ch-skills

This skill should be used when the user asks '最近有什么催化剂', '这周有什么重要事件', '财报什么时候出', or during daily morning checks. Maintains a forward-looking catalyst calendar (earnings, conferences, policy events) linked to the stocks you track, consolidated in a catalysts-calendar.md file.

This skill should be used when the user asks to '查一下XX的财务数据', '这只股票估值多少', '找一下XX ETF', '对比一下同行', 'ETF日线行情', or when any analysis task needs financial statements, valuation metrics, ETF listings, or ETF daily OHLCV data. Fetches stock financials (revenue, profit, margins, ROE, PE/PB) and ETF data via Tushare Pro (primary) and AKShare (fallback + ETFs).

This skill should be used when the user asks to '梳理一下XX产业链', '这个行业的上下游是什么', '哪个环节弹性最大', or when starting research on a new industry theme. Builds and maintains persistent industry-chain maps (upstream/midstream/downstream, key companies, market share, investment-elasticity ranking). Artifact-focused; complements the process-focused industry-chain-research skill.

This skill should be used during daily research scanning, or when the user asks '最近有什么新消息', '扫描一下XX的最新动态', '帮我看看雪球上在聊什么'. Scans Xueqiu, Eastmoney, 10jqka, and web search for investment-related news filtered by the industry-chain keywords you track. Outputs HIGH/MEDIUM findings only — signal, not noise.

This skill should be used when the user asks to '分析一下XX股票', '研究一下XX', '这只股票能不能买', or when a research task identifies a stock candidate for deep analysis. Produces structured research notes covering 5 dimensions: business model, financials, valuation, catalysts, and risks — with a clear buy/sell/hold thesis and falsification conditions.

A股/美股行情数据获取工具集 — 交易日检查、指数/板块/涨停池/北向资金数据拉取，基于 AKShare（免费、无需 token）。Use when the user needs free A-share/US market snapshots: trading-day checks, index/sector/limit-up-pool/northbound data, or per-stock daily OHLCV.

This skill should be used when the user asks '现在能买吗', '技术面怎么样', '支撑位在哪', '量能如何', or after stock-analyzer confirms a fundamental thesis and entry timing is needed. Provides MA trend, support/resistance levels, and volume analysis as a SECONDARY timing tool — never the primary decision basis.

This skill should be used when the user asks '查一下XX的行情', '拉一下财务数据', '估值数据', 'PE/PB多少', '股东变化', '业绩预告', or when any analysis/research task needs A-share market data, financial statements, valuation metrics, or shareholder data. Tushare Pro is the PRIMARY structured data source — more stable and comprehensive than AKShare. Requires a TUSHARE_TOKEN env var (your own Tushare Pro token).

This skill should be used when the user asks '这只股票贵不贵', '估值合理吗', '目标价多少', '跟同行比怎么样', or during a stock-analyzer valuation step. Calculates PE/PB/PS historical percentiles, builds peer-comparison tables, and derives target prices via PE-based or PB-based methods. Quantitative/relative valuation — distinct from the DCF-style intrinsic-value-analysis skill.

Maintain a local, incrementally-updated library of WeChat Official Account (公众号) articles as Markdown + a SQLite index, and pull new posts on demand. Use when the user wants to subscribe to 公众号, fetch/update 公众号 articles, build a searchable feed of specific accounts, or says "update my feeds" / "拉一下公众号" / "增量更新公众号文章". Bundles a self-contained Bun scraper (tool/) that drives a logged-in Chrome via a tiny CDP proxy.

Analyze a company through three layers — story, logic, judgment — and deliver a narrative-driven report with a clear take. Use whenever the user asks to research, analyze, or deeply understand a specific company, whether the motivation is investing, career, competitive intel, partnership, or curiosity. Trigger even when the user says "研究 XX 公司", "深度分析 XX", "带我看懂 XX 这家公司", or names a company alongside investment/career/competition context without explicitly saying "analyze". NOT for quick fact lookup, real-time stock quotes, or broad multi-company surveys.

产业链研究：从宏观趋势拆解产业链、定位瓶颈环节、找到具体标的、交叉验证风险。核心理念——不问AI"买什么"，在结构化框架里让AI做产业链研究员。Use when user says 产业链分析, 拆产业链, 产业链研究, 瓶颈分析, 景气度投资, supply chain analysis, industry chain, "帮我拆一下XX产业链", "XX赛道有哪些机会", or wants to systematically research an industry theme for A-share investing.

用老唐(唐朝)估值法分析一家企业的内在价值。当用户要分析/估算某公司内在价值、判断买卖点、给某只股票估值、做价值投资研究、问"这家公司值多少钱/现在能不能买/什么价位卖"时触发。以巴菲特/格雷厄姆DCF思想的工程化简化(老唐估值法)为骨架：三大前提排雷 → 把好公司当债券 → 三年后合理估值打五折买入。

Rigorous problem-analysis methodology for any substantive decision — housing, education, medical, career, investment, tech/architecture, debugging, research, life choices. Governs HOW Claude works (process), not the output format. Forces deep investigation (specific numbers/cases, not vibes), stakeholder mapping, main-contradiction + transition analysis, staged strategy, worst-case wargaming, concentrated main attack, and concrete next-step actions. Triggers — /mma slash command, 用马哲/毛选/矛盾分析/实事求是/一分为二 keywords, or proactively for any weighty judgment task.

把用户口语化/模糊的任务描述转成一段高质量、可直接复制到其他 AI 会话使用的 prompt。**必须用此 skill**当用户说「帮我优化 prompt」「这段任务怎么问 AI 更好」「写一个 prompt 我发给 GPT/Claude」「帮我写 prompt」「把这个需求包装成 prompt」「meta prompt」，或者显式调用 `/mp`。默认产出 Claude 友好的 XML 结构化 prompt，当用户指定目标是 GPT/ChatGPT/OpenAI 时切换为 markdown 分节格式。**不要在当前会话执行产出的 prompt，只输出 prompt 文本给用户复制**。