国家趋势与顺势而为分析助手。围绕国家最新五年规划、重大政策文件与近期重大新闻，做"势—道—术"三层推演，面向投资、创业方向、商业思路、产品思路、就业择业、学习规划六大场景输出图文并茂的分析报告。Use this skill when the user asks to "分析国家政策"、"顺着国家走"、"势头上赚钱"、"五年规划解读"、"国家趋势分析"、"顺势而为"、"国势分析"、"国家导向分析"、"国家战略解读"、"政策红利分析"、"产业政策机会"、或任何希望结合国家政策与趋势做投资/创业/职业/学习决策的场景。默认聚焦中国（可配置为其他国家），输入用户特点（擅长的领域、特长、爱好等），未输入则按普通人处理，输出 markdown 报告到当前项目的 markdown 目录，图文并茂。

分析通用复杂问题，识别所涉及的领域范畴，召唤对应领域的专家角色（可多位）分别搜证与深度解析，最后将所有专家视角无缝合成为一篇面向小白、第一人称、图文并茂的 Markdown 文章，输出到项目 markdown/ 目录。触发条件：用户提出任何需要深度分析的问题，尤其是跨学科、跨领域的复杂问题。提到"帮我分析"、"深度解析"、"多角度分析"、"专家视角"、"帮我搞清楚XX"、"为什么XX"、"XX是怎么回事"、"用第一性原理分析"、"从多个维度看"等。即使用户只是提出一个开放性问题如"为什么XX会发生"或"如何看待XX现象"，也应使用本 skill，尤其当问题涉及多个专业领域时。

给定一个行业，围绕该行业提出若干个"好问题"（只提问、不给答案，但每个问题要配"为什么这是个好问题"的理由）。触发条件：用户提到"帮我想几个好问题"、"这个行业有什么值得问的问题"、"帮我出选题"、"行业狗皮膏药问题"、"行业老大难问题"、"近期热点问题"、"帮我策划几个话题"、"这个行业值得深挖的问题有哪些"、"good ask"、"提问清单"，或者在准备写行业分析/公众号文章/辩论/调研之前想先找到几个真正值得问的问题。即使用户只说"帮我想想XX行业能问点啥"或"XX行业有哪些值得讨论的问题"，也应使用本 skill。本 skill 只产出问题和理由，不产出答案、不产出解决方案，如果用户还想要答案/深度分析，应在问题清单产出后提示可以用 multi-expert-analyzer、bug-hunter、red-blue-debate、industry-insight-writer 等 skill 继续深挖。

Analyze an industry or sector from a senior investment-banking perspective for ordinary investors by mapping the industry chain, identifying representative listed companies at each node, and writing a source-backed Markdown report. Use when the user provides an industry/sector/产业 name and asks for 产业链分析, 行业上市公司梳理, 投资银行视角分析, 商业模式/上下游/核心竞争力/护城河/竞争格局/风险揭露, or a visual Markdown investment reference saved under the current project's markdown directory.

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.

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.

Generate a source-backed, shareable Chinese Markdown reading note from a Douban book URL. Use when the user provides a Douban book link and asks for 读书笔记, book notes, book summary, reading reflection, 图文并茂笔记, or a Markdown article that combines book metadata, high-quality external research, the author's argument, evidence, logic, assumptions, insights, transferability, and personal reflection saved under the current project's markdown directory.

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.

Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".

Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.

Plans Convex schema and data migrations with widen-migrate-narrow and @convex-dev/migrations. Use for breaking schema changes, backfills, table reshaping, or zero-downtime rollouts.

Builds reusable Convex components with isolated tables and app-facing APIs. Use for new components, reusable backend modules, integrations, or component boundary work.

Read or configure the vault filing methodology and suggest destinations for planned knowledge creation under Generic, LYT, PARA, or Zettelkasten. Use for wiki mode, methodology mode, what is my vault mode, set vault mode, switch to PARA, use LYT, Zettelkasten setup, change mode, configure mode, or methodology routing. This skill does not save content or migrate notes.

Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.

Fine-tune MiniCPM5-1B or MiniCPM5-2B with LLaMA-Factory (YAML-driven SFT / DPO / WebUI). Use when the user wants to fine-tune via LLaMA-Factory, llamafactory-cli, mentions YAML configs, WebUI, or asks for the most-documented community framework.

Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.

Generate competitive SEO content briefs with per-section word counts, competitor scoring, keyword density guidance, and page-type templates. Supports both new page briefs and improve-existing-page briefs. Use when user says "content brief", "write a brief", "content outline", "blog brief", "service page brief", "brief for", "writing brief", "content plan", or "outline for".

SERP-based semantic topic clustering for content architecture planning. Groups keywords by actual Google SERP overlap (not text similarity), designs hub-and-spoke content clusters with internal link matrices, and generates interactive visualizations. Optionally executes content creation if claude-blog is installed. Use when user says "topic cluster", "content cluster", "semantic clustering", "pillar page", "hub and spoke", "content architecture", "keyword grouping", or "cluster plan".

Live SEO data via DataForSEO MCP server: SERP analysis, keyword research (volume, difficulty, intent, trends), backlink profiles, on-page analysis, competitor and content analysis, business listings, AI visibility (LLM mention tracking), and domain analytics. Requires DataForSEO extension installed. Use when user says "dataforseo", "live SERP", "keyword volume", "backlink data", "AI visibility check", or "real search data".

Run commands inside a devbox environment when a directory provides one. If a `devbox.json` exists in the current directory (or an ancestor/subdir root), devbox can supply tools and scripts the bare shell lacks — e.g. psql, python, gcloud, node. If a binary is provided by devbox, prefer it over the system binary.