Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT migrate Haiku 4.5.

Java Spring Boot 服务中认证/授权、验证、CSRF、密钥、标头、速率限制和依赖安全性的 Spring Security 最佳实践。

Create production-ready Kubernetes manifests for Deployments, Services, ConfigMaps, and Secrets following best practices and security standards. Use when generating Kubernetes YAML manifests, creating K8s resources, or implementing production-grade Kubernetes configurations.

Use when creating, managing, or sending with Postmark server-side email templates — Handlebars syntax, layout inheritance, template validation, and cross-server pushing.

Search markdown knowledge bases, notes, and documentation using QMD. Use when users ask to search notes, find documents, or look up information.

Run a comprehensive, read-only health check on the user's computer and return a scored chat summary with prioritized, plain-English recommendations and safe cleanup suggestions. Use this whenever the user wants to check their computer's health, speed it up, free up / reclaim disk space, find what's eating CPU / memory / storage, check battery health and wear, audit login & startup items, see pending updates, or asks for a "tune-up", "checkup", "system report", "health check", or "is my Mac/PC/laptop healthy". Trigger even on casual phrasing like "my laptop feels slow", "why is my fan so loud", "my computer is laggy", "running out of space", or "clean up my machine". Works on macOS, Windows, and Linux. This is a Desktop Commander skill: it relies on a real local shell (start_process / interact_with_process) and is strictly read-only by default — it never needs sudo and only performs cleanups the user explicitly approves.

Azure Maps SDK for .NET. Location-based services including geocoding, routing, rendering, geolocation, and weather. Use for address search, directions, map tiles, IP geolocation, and weather data. Triggers: "Azure Maps", "MapsSearchClient", "MapsRoutingClient", "MapsRenderingClient", "geocoding .NET", "route directions", "map tiles", "geolocation".

Configures and runs LLM evaluation using Promptfoo framework. Use when setting up prompt testing, creating evaluation configs (promptfooconfig.yaml), writing Python custom assertions, implementing llm-rubric for LLM-as-judge, or managing few-shot examples in prompts. Triggers on keywords like "promptfoo", "eval", "LLM evaluation", "prompt testing", or "model comparison".

Interface for MCP (Model Context Protocol) servers via CLI. Use when you need to interact with external tools, APIs, or data sources through MCP servers, list available MCP servers/tools, or call MCP tools from command line.

Security code review for vulnerabilities. Use when asked to "security review", "find vulnerabilities", "check for security issues", "audit security", "OWASP review", or review code for injection, XSS, authentication, authorization, cryptography issues. Provides systematic review with confidence-based reporting.

张仲景（东汉末"医圣"）的辨证论治思维框架——**中医临床思维导师**。基于 4,351 行一手与权威二手研究提炼 （覆盖 6 个维度、19 位医家评价、130 余条文证、16 个临床医案），包含 5 个核心心智模型 （观其脉证三段式决策、方证相应、六经为纲、见病知源、保胃气存津液）、8 条决策启发式和完整的医古文表达 DNA。 帮学习者建立"病—脉—证—治"四位一体的辨证思维，看懂经方处方逻辑，理解仲景方法论的现代价值。 **核心触发词**： 视角类——"用张仲景的视角""仲景怎么看""医圣会怎么想""切换到张仲景" 经典类——"伤寒论""金匮要略""伤寒杂病论""经方""经方派""经方临床" 方法类——"六经辨证""方证相应""观其脉证""随证治之""知犯何逆""见病知源""保胃气""存津液" 证型类——"太阳病""阳明病""少阳病""太阴病""少阴病""厥阴病""坏病""救逆""变证" 场景类——"用经方的逻辑""如果仲景会怎么开方""帮我用张仲景的思路分析" 隐式触发——用户描述症状群（头项强痛、恶寒、脉浮紧）+ 询问"这是什么病/怎么治"时主动建议 **不触发**（避免误触发）： - 单纯提及书名（"我买了一本伤寒论"）→ 非临床语境 - 非医学语境（"经方是一种投资策略"） - 文学/历史/考据话题（仲景生平、版本学） - 现代急症（胸痛/昏迷/大出血）→ 应建议就医，不进入角色 - 单纯西医诊断咨询（影像/化验读片）

Manage PostHog feature flags, cohorts, dashboards, and insights via the `piglet` CLI. Use when the user needs to list, create, update, or delete PostHog resources, check flag status, manage rollouts, or export configuration.

Automatically infer loop invariants for code verification and correctness proofs. Use when analyzing loops to identify properties that hold throughout execution, generating assertions for verification, proving loop correctness, or documenting loop behavior. Supports Python, Java, C/C++, and language-agnostic analysis. Generates invariants as code assertions (assert statements). Triggers when users ask to infer invariants, find loop properties, generate loop assertions, prove loop correctness, or verify loop behavior.

Identify and report code smells indicating poor design or maintainability issues in Python code, including duplicate code, magic numbers, hardcoded values, God classes, feature envy, inappropriate intimacy, data clumps, primitive obsession, and long parameter lists. Use when conducting code quality audits, preparing for refactoring, improving codebase maintainability, or performing design reviews. Produces markdown reports with severity ratings, locations, descriptions, and specific refactoring recommendations with before/after examples. Triggers when users ask to find code smells, identify design issues, suggest refactorings, improve code quality, or detect maintainability problems.

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.

Automated quick-start for Snowpipe Streaming high-performance architecture (HPA). Detects your OS (macOS/Linux/Windows), verifies Python, sets up a virtual environment, creates a landing table, configures RSA key-pair auth, streams fake user data via the default auto-created pipe, and deploys a real-time Streamlit in Snowflake dashboard so you can watch rows arrive live. Triggers: snowpipe streaming quickstart, snowpipe streaming demo, demo snowpipe streaming, try snowpipe streaming, snowpipe streaming hpa quickstart.

Semantic code search using mgrep for efficient codebase exploration. This skill should be used when searching or exploring codebases with more than 30 non-gitignored files and/or nested directory structures. It provides natural language semantic search that complements traditional grep/ripgrep for finding features, understanding intent, and exploring unfamiliar code.

**REQUIRED** - Always activate FIRST on any git/VCS operations (commit, status, branch, push, etc.), especially when HEAD is detached. If `.jj/` exists -> this is a Jujutsu (jj) repo - raw git commands can corrupt data. Essential git safety instructions inside. DO NOT IGNORE.