WebRTC, and packaging.

Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow,…

自动分析告警信息，按SOP排查问题并生成处理报告

End-to-end pipeline for releasing an iOS / watchOS app to TestFlight and the App Store. Use when the user wants to publish, ship, or release an iOS/watchOS app, get a build onto TestFlight, archive…

Technical leadership guidance for engineering teams, architecture decisions, and technology strategy. Includes tech debt analyzer, team scaling calculator, engineering metrics frameworks, technology…

Generate a complete set of favicons from a source image and update HTML. Use when setting up favicons for a web project.

Provides AWS CloudFormation patterns for Amazon Bedrock resources including agents, knowledge bases, data sources, guardrails, prompts, flows, and inference profiles. Use when creating Bedrock agents…

Responsive layout pass covering breakpoints, touch targets, safe areas, and fluid type. Use when the UI has layout or touch issues on mobile/tablet, when adding a new screen that hasn't been tested…

Audit Value Delivery compliance after PR push

Plan and execute effective sprints using Agile methodologies. Define sprint goals, estimate user stories, manage sprint backlog, and facilitate daily standups to maximize team productivity and deliver…

Use when ECS Service Connect の DNS alias が IPv6 アドレスを返し、 IPv4-only の Fargate task から `network is unreachable` / `EAI_AGAIN` 等で接続できない問題に遭遇したとき。 OTel Collector → Tempo の OTLP gRPC、 Fargate → Service…

Add real-time or turn-based multiplayer to an existing browser game using PartyKit (Cloudflare Durable Objects). Scaffolds a room-based server, a NetworkManager client, EventBus events, GameState…

Architecture reviews across 7 dimensions (structural, scalability, enterprise readiness, performance, security, ops, data) with scored reports. Triggers on: "review architecture", "critique design",…

专业的代码审查助手，提供结构化的审查流程、详细的检查清单和建设性的反馈指南。适用于审查Pull Request、代码提交或任何需要代码质量评估的场景，涵盖功能性、安全性、性能、测试、文档、架构设计等多个维度。

将用户的演示讲稿转化为拟人化动物世界主题的演示文稿图像（顶级3D动画电影风格）。 分三步：① 理解演讲内容与受众 ② 生成每页的3D动画电影风格生图提示词（Markdown 格式，保存到 workspace/docs/outline/） ③ 调用 image_gen_ppt.py 批量生成图像（保存到 workspace/docs/slides/）。 触发条件：用户提供演示稿/PPT…

Colorblind-friendly palettes and accessible visualization design

Agent-to-Agent (A2A) communication protocol. Connect two or more Claude agents that pass messages, share context, delegate tasks, and collaborate. Implements structured handoffs, shared memory, and…

Use when a Rudder development request has an unclear lifecycle stage or owner: requirements, advisor analysis, UI design, implementation, verification, review, release, recovery, runtime contracts,…

Pressure-tests an ambitious proposal and returns a landing judgment, one minimum viable proof, explicit cuts, success/failure signals, and a stop rule. Use when a direction has more vision than…

YAML format for Claude Code agent definitions as alternative to markdown. Use when creating agents with YAML, converting markdown agents to YAML, or validating YAML agent schemas. Trigger keywords -…

Build fast applications with Bun JavaScript runtime. Use when creating Bun projects, using Bun APIs, bundling, testing, or optimizing Node.js alternatives. Triggers on Bun, Bun runtime, bun.sh, bunx,…

端到端产品教练 — 把一句话想法走到 PRD + 可点击 HTML 原型。会顶嘴、强制砍功能、用 Nielsen + Norman 做友好性硬检。Use when user 说"我有一个想法"、"想做一个产品"、"做 MVP"、"写 PRD"、"做用户友好的产品"，或调用插件命令 `/idea-coach:idea`。Do NOT use when 用户已有完整 PRD 在跑、明确说"只…

Exploits ADCS through ACL abuse on templates/CA objects and NTLM relay to enrollment endpoints. Covers ESC4 (template ACL → modify to ESC1), ESC5 (PKI object ACLs), ESC7 (ManageCA/ManageCertificates…

Review a Shadow MCP target, approve an explicit audience, and safely onboard and distribute it through the Speakeasy AI Control Plane Platform MCP.

1C-Bitrix integration. Manage data, records, and automate workflows. Use when the user wants to interact with 1C-Bitrix data.

Creates atomic git commits and pushes to remote. Use when you want to commit changes and push without creating a PR (e.g., "commit and push my changes" or "push this up").

Expert guidance for Angular and TypeScript development focused on scalable, high-performance web applications

Teaches the factory pattern for flexible object creation. Use when you need to create objects dynamically without using the new keyword or when object creation logic should be centralized.

Use when creating, releasing, or maintaining a Claude Code Plugin Marketplace - covers marketplace.json schema, version management, release checklists, changelog conventions, and validation to prevent…

Three-Layer Memory System — automatic fact extraction, entity-based knowledge graph, and weekly synthesis. Manages life/areas/ entities with atomic facts and living summaries.

Drive a live browser from the CLI with playwright-cli to navigate, interact, snapshot, and capture evidence. Use for ad-hoc browser commands, page inspection, screenshots, traces, network mocking,…

超压缩通信模式。通过去掉废话、冠词和客套语，在保持完整技术准确性的同时削减约 75% token 用量。 当用户说"caveman 模式"、"简洁模式"、"少废话"、"省 token"、"简短点"或调用 /caveman 时触发。

Implement VCG mechanism for incentive-compatible ad slot allocation with truthful bidding. Use this skill when the user needs to design a truthful auction mechanism, compute externality-based…

Diagnosis-only investigation of a failure with unknown cause - reproduce, localize, reduce, deliver root cause with evidence. Read-only; an explicit fix request routes by target and tier instead,…

Create React/Vue component with TypeScript, tests, and styles. Auto-invoke when user says "create component", "add component", "new component", or "build component".

The Foundation Skill. LLM Firewall + 2025 Security + Cross-Skill Coordination. Use for ALL code output - prevents hallucinations, enforces security, ensures quality.

Analyze the user's authorized Quantified Self training data through its read-only MCP tools. Use for current Training plans, standalone planned workouts, upcoming sessions, workout instructions,…

Execute mcloud local build to reproduce a Cloud build on the local machine. Use when debugging a build-failed deployment without pushing to the tracked branch, iterating on a build fix, or testing…

AI voice assistants with custom instructions, knowledge bases, and tool integrations.

Creating a handoff document that captures session state (completed work, decisions, open items, next steps) and delivering it via Plan Mode so the user gets the native 'clear context and continue…

Control API Platform serialization with groups, #[Context], IRI links (readableLink/writableLink), and custom context builders

Administer Jira projects. Use when creating/archiving projects, managing components, versions, roles, permissions, or project configuration.

Generate comprehensive content briefs for writers, ensuring clarity, alignment, and strategic content creation across all formats.

Eight-step epic build cycle — reads state.yaml, execution-status.yaml, and one epic capsule; updates status via bp-yaml-set or direct edit. Resume mode runs one step per invocation. Use instead of…

Visualizes, creates, and diagnoses dependencies between MCP work items. Use when a user says: what blocks this, add a dependency, show dependency graph, why can't this start, link these items, unblock…

Uses the jj (Jujutsu) version control system. Use when asked about jj commands, git push/fetch workflow, or rebasing onto main for non git repo

Scaffolds new Meta Quest and Horizon OS projects with recommended settings for Unity, Unreal, Android/Spatial SDK, or WebXR. Use when creating a new Quest app from scratch.

Code review a pull request

Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, typography,…

Design and operate bounded multi-agent workflows with task decomposition, dependency graphs, ownership, handoff contracts, shared-state controls, approvals, recovery, and synthesis. Use when a task…

Shipany AI-powered SaaS boilerplate documentation. Use when working with Shipany framework, Next.js 15, TypeScript, Drizzle ORM, NextAuth, payment integration, or building SaaS applications.