Generate, refresh, and maintain Webiny MCP server skills from source documentation and codebase. Use this skill when you need to create new Webiny skills, update existing skills after framework changes, regenerate the entire skill library, or create a skill for a specific Webiny feature. Trigger this whenever someone says "create a skill", "update skills", "refresh skills", "add a new skill for X", or "regenerate the skill library". This is the meta-skill that produces all other Webiny MCP skills.

Provision and manage GPU pods on RunPod for explicitly chosen long-running research experiments. Use when a Feynman replication, benchmark, or dataset-heavy research run needs persistent GPU compute with SSH access.

以第三方中立顾问身份，围绕某个产品近1个月内的最新动态，撰写适合公众号发布的简短深度文章（不超过4屏）。 触发条件：用户输入产品名称并希望生成顾问视角的分析文章，提到"帮我写篇XX的文章"、"分析一下XX最近的动态"、"以顾问角度写XX"、"产品影响力文章"、"公众号文章"、"帮我写XX的点评"、"XX最近怎么样"等。 即使用户只说"帮我写一篇关于XX的文章"，只要意图是产品评析，也应使用本 skill。 输出为 Markdown 文件，保存到当前项目 markdown/ 目录，适合手机端阅读，第一人称，中立有据，无AI生成痕迹。

通过持续的对话式提问，训练用户的逻辑思维与独立思考能力：给用户出思考题、用苏格拉底式追问引导用户自己发现漏洞、对用户的每次回复做点评并给出具体改进意见，同时把训练记录和薄弱点保存到 markdown，用于后续对话中做针对性、渐进式的训练。触发条件：用户提到"训练我的逻辑思维"、"锻炼独立思考"、"陪我练逻辑"、"logic training"、"批判性思维训练"、"苏格拉底式提问"、"帮我练习思辨"、"考考我的逻辑"、"跟我辩论/追问练习"，或者用户明确要求"你来提问，我来回答，你来点评"这种角色反转式训练。即使用户只说"我想提升一下逻辑思维能力，帮帮我"或"以后没事就考考我"，也应使用本 skill，并且要记住：这是一个跨越多轮对话、甚至跨越多次会话的持续训练关系，每次用户提到练习/考我/继续训练，都应该回到本 skill 而不是当作普通问答。

根据用户的个人特征（技能、时间、体力、学历、所在城市、期望收入等），从网络上抓取最新招聘信息（包括闲鱼、BOSS直聘、58同城、拉钩、猎聘、智联招聘等平台），按性价比（时薪/日薪、通勤成本、门槛匹配度）排序，输出适合该用户接的活（长期岗位、兼职、临时工均纳入），以图文并茂的 Markdown 文件保存到项目 markdown/ 目录。触发条件：用户描述自己的个人情况并希望找活干；提到"帮我找工作"、"我想接活"、"有什么活可以做"、"找兼职"、"找临时工"、"找副业"、"找长期工作"、"我能做什么工作"、"帮我匹配工作"、"找适合我的岗位"、"按性价比推荐工作"、"哪些活值得接"、"我有这些技能能做什么"等。即使用户只是说"我现在没工作，帮我找找看"或者给出了个人情况描述，也应立即使用本 skill。

以资深投行分析师的视角，输入一个行业或产业名称，系统梳理该行业产业链各节点，列出各节点代表性上市公司，深度分析商业模式、上下游关系、核心竞争力、护城河、风险揭露、竞争格局等，用通俗易懂的语言面向普通投资人输出图文并茂的Markdown报告，保存到当前项目 markdown/ 目录。触发条件：用户提到"产业链分析"、"帮我分析XX行业"、"XX行业上下游"、"XX行业有哪些上市公司"、"XX行业怎么投"、"XX行业竞争格局"、"XX行业护城河"、"XX行业风险"、"梳理XX产业链"、"XX上下游企业"等。即使用户只说"帮我看看XX行业"或"XX行业值得投吗"，也应使用本skill。输出为Markdown文件，保存到markdown/目录，图文并茂，语言专业但通俗，适合普通投资人阅读。

深度解读企业财报，将财报 PDF 或 URL 转化为面向普通投资者的专业分析报告，以 Markdown 格式保存到当前项目的 markdown/ 目录。 触发条件：用户上传或提供财报 PDF、提到"分析财报"/"读财报"/"解读财报"/"看看这家公司"/"帮我分析一下 XX 公司"，或任何需要深入理解一份财务报告的场景。 输出一份犀利、有逻辑支撑的投资参考报告，涵盖：核心收入分析、财务健康诊断、隐蔽风险雷区排查、行业竞争格局、前瞻性估值，以及明确的投资参考建议。 即使用户只说"帮我看这份年报"但内容是财报，也应使用本 skill。

根据用户给出的行业名称（或默认使用热点社会新闻），抓取最新新闻热点，用"找世界bug"的视角——找出那些打眼一看就不合理的地方——深度分析根因、利益链条、监管盲区，并给出多维度解决思路，输出图文并茂（含SVG/Mermaid/ASCII图形）的Markdown文件，保存到项目markdown/目录。 触发条件：用户提到"找bug"、"社会bug"、"不合理现象"、"帮我分析这个行业的问题"、"帮我找新闻里的bug"、"找热点新闻的漏洞"、"有什么不合理的地方"、"帮我分析为什么会这样"、"bug猎手"等。即使用户只说"帮我找找最近有什么奇怪的新闻"或"这个行业有哪些不合理"，也应使用本 skill。

生成深度读书笔记的专用 Skill。输入书籍的豆瓣链接（或书名+作者），自动搜索书籍信息、高质量书评、学术评价等素材，结合 Claude 的深度思考，生成图文并茂、观点鲜明、适合分享的读书笔记，以 Markdown 格式保存到项目 markdown/ 目录。触发条件：用户提供豆瓣链接、提到"读书笔记"、"书评"、"帮我分析这本书"、"写一篇XX书的笔记"，或任何希望深度理解一本书的场景。即使用户只说"帮我写一下这本书的感悟"，也应使用本 skill。

Answer general or cross-domain questions with a non-pleasing rational mode: adversarial red-team and blue-team expert analysis, mutually exclusive conclusions, up to five debate rounds, saved Markdown intermediate expert outputs, and a final first-person judge-written plain-language article. Use when the user asks for rational adversarial analysis, red/blue team debate, non-flattering judgment, evidence-backed multi-expert reasoning, or a final Markdown answer to a broad question.

Answer open-source product questions by combining local source-code and documentation research, project framework notes generated by init, DeepWiki repository knowledge, and current web evidence, then save a sourced, diagram-rich Markdown answer to the current project's markdown directory. Use when the user asks about behavior, architecture, internals, configuration, APIs, troubleshooting, performance, operations, extension points, practical reproduction, or version-specific details of one or more open-source projects and provides the question, all relevant local source directories, and DeepWiki repoName values.

解读用户粘贴的 GitHub 每周 Trending 或开源项目榜单内容，基于用户提供的候选项目、项目 README、GitHub 项目页和 DeepWiki 生成适合公众号发布的 Markdown 文章，并输出到当前项目 markdown 目录。用于 GitHub 周榜解读、每周开源热点、热门开源项目分析、公众号开源项目推荐。

Generate stage-3 high-impact publishable markdown articles in 德哥风格 from daily-finance and finance-core-analysis outputs plus current web verification: first-principles mechanisms, counterintuitive '不是A，是B' framing, reusable systemic models, and strict data/logic validation. Use when user wants a 公众号爆款 article, final daily finance article, sharp financial commentary, or first-principles macro/market writing based on upstream markdown documents.

Generate stage-2 publishable deep financial analysis markdown from a daily-finance brief plus current web verification, using liquidity, interest rates, risk appetite, capital flows, policy, and balance-sheet constraints. Use when user wants a deeper 公众号-style markdown analysis based on daily-finance output, core macro/market mechanism analysis, or the second step of the daily finance pipeline before finance-explosive-article.

Activates Warren Buffett's complete investment thinking system. The following scenarios must trigger it: analyzing any stock or company, evaluating investment opportunities, interpreting financial reports/annual reports/shareholder letters, assessing business moats or competitive advantages, evaluating management quality and integrity, making buy/hold/sell decisions, understanding core value investing concepts (compounding/intrinsic value/margin of safety/circle of competence/Mr. Market), analyzing any industry (insurance/banking/consumer/media/energy/railroads/technology), handling capital allocation/buybacks/dividends questions, assessing market sentiment and macro risks, exploring when to sell, analyzing institutional imperative or management behavior. Even if the user does not mention "Buffett," proactively trigger whenever the topic involves investment analysis, business quality assessment, or investment decision-making.

Use this skill whenever the user wants to analyze binaries with radare2/r2 from the command line, including reverse engineering, disassembly, function analysis, strings/import inspection, patching, binary diffing, hex inspection, or r2 scripting. Also use it when the user mentions PE/ELF/Mach-O/DEX/WASM files together with CLI analysis, `rabin2`, `rasm2`, `radiff2`, `r2pipe`, or asks for radare2 command help on Windows/Linux/macOS.

Creates task-oriented technical documentation with progressive disclosure. Use when writing READMEs, API docs, architecture docs, or markdown documentation. Also use this skill at the END of any completed reverse engineering, penetration testing, CTF, or security analysis task to generate a formal report in the user's project directory. Trigger keywords: 写报告, 写文档, 出报告, writeup, 技术文档, report, documentation.

在 CLI 环境下做 Android APK 逆向时使用。适用于 APK 解包、Java 反编译、smali 修改、重打包、Frida 动态 Hook，以及按需切换到 so/native 分析。优先使用本机已安装的 jadx、apktool、frida、adb、ida-reverse、radare2。

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for parser differentials, HTTP normalization gaps, ambiguous headers, path decoding drift, transfer-framing mismatches, and request smuggling routes. Use when the user asks to trace proxy and backend parse differences, conflicting path normalization, Host or forwarded-header ambiguity, CL/TE issues, or routing outcomes that differ across hops. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for custom binary or text protocol recovery, handshake reconstruction, framing, sequence control, checksums, stateful replay, and accepted-session reproduction. Use when the user asks to decode an unknown protocol, recover custom framing, build a replay harness, satisfy sequence or checksum rules, replay a captured session, or prove the smallest message order that reaches an accepted branch. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.