Start up, tear down, and configure the local Kubernetes development environment for OpenShell. Uses k3d (Docker-backed k3s) + Skaffold + Helm. Covers cluster lifecycle, optional add-ons (Keycloak OIDC, Envoy Gateway), HA testing, and port mappings. Trigger keywords - local k8s, local cluster, k3d, skaffold, helm dev, start cluster, stop cluster, tear down cluster, delete cluster, create cluster, helm:k3s, helm:skaffold, local dev environment, dev cluster, k8s dev, envoy gateway local, keycloak local, high availability, HA.

Investigate a plain-language problem description by deeply exploring the codebase, then create a structured GitHub issue with technical findings. Prequel to build-from-issue — maps vague ideas to concrete, buildable issues. Trigger keywords - spike, investigate, explore, research issue, technical investigation, create spike, new spike, feasibility, codebase exploration.

Given a GitHub issue number, plan and implement the work described in the issue. Supports direct user requests and unattended queue processing through the `agent:*` workflow labels. Includes tests, documentation updates, and PR creation. Trigger keywords - build from issue, implement issue, work on issue, build issue, start issue.

Building forms with the FormModel system — field types, renderers, layout, validation, conditional rules, computed fields, and dynamic zones. Use this skill when the developer needs to define form fields with the builder API, choose renderers, build layouts with tabs/rows/separators, add validation (Zod or imperative), use conditional visibility/disable rules, create computed fields, or work with object fields and templates (dynamic zones).

Build reusable Manim explainers for technical concepts, graphs, system diagrams, and product walkthroughs, then hand off to the wider video stack if needed. Use when the user wants a clean animated explainer rather than a generic talking-head script.

输入一个产品 idea（一句话或详细描述均可），自动生成图文并茂、结构完整的 MRD（市场需求文档），以 Markdown 格式保存到当前项目 markdown/ 目录，同时输出配套 SVG 图表文件。触发条件：用户提到"写 MRD"、"帮我写市场需求文档"、"生成 MRD"、"写产品市场需求"、"我有个产品想法"、"帮我把这个 idea 写成 MRD"、"市场需求文档模板"、"产品立项文档"、"帮我写需求文档"。即使用户只给出一句简短的产品描述如"我想做一个 XX 产品"，也应立即使用本 skill 生成 MRD。本 skill 面向产品经理、创业者、产品负责人，输出可直接用于团队评审和立项决策的专业文档。

预测美股个股次日走势，输出图文并茂的 Markdown 分析报告（含逻辑推导、中间结果、概率量化、操作建议）。触发条件：用户输入美股股票名称或代码，并希望获得次日走势预测；关键词包括"预测明天走势"、"明天能涨吗"、"帮我分析一下XX股票"、"明天该买吗"、"次日预测"、"做T建议"、"短线操作"、"明日行情"、"值得持有吗"等。即使用户只说"帮我看看NVDA明天怎么走"或"AAPL明天能不能买"，也应使用本 skill。输出 Markdown 文件保存到当前项目 markdown/ 目录，要求逻辑清晰、概率可量化、图文并茂，投资小白也能看懂。

用红蓝双队辩论模式深度解答通用问题，以非讨好型人格的理性人视角输出最终报告。 触发条件：用户提出任何值得深度分析的问题，尤其是存在争议、有多个维度、需要权威数据支撑的问题。 提到"红蓝辩论"、"辩证分析"、"正反两面"、"两种观点"、"帮我深度分析"、"有没有反驳意见"、"理性分析一下"、"客观看待"，或提出任何开放性、争议性问题时必须使用本 skill。 即使用户只是提出一个看似简单的问题如"XX 到底值不值得做"或"XX 是对的吗"， 只要涉及价值判断、策略选择、事实真相等复杂情境，也应使用本 skill。 本 skill 不追求讨好用户，拒绝模糊骑墙，双队结论必须互斥，最终裁判整合并输出面向小白的第一人称深度文章。

基于功能设计文档与现有源码，端到端实现一个产品功能：开发、代码 review、测试用例编写与执行， 循环迭代直到测试通过，最终产出用户手册与实现总结文档（保存到当前项目 markdown/ 目录）。 触发条件：用户提供了功能设计文档（PRD/设计文档/需求描述）+ 源码目录（或代码库路径）， 并希望"实现这个功能"、"开发这个功能"、"把这个设计文档变成代码"、"做这个功能的开发+测试"、 "完整实现并测试"、"端到端开发"，或明确要求按"开发-review-测试"循环推进直到测试通过。 也适用于需要额外运行环境的开发任务，例如 PostgreSQL/MySQL 等数据库插件开发 （可能需要编译、搭建实例、配置参数、初始化、跑测试）、需要启动服务进程才能测试的后端功能、 需要特定运行时环境的库或框架功能。 即使用户只是说"帮我把这个功能做出来"、"按设计文档实现一下"、"这个功能开发完了麻烦测试一下"， 但同时给出了设计文档和代码路径，也应使用本 skill。 本 skill 的核心是严格的"开发 ⇄ Review"循环 + "测试者不预先看代码"的盲测试原则， 因此当用户提到"独立测试"、"测试不能看代码"、"先写测试用例再看代码"、"black-box 测试"时， 也应优先使用本 skill。 不适用于：只是要求"写一个脚本"、"改一行代码"、"快速修一个 bug"等轻量级、 无需走完整开发-review-测试闭环的任务；也不适用于纯粹的代码评审（无需新开发功能） 或纯粹的测试用例编写（无设计文档、无需开发）这类单一环节请求—— 这些更适合直接处理而非套用本 skill 的完整闭环流程。

Write Chinese Markdown articles for university students and adults with social experience that explain one viewpoint, axiom, theorem, law, principle, or theory system through "求真讲法、求存讲法、思考", with text/Mermaid and standalone GitHub-renderable SVG files, assumptions, derivation or motivation, applicability boundaries, positive and negative examples, and save the result under the current project's markdown directory. Use when Codex is asked to generate 公理讲解文案、定理讲解、理论体系通俗解读、观点拆解、面向大学生和成年人的图文并茂 Markdown 文章.

Download WeChat official account articles in multiple formats (HTML, PDF, Word, Markdown, TXT, MHTML), including single article download, collection (appmsgalbum) download, local bulk workflows, and metadata export. Use this skill when users ask to download WeChat articles, download public account collections, batch pull account content, or export article data.

Use for authorized macOS and Mach-O reverse engineering including codesign, Objective-C/Swift recovery, endpoint security surfaces, and Apple platform malware analysis.

Default entrypoint and master ctf-sandbox-orchestrator workflow for CTF, exploit, reverse engineering, DFIR, pwnable, crypto, stego, mobile, AI-agent, cloud, container, Active Directory, Windows-host, and identity challenges. Use first when the user presents challenge infrastructure, binaries, prompts, hosts, or identities that should be treated as sandbox-internal by default and Codex needs to choose, route, and load the right downstream analysis path with concise evidence.

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for file uploads, imports, previews, archive extraction, format conversion, parser invocation, and deserialization chains. Use when the user asks to inspect an upload or import path, trace archive extraction, preview or converter behavior, explain how a file reaches a parser or deserializer, or connect one uploaded artifact to the decisive backend effect. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

Cold-start interview — builds your watchlist, indexes the policy library, and learns your materiality threshold so the monitor surfaces signal instead of noise. Use on fresh install, when reconfiguring (--redo), or when re-checking what connectors are actually responding (--check-integrations).

Guided customization of your litigation practice profile — change one thing without re-running the whole cold-start interview. Adjust practice role, side (plaintiff / defense / mixed), risk calibration, landscape, house style, escalation contacts, severity vocabulary, or matter workspace paths. Use when the user says "change my [thing]", "update my profile", "edit my config", or "customize".

Professor's one-time clinic setup — practice areas, jurisdiction, supervision style (formal review queue / configurable flags / lighter-touch), and handbook/rules upload. Writes CLAUDE.md so every other skill and every student who runs /ramp reads from the same clinic context. Use on fresh install, when CLAUDE.md has placeholders, when re-doing setup with --redo, or when re-checking integrations with --check-integrations.

Cold-start setup — learns your jurisdictional footprint and escalation rules from your handbook and termination memos. Asks which states and countries have employees, reads seed documents, and builds a jurisdiction-aware escalation table. Use on fresh install, when CLAUDE.md still has [PLACEHOLDER] markers, or when re-running with --redo or --check-integrations.

Triage open pull requests for CI status, review comments, and merge readiness. Use in PR babysitter loops. Respects project review norms and required checks.

Parse CI failures, identify failing job/step, classify as flake, regression, env, or config. Use in CI sweeper loops before any fix attempt.