Search, read, and query research papers via Feynman's alphaXiv-backed alpha tools. Use when the user asks about academic papers, wants to find research on a topic, needs to read a specific paper, ask questions about a paper, inspect a paper's code repository, or manage paper annotations.

Migrates Next.js projects to vinext (Vite-based Next.js reimplementation). Load when asked to migrate, convert, or switch from Next.js to vinext. Handles compatibility scanning, package replacement, Vite config generation, ESM conversion, and deployment setup (Cloudflare Workers natively, other platforms via Nitro).

Generate stage-1 publishable daily financial news markdown by accessing current web data, filtering reliable macro/market news, validating numbers and article logic, and writing a source-backed brief. Use this skill whenever the user asks for "今日财经", "财经日报", "财经简报", "市场要闻", "每日财经", financial summary, market analysis, daily finance report, 公众号财经日报, or the first step of the daily finance pipeline that feeds finance-core-analysis and finance-explosive-article. Even if the user only says "帮我看看今天市场怎么样" or "今天有什么财经新闻", use this skill.

给定一篇文章的 URL 或全文内容，深度阅读消化后，以更高屋建瓴的视角创作一篇全新文章： 提取核心观点+基石假设，找逻辑漏洞或用第一性原理重构假设，续写新内容，最终输出图文并茂的 Markdown 文章。 触发条件：用户提供文章链接或粘贴文章内容，并说"帮我改写"、"写一篇更高层次的文章"、"找逻辑漏洞"、 "重构观点"、"消化后重写"、"升华这篇文章"、"基于这篇文章写一篇新的"，或用户说"这篇文章有什么问题/ 漏洞/不足"并希望输出新文章时，必须使用本 skill。即使用户只说"帮我把这篇文章写得更好"或"这篇文章太 浅了，帮我深化一下"，也应使用本 skill。

将 PRD 翻译成「可独立测试」的功能设计文档。文档的下游使用者包括开发者、评审者、测试者,且三方互相隔离(测试者看不到开发者写的代码),所以必须把行为、状态、接口、数据、权限、异常、验收标准全部显式化,让测试者能独立从文档推导用例。输入是一份已写好的 PRD 文档,输出是一份完整的 Markdown 功能设计文档,保存到当前项目的 `markdown/` 目录。适用于:写功能设计文档、技术设计文档、Tech Design、详细设计说明书、FDD、Functional Design Doc、Detailed Design、模块设计文档、把 PRD 翻译成开发设计、把需求拆成可开发/可测试/可评审的规格。

Analyze PostgreSQL git commit history between two commit ids and, when valuable DBA/application-developer changes exist, write a Chinese Markdown article for WeChat/公众号 readers with examples checked against SQL tests, docs, or relevant source. Use when the user is inside a PostgreSQL source checkout and provides two commit ids, asks to interpret Postgres commits, summarize a release/development window, identify DBA/application-developer value from commit logs, group related commits, exclude reverted commits, and either output a sourced article under the current project's markdown directory or return a no-article analysis when no valuable commits are present.

Answer PostgreSQL core database questions by researching the local postgres source tree, PostgreSQL documentation under doc/src/sgml, relevant source code, and DeepWiki repository knowledge for postgres/postgres; use when the user asks any PostgreSQL database behavior, internals, SQL, configuration, administration, performance, storage, planner, executor, replication, or documentation question and wants a sourced Markdown answer saved to the current project's markdown directory. Refuse questions about non-PostgreSQL-core projects, including PostgreSQL ecosystem plugins, extensions maintained outside postgres/postgres, external tools, drivers, cloud services, forks, or third-party products.

Analyze an open-source project from a repository URL and write a deeply sourced Chinese Markdown article. Use when the user asks to research a GitHub/open-source project, read its README, use DeepWiki MCP for architecture analysis, search related articles, compare competitors, validate claims, and save the final article under the current project's markdown directory.

Generate a concise Chinese WeChat-ready Markdown article from an industry name by searching current news from the last month, verifying evidence across production, demand, inputs, ecosystem, policy, financing, and technology signals, and writing first-person neutral third-party industry insight without visible author identity or AI traces. Use when the user asks for 行业新闻追踪, 行业洞察, 近一个月行业分析, 公众号短文, industry trend notes, or a source-backed short article saved to the current project's markdown directory.

系统性'讲透'一个行业的深度分析技能。覆盖产业链分布、利润分布、代表企业、人货场、供需连接, 并推演不合理点、机会点、入局策略(产品/客群/商业模式/定价)、竞争对手与合作伙伴。触发场景: 讲透/分析XX行业、XX产业链、XX行业机会、如何进入XX行业、XX赛道分析、我想做XX怎么切入等。输出图文并茂的深度分析报告到当前项目 markdown/ 目录。

Find latent bugs in a local PostgreSQL source tree (REL_xx_STABLE branch or HEAD) the way a core hacker does: build a heavily-poisoned debug instance (cassert + cache-discard + -O0/-ggdb3 + core dumps), fuzz it (sqlsmith) until the backend crashes, triage the core into a minimal reproducer (MRE), git-bisect the introducing commit, and render a community-style pgsql-bugs markdown report. The instance never auto-shuts-down. Use when the user says "find a bug in postgres", "fuzz postgres", "hunt for a crash", "test a recent commit", "write a repro", "bisect this crash", "把 PG 跑起来找 bug", "fuzz 一下 postgres", "看看这个 commit 会不会出问题", etc. Triggers whenever the user points at a PG source dir and wants to hunt bugs.

Analyze company annual reports, quarterly reports, 10-K/10-Q filings, earnings releases, shareholder letters, or financial-report PDFs/URLs/files and produce a professional Chinese Markdown report for ordinary investors. Use when the user provides a company financial report address or local file and asks for 财报分析, 年报解读, 季报解读, 10-K/10-Q analysis, earnings analysis, investment reference, accounting red-flag detection, valuation discussion, or beginner-friendly explanation saved to the current project's markdown directory.

Explain a finance-explosive-article markdown file for readers with weak financial knowledge by unpacking concepts, causal chains, examples, analogies, and transferable analysis methods. Use when the user asks to turn a daily finance explosive article, 德哥财经爆款文章, market commentary, or finance markdown into a beginner-friendly detailed interpretation saved under the current project's markdown directory.

基于用户提供的企业名、企业简介、公司网站、产品信息、财报或访谈材料，搜索当前公开资料并生成企业画像、未来规划与建议书。Use when the user asks for 企业未来规划、公司战略建议书、企业画像、行业/赛道/场景分析、商业机会挖掘、客户付费痛点、产品原型、MVP、团队组建、变现路径、转型增长方案, and wants a source-backed Chinese Markdown report saved under the current project's markdown directory.

Turn a blog post, article, notes, or any source material into a set of vertical poster images — one cover plus several coherent content slides that explain the core points. Renders HTML/CSS to exact-size PNGs via headless Chrome. Use whenever the user wants cover art, 讲解图/配图, carousel slides, 封面图, poster series, or "content images" from an article/文章/素材/文件, especially for blog, 公众号, 小红书, or social posts. Default output is 1080×1920 PNG named 1.png (cover), 2.png, 3.png … written to the current working directory (the project the user is in) — never the source file's directory.

三层审查模型,逐段逐句验证文章真伪、证据链与逻辑结构。Use when the user asks to fact-check, verify, audit, or evaluate the credibility of an article, essay, report, opinion piece, social-media post, or any written claim — including checking logical consistency, evidence chains, source reliability, fabrication, non-quantifiable conclusions, and producing a scored report with original-text citations.

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.

Alef-managed generated bindings in packages/* and binding crates — the regeneration workflow (task alef:generate / alef:format), Go DocumentExtractor→Extractor rename mapping, the git-diff freshness check, and the key alef.toml sections. Load before editing anything under packages/* or a binding crate, or when regenerating, formatting, or verifying Alef output.

Use for authorized reverse engineering of browser extensions (Chrome/Firefox) including manifest analysis, background workers, and extension-based credential or traffic logic recovery.

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for Kerberos, WinRM, SMB, RDP, Windows credential material, replayable tickets, delegation edges, and host-to-host pivot chains. Use when the user asks to replay Kerberos material, trace a WinRM, SMB, or RDP pivot, understand host-to-host privilege movement, or prove which Windows service accepted a credential or ticket. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.