novel-language-style
网文语言与文风光谱。当用户需要调整文风、选择叙述视角、运用修辞技法、植入玩梗、增强画面感时触发。覆盖白描/华丽/口语化/文艺/中二/翻译腔/新媒体风等文风类型,以及特写/慢镜头/蒙太奇/空镜头/长镜头等画面感技术。
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
网文语言与文风光谱。当用户需要调整文风、选择叙述视角、运用修辞技法、植入玩梗、增强画面感时触发。覆盖白描/华丽/口语化/文艺/中二/翻译腔/新媒体风等文风类型,以及特写/慢镜头/蒙太奇/空镜头/长镜头等画面感技术。
网文节奏与结构工程。当用户需要设计开篇、规划章节结构、编排高潮、设置断章钩子、控制字数节奏时触发。覆盖黄金三章/黄金一章模板、30+种断章钩子技法、多幕式结构、高潮编排与密度控制。
网文爽点模式大全与疲劳管理。当用户需要设计爽感、打脸桥段、逆袭高潮、金手指设定、装逼场景,或需要分析爽点心理机制、控制爽点密度、防止读者审美疲劳时触发。覆盖60+种爽点模式及其结构模板。
网文润色与去AI味。当用户需要润色AI生成的文本、去除AIGC痕迹、改写机械句式、增加口语化表达、注入个人风格时触发。覆盖去AI化核心策略、润色指令模板、风格增强技术、前后对比案例。
网文世界观与设定体系。当用户需要构建力量体系、设计地图与势力格局、建立经济体系、维护设定一致性、铺设悬念与谜题时触发。覆盖修仙/玄幻/科幻/都市等各类世界观模板与设定管理方法。
Personal US-equity options trading knowledge base with subcommands. `/trade setup` scaffolds a knowledge directory (substack, X, writedowns); `/trade import [file]` parses one raw file (PDF, screenshot, text) into structured YAML; `/trade report [tickers]` reads today's capital flow / 资金流向 (retail / 大单 / institutional proxy from options premium-flow); `/trade analysis` (or any unrecognized first word) runs the default analysis flow, auto-loading the knowledge directory. Use for trade analysis, earnings plays, money-flow / 流入流出 checks, or ticker mentions (e.g., "analyze APP"). Triggers on multi-leg options (Jade Lizard, bull put spread, iron condor, diagonal, calendar), IV / IV crush, LEAPS / stock replacement, dealer GEX / gamma / options flow, or VIX / vol hedging. 27 pitfalls, a gamma framework, case studies. TradingView + Funda for data; replies in Chinese. Check 3 axes: vega vs IVR (p19), delta vs thesis, asymmetry; bull-conviction >= 4 forbids Jade Lizard / IC / Calendar (p24).
Qualify leads against ICP with transparent scoring and clear next steps. Use when converting raw prospects into prioritized outreach queues.
Calculate weighted risk scores from specialist agent reports. Use when synthesizing multiple due diligence reports into an overall investment risk assessment.
Audit pasted chatbot output, AI-cleanup diffs, wiki drafts, Markdown/MDX/docs, and source-backed articles for generic AI fluff, LLM writing tells, weak audience model, lack of theory of mind, inflated significance, vague attribution, leaked tokens, placeholders, broken markup, fabricated or mismatched citations, and detector false positives. Use for requests like "AI writing audit", "check for AI slop", "find writing fluff", "does this sound like ChatGPT", "cleanup LLM tells", "make this less generic", "verify these citations", "detector flagged this", or text containing turn0search0, oaicite, oai_citation, contentReference, utm_source=chatgpt.com, malformed references, or wrong target-format markup.