skills

Transform any article into Ming-Qing eight-legged essay （八股文 / 經義文 / 明清制藝）—— a strict eight-section structure inherited from the imperial examination system. Eight sections required: 破題、承題、起講、入手、起股、 中股、後股、束股。 The four 股（起股／中股／後股／束股） MUST be paired parallel couplets （兩兩對仗、字數相當、虛實相對、平仄錯綜）。 Voice is 代聖人立言: speak as Confucius / Mencius / Zhu Xi would, never first-person 「我」。 Allusions to 四書五經 expected. Modern themes are welcome (KPI / 開會 / 健身 / 社群媒體）； the contrast between strict 八股 frame and modern subject is the point. Serious register only — do NOT mock the form. Primarily user-invoked via "/bagu-essay"; also triggers on "改寫成八股文", "八股文改寫", "經義文", "明清制藝", "破題承題", "起股中股後股束股", "代聖人立言", "科舉文", "Eight-legged essay", "rewrite as bagu".

Transform any modern article into a 中文十四行詩 (Chinese sonnet) — a strict 14-line metrical poem in modern Chinese, modelled after 馮至《十四行集》(1942) with formal scaffolding from the two canonical Western forms: Petrarchan (義式 8+6, 押 ABBAABBA CDECDE 或 CDCDCD, volta 在第 9 行) and Shakespearean (英式 4+4+4+2, 押 ABAB CDCD EFEF GG, volta 在第 9 或第 13 行， 結句 couplet 收). Output strictly obeys 14 lines; each line 10–12 字 (允許 9 或 13 緊急 伸縮);each line 4–5 頓 (意義停頓 / 語法停頓);押韻採同部寬韻 (現代漢 語通押) but the rhyme scheme structure of the chosen form is preserved; voice walks 馮至式沉思凝視 baseline, not romantic outpouring; volta (轉折點) must occur at the structural pivot;預設 Petrarchan,可指定 Shakespearean。Use this skill whenever the user asks for 十四行詩、 十四行集、馮至體、Petrarchan、Shakespearean、八六結構、四四四二、 中文格律新詩、商籁體、改寫成十四行、sonnet、Chinese sonnet, "rewrite as a sonnet", "sonnet form", or any request mentioning 十四行 / 馮至 / sonnet with a Chinese rewrite intent. Primarily user-invoked via "/chinese-sonnet-style".

Transform Chinese text into Chinglish (中式英語) — English that is heavily influenced by Chinese grammar, word order, and thought patterns, producing the characteristic "中式英文" style found on signs, menus, instructions, and everyday speech. Can also take English text and re-render it through a Chinese-thinking lens to produce Chinglish. Applies a 25-item checklist covering article errors, copula dropping, topic-comment structure, verb confusion, literal calques, tense flattening, and more. Useful for humor, creative writing, language education, or demonstrating L1 transfer patterns. Triggers on "/chinglish", "寫成中式英文", "翻成中式英語", "Chinglish化", "translate to chinglish", "make it chinglish", "chinglish this", "中式英文".

Transform any article into 「義大利麵就應該拌 42 號混凝土」體（concrete-42 pseudo-professional jargon-soup style）— Traditional Chinese, paragraph-style 論述外殼包裝跨領域名詞拼貼，每段強制至少 3 個跨領域具體名詞同時出現 （數學定理／工業規格／食物／歷史人物／物理化學概念／經濟術語），用偽因果 連接詞（因此／顯然／必然導致／由此可見／綜上所述）串成一本正經但前後不通 的論述，結論與開頭主題完全脫節。源自抖音「延邊刺客」卧龍鳳雛網路梗 (2024)。Primarily user-invoked via "/concrete-42"; also triggers on 「義大利麵」「42 號混凝土」「答非所問」「偽專業」「術語堆砌」「改寫成 42 號混凝土體」「偽專業話術」「答非所問風格」「義大利麵體」「rewrite as concrete-42」.

Review and rewrite Traditional Chinese text to remove Europeanized (歐化) writing patterns that arise from over-literal translation of Western sentence structures. Applies a 25-item checklist covering passive voice, abstract subjects, clause ordering, 的/們/性/地 overuse, calque prepositions, weak verbs, pronoun/tense overuse, long pre-modifiers, and more. Works on markdown files or inline text. Triggers on "/dewesternise", "去歐化", "太歐化了", "翻譯腔", "remove Europeanized patterns", "去翻譯腔", "改掉西化", "西化中文".

Transform text into Dongbei Mandarin （東北話） — the Northeast Chinese variant of Mandarin spoken across Heilongjiang, Jilin, and Liaoning, shaped by long contact with Manchu, Mongolian, Russian, and a strong oral-performance tradition （二人轉、 小品、《鄉村愛情》). Features the all-purpose verb 整， the intensifier 賊， signature lexicon （嘎哈/咋整/老鐵/妥妥的/杠杠的/必須的/可勁兒/瞅）, 老 X / 小 X prefixes, moderate 兒化， sentence-final particles （唄/咧/哈/嘎/嗯哪）, short punchy clauses, rhetorical questions, and onomatopoeia. Three intensity levels: Light (a few markers on a Mandarin backbone), Medium (clearly Dongbei-flavored conversational text), Heavy (《鄉村愛情》-style oral-performance register). Useful for creative writing, cultural appreciation, language education, or humor. Triggers on "/dongbei-mandarin", "寫成東北話", "東北話", "東北腔", "大碴子味", "二人轉腔", "趙本山體", "make it dongbei", "Northeast Chinese style", "賊 X", "嘎哈", "咋整", "老鐵".

Transform any article into Eileen Chang-style （張愛玲體） Chinese prose — Traditional Chinese, 400–1000 characters, 蒼涼基調 (the world quietly sinks, never erupts), 舊上海/戰時香港 mise-en-scène, female gaze on fabric and family power, 反高潮收尾 (cool off at emotional peak), 細節暴力 (one tiny detail carries an entire feeling), 古典-通俗夾雜 with low- saturation colours （暗黃、月白、灰青）。 Use this skill whenever the user asks for 張愛玲體，張派，上海蒼涼派，張愛玲式改寫， "rewrite as Eileen Chang", "Eileen Chang style", or anything mentioning 蒼涼、舊上海、反高潮、 女性凝視 with a Chinese rewrite intent — even if the wording is not exact. Primarily user-invoked via "/eileen-chang-style".

Rewrite any article into Feihua Literature (廢話文學) — the 2021–2022 Chinese internet meme genre that produces grammatically perfect, tonally earnest sentences carrying zero new information. Hallmarks: synonym substitution (「聽君一席話，如聽一席話」), tautology / contradiction (「這個西瓜很甜，因為它不苦」), and Q-keyword echo (「Q: 你為什麼遲到？ A: 因為我沒有準時。」). The text must read as if it were earnestly delivering truth while in fact saying nothing. Primarily user-invoked via 「/feihua-literature」; also triggers on 「改寫成廢話文學」、「廢話風格」、 「同義反覆」、「套套邏輯」、「聽君一席話如聽一席話」、「nonsense rewrite」、「tautology talk」.

Transform any article into Mid-Era Gulong (中後期古龍《多情劍客無情劍》 1969 之後) wuxia narrative — Traditional Chinese, 200–600 characters with extreme short-sentence rhythm (avg ≤12 chars), embedded aphorisms, mandatory contrast tension (殺手 vs 殺手 / 生 vs 死 / 動 vs 靜 / 年輕 vs 年老), no battle process. Designed as the duality counterpart of the future `jinyong-style` (章回招式派) — for that style use jinyong-style when it lands. Primarily user-invoked via "/gulong-style"; also triggers on "改寫成古龍", "古龍體", "古龍式武俠", "rewrite as Gulong wuxia".

Compress and distill any modern article into a Japanese 俳句 (haiku) in Traditional Chinese translation. Hybrid output modes: Light/Medium produce one (or two) standalone haiku from the most condensed moment of the source; Heavy produces a 3–7-haiku 連作 sequence in the manner of 松尾芭蕉《奧之 細道》 (prose 俳文 interleaving multiple haiku). Strictly observes the three pillars: 5-7-5 mora structure (in Chinese translation, two schools — 意境派 林文月／鄭清茂 with flexible 4–9 character lines preserving juxtaposition, vs. 嚴格派 鄭民欽 holding rigid 5-7-5 character counts), 季語 (kigo — spring 梅／櫻／蛙／燕, summer 蟬／螢／夕立／蓮, autumn 月／紅葉／秋風／鴈, winter 雪／枯野／寒椿／炭), and 切字 (kireji — Chinese equivalents of 「や」「かな」「けり」rendered as 「啊」「呀」「吧」「了」「——」). Output is full-width-punctuated Traditional Chinese verse drawing on classical Japanese aesthetics (juxtaposition over causation, no abstract emotion words, no closing summary). Use this skill whenever the user asks for 俳句、haiku、 寫俳句、改成俳句、5-7-5、季語、切字、松尾芭蕉、奧之細道、日本詩、俳句連作、 haikai、寫成日本詩. Primarily user-invoked via

Transform English text into Hanjified English — replacing words with CJK characters (Hanzi/Kanji/Hanja) while preserving English grammar structure. Uses a hybrid morphology where inflectional suffixes stay as Roman letters and derivational suffixes/prefixes become Hanzi. Produces three output versions: pure Hanjified, HTML Ruby annotation, and original text. Works on markdown files or inline text. Use this skill whenever the user mentions hanjify, hanjification, writing English in kanji or hanzi, mixing Chinese characters with English, creating an alternate writing system for English, or is curious about what English would look like written in CJK characters. Triggers on "/hanjify", "hanjify this", "convert to hanzi", "英語漢字化", "漢字化", "hanjify english", "english to hanzi", "write this in kanji", "英文漢字化".

Transform any article into a Chinese rendering of Hemingway-flavored prose （中譯海明威腔） — Traditional Chinese, 短句為主、動詞主導、拒絕修飾， 外部動作敘述，情緒壓在地表下，以冰山理論（七分水下、一分水上）承載強烈 情感。風格參照《老人與海》《白象似的群山》《雨中的貓》《一個乾淨明亮 的地方》《大二心河》《戰地春夢》《我們的時代》。歐化句法（「於是」「然 後」「他走進去。他坐下。他點了酒。」這類短句並列）在這個 skill 是 feature 不是 bug — 翻譯腔即是中譯海明威腔的指紋之一。Primarily user-invoked via "/hemingway-style"; also triggers on "改寫成海明威", "海明威體", "海明威腔", "冰山理論寫作", "極簡敘事", "rewrite as Hemingway style", "Hemingway iceberg".

Transform text into Hong Kong Chinese (港式中文) — a written register shaped by Cantonese substrate, English contact, and Hong Kong-specific social vocabulary. Features Hong Kong-specific terms (巴士/的士/士多/雪櫃), transliterations (荷里活/三文治/梳化), Cantonese lexicon (食飯/飲茶/睇/搞掂/啲/嘢), frequent English code-mixing (開 meeting / send email), AB/BA word-order flips (質素/私隱/擠擁), and — at Heavy intensity — optional full Cantonese-written features (係/唔/嘅/咗/佢/呢/嗰). Three intensity levels from light HK flavor (standard Chinese backbone) to heavy 港式粵語混合體. Useful for creative writing, cultural appreciation, language education, or humor. Triggers on "/hongkong-chinese", "寫成港式中文", "港式中文化", "翻成港式中文", "translate to hong kong chinese", "make it hong kong style", "港式書面語", "港味".

Remove AI-generated writing tics (grandiose wording, tricolon abuse, vague attribution, hollow parallel structures) and rewrite flagged passages in a more natural voice. Works on markdown files or inline text; checklist is tuned for Traditional Chinese but principles apply to any language. **Scope boundary**: humanize targets *AI-flavored tone*. If the issue is Europeanized sentence structure (翻譯腔 / 歐化) — passive voice, abstract subjects, 的/們/性/地 overuse, long pre-modifiers, calque prepositions — use `dewesternise` instead, which has a specific 25-item 歐化 checklist. Triggers on "/humanize", "make it sound human", "remove AI tone", "去 AI 味", "寫得更像人", "降低 AI 感" — but if the user says "翻譯腔" / "太歐化" / "去歐化", route to `dewesternise` first.

Transform text into 晶晶體 — a Taiwan colloquial register (起源於 2016 年 媒體名媛口語現象) characterised by a Chinese sentence frame sprinkled with unnecessary English single words or short phrases (amazing / busy / fashion / life style / nice / really 等),其炫耀感正來自「明明可以用中文卻用英文」。 Three intensity levels (Light 每 4–5 句 1 處 / Medium 每 2–3 句 1 處 / Heavy 每句 1–2 處)。Useful for stylistic experiments, satire of code-switching habits, creative writing, and language education. Triggers on "/jingjing-style"、「改寫成晶晶體」、「中英夾雜風格」、 「名媛體」、「台灣名媛體」、「晶晶體化」、「李晶晶式」、"jingjing", "rewrite as jingjing", "make it jingjing".

Transform any article into Mid-Era Jinyong (中期黃金期金庸 1957–1969, 《射鵰》《神鵰》《倚天》《天龍》《笑傲》流派) wuxia narrative — Traditional Chinese, 400–1200 characters with 章回式長句 (avg ≥18 chars), mandatory martial-art moves with names, embedded classical poetry, and historical anchoring (specific dynasty + place). Designed as the duality counterpart of `gulong-style` (短句留白派) — for that style use gulong-style. Excludes 《鹿鼎記》 (late-period anti-wuxia variant). Primarily user-invoked via "/jinyong-style"; also triggers on "改寫成金庸", "金庸體", "金庸式武俠", "rewrite as Jinyong wuxia".

Transform any article into a narrative-style Zen koan (敘事故事型禪宗公案) in the 白隱「是這樣嗎？」 tradition — Traditional Chinese, white-vernacular with light classical particles, 100–400 characters, no commentary appended. This is the narrative-story type, NOT the short Q&A koan (機鋒問答型 趙州狗子). Primarily user-invoked via "/koanify"; also triggers on explicit phrases like "改寫成公案", "做一則公案", "rewrite as a Zen koan".

Use this skill to rewrite articles, stories, or any text into the Chinese YouTube mystery-narration genre — the "未解之謎 / 都市傳說 / 失落古文明 / 神秘解說" voiceover style popularized by 老高與小茉 and similar channels. Trigger broadly whenever the user wants text reshaped to sound like a Chinese mystery/conspiracy/lost-civilization YouTube video: 老高體、老高與小茉風格、laogao style、Mr & Mrs Gao style、雙人解說 (narrator + reactor)、單人解說口播、未解之謎口播、都市傳說旁白、YouTube 神秘解說腔。Also trigger when the request mentions signature surface markers: 【震撼】【深挖】【神人】【顛覆認知】等情緒中括號標題、「巧合的是」「無獨有偶」「至今無法解釋」「你能想到嗎」、「大家好我是 XXX」開場、「訂閱按讚開小鈴鐺」結尾、賣關子節奏、跨文明跳躍關聯 (亞特蘭提斯/瑪雅/三星堆/諾查丹瑪斯). Trigger even when the source is academic, science-pop, or historical (金字塔、三星堆、考古、歷史) — converting serious content into this mystery style is the core use case. Also user-invoked via /laogao-style. Do NOT trigger for: TED talks, 廢話文學、知音 sob-story, travel vlogs, sincere academic writing, or genuine conspiracy/pseudoscience generation.

Transform any article into a 聊齋體 classical Chinese short tale (蒲松齡 《聊齋誌異》流派) — 200–800 character pure 文言 narrative with mandatory supernatural transposition (one element becomes 狐/鬼/妖/精/神/異獸/物精), 史傳式 opening, and a conditional 「異史氏曰」 commentary if the source carries satire or moral tone. Primarily user-invoked via "/liaozhai-tale"; also triggers on "改寫成聊齋", "寫成聊齋體", "蒲松齡體", "志怪短篇", "rewrite as a Pu Songling tale".

Transform any article into 魯迅體（早期白話雜文）—— a 1920–30s vernacular voice fusing 文白夾雜 (early baihua spine with classical function-words 然而／便／罷了／也罷／未免／實乃 sprinkled in)， 反諷距離 (the narrator stands at the scene yet outside it, neither endorsing nor mocking)，標誌虛詞密集（然而、便、罷了、未免、實在、想來、 只是、倒是、至於、究竟），「我」字第一人稱抒情主體偶現，短段落為主 (50–150 字），破折號連接思考停頓，結尾不下定論（留問號／留靜默／留動作）。 Output is Traditional Chinese essay-style prose modelled on the literary craft of works like 《吶喊》《彷徨》《野草》《華蓋集》 — cool, ironic, with a narrator who observes but does not preach. Strictly a literary craft homage, not a political stance reproduction. Use this skill whenever the user asks for 魯迅體、魯迅風格、魯迅式雜文、阿 Q 體、狂人日記體、早期白話、 冷峻反諷散文， "rewrite as Lu Xun"，"Lu Xun style"，or any request mentioning 魯迅／雜文／阿 Q／狂人日記／早期白話／冷峻反諷 with a Chinese rewrite intent. Primarily user-invoked via "/lu-xun-style".

Transform text into Mainland China Mandarin （中國大陸普通話） — the everyday spoken and media register of the People's Republic of China. Features PRC-specific everyday vocabulary （視頻/質量/出租車/公交/軟件/互聯網/視 頻/屏幕/鼠標）, administrative-life terms （戶口/社保/落戶/北漂/公積金）, social-platform terms （微信/朋友圈/微博/熱搜/B站/彈幕/抖音/小紅書/拼多 多/美團）, and 2020-2025 internet slang （內卷/躺平/yyds/破防/絕絕子/家人 們誰懂啊/友友們/666/拿捏/鴿了/翻車/emo 了/蚌埠住了/citycity/偷感很重 /草台班子）. Three intensity levels from light vocabulary swap to heavy 抖音/B站 caption/弹幕 style. NOT party-state bureaucratese (use prc-bureaucratese for that), NOT a sub-dialect (use dongbei-mandarin / sichuan-mandarin / shanghainese for those). Useful for creative writing, cultural understanding, language education, or humor. Triggers on "/mainland-mandarin", "寫成大陸普通話", "改成中國大陸中文", "翻成大陸普通話", "中國大陸風格", "簡體字風", "微博體", "抖音體", "B 站體", "make it mainland mandarin", "PRC mandarin", "中國風中文", "內卷", "躺平", "yyds", "家人們誰懂啊".

Rewrite an article through a postmodern lens — events stay intact, but the narrative's interior (its master story, its narrator's authority, its assumed binaries, its claim to be "the" version) gets re-narrated so the article looks at itself with suspicion: which big story is smuggling itself in, who gets to say it, what other version was edited out, and what stays unsayable. This is a **lens** skill, not a style skill: surface language need not change shape, but the *interpretive frame* does. Triggers on "/postmodern-lens", "後現代重寫", "用後現代 改寫", "postmodern rewrite", "解構視角", "解構式改寫", "元敘事懷疑", "不可靠敘事", "戲仿", "互文", "Derrida 風格", "Foucault 視角", "Lyotard 視角", "Baudrillard 改寫", "Jameson 改寫", "作者之死". Use this skill whenever the user wants the article retold so that the grand story it leans on starts cracking, a competing version surfaces, the narrator stops trusting itself, or the "real" event reveals itself as already a copy — even if the request wording isn't an exact match.

Transform text into PRC party-state bureaucratese (中共公文體 / 黨政公文體) — the institutional writing style of Mainland China's Party and government documents, news bulletins, and official speeches. Features high-frequency action verbs (落實/加強/推進/深化), adverb-verb stacks (紮實推進/深入貫徹/全面落實), four-character parallel phrases (不忘初心、牢記使命), numerical political slogans (三個務必/四個全面/五位一體), New-Era ideological vocabulary (新時代/新發展格局/ 中國式現代化/偉大復興), and template openings/closings (以習近平新時代中國特色 社會主義思想為指導... / 奮力譜寫新篇章). Three intensity levels from routine administrative notices up to full 黨八股 Party editorial style. Useful for creative writing, satire, historical simulation, translation comparison, or teaching rhetorical analysis. Triggers on "/prc-bureaucratese", "寫成公文體", "改成中共公文體", "黨政公文化", "黨八股化", "make it chinese official style", "PRC official style", "官樣文章".

Rewrite an article through a psychoanalytic lens — events stay intact, but the narrative's interior (motives, meanings, narrator's asides) is re-narrated using Freudian / Lacanian vocabulary so that the article itself looks at its own subject through the analytic ear. This is a **lens** skill, not a style skill: the surface language need not change shape, but the *interpretive frame* does. Triggers on "/psychoanalytic-lens", "精神分析重寫", "用精神分析改寫", "Freudian rewrite", "Lacanian narrative", "潛意識視角", "拉康式改寫", "佛洛伊德角度". Use this skill whenever the user wants the article retold so that desire / repression / the Oedipal structure / the gaze of the Other becomes the thread of meaning, even if the request wording isn't an exact match.

Transform any modern article into a 台灣 PTT 鄉民體 BBS post —— complete with a category-tagged title (例如 [問卦]／[新聞]／[爆卦]／[心得]／[討論] ／[黑特]／[Re: 問卦]), a colloquial 鄉民 body that opens with 自介起手 式（肥宅我／弟弟我／妹妹我）, drops in 鄉民詞 (484／笑死／ㄎㄎ／中肯／ zzz／RR／QQ／3Q／喇／啦／齁), and ends with a 求支援／求戰／文長慎入 closing line, followed by a stack of 5–15 simulated 推文／噓文／→ replies written by anonymized fake IDs (rookie123／fatdog2024／pttuser5566／ taipei_anon／kindstranger). Output is a complete BBS-formatted post in Traditional Chinese ready to read like a real PTT thread, but with all real PTT IDs, real public figures, and real political incidents scrubbed — irony targets are abstract universals (鄉民集體心理／月經文 循環／釣魚與被釣／業配偵測), never specific persons or groups. Use this skill whenever the user asks for PTT 體、鄉民體、BBS 體、八卦版口吻、 推文模擬、PTT 貼文、肥宅體, "rewrite as PTT post"、"PTT style"、 "PTT BBS"、"鄉民風格", or any request mentioning PTT／鄉民／八卦版／ 推文／噓文／肥宅／BBS with a Chinese rewrite intent. Primarily user-invoked via "/ptt-bbs-style".

Transform any article into a Mid-Era Qiongyao (中期瓊瑤,《在水一方》 《一簾幽夢》流派) romance — 300–800 character modern-vernacular romance with a mandatory love axis, a structural obstacle, high emotional density, optional poetry inlay (max 1–2 at peak moments), and an ending that preserves the ache. Use only for romance narrative — the grandiose framing, tricolons, and exclamations are signature features of the genre but become AI-flavored noise outside of it. Primarily user-invoked via "/qiongyao-style"; also triggers on "改寫成瓊瑤", "寫成瓊瑤體", "瓊瑤式愛情", "rewrite as Qiongyao romance".

Transform text into classical-era Republic of China bureaucratese (中華民國 1960s-80s 公文體) — the distinctive semi-classical administrative writing style of the ROC government before the gradual 白話化 of the 1990s. Features single-character classical vocabulary (之/於/以/係/為/俾/爰), archaic connectives (茲/惟/嗣/俟/頃/殆/甫), hierarchical honorific terms (鈞/貴/本/職/台端/鈞長), fixed procedural formulas (查照/鑒核/核備/照辦/奉悉/敬悉/業經/迭經), and standard closing conventions (此致 XX 鈞鑒 / 為荷 / 特此函達). Three intensity levels from light administrative formality up to dense electrical-telegram-era concision. Useful for creative writing, historical simulation, satire, generation of period-appropriate bureaucratic text, or teaching rhetorical analysis. Triggers on "/roc-bureaucratese-classic", "寫成民國公文體", "改成中華民國公文", "舊式公文化", "民國公文化", "make it roc official style", "ROC classic bureaucratese", "仰即/著即 公文體".

Transform any article into Mid-20th-century Zhu-Shenghao-style Chinese translation of Shakespearean tragedy （朱生豪式中譯莎劇腔） — Traditional Chinese, 300–1000 characters, half-classical-half-vernacular voice with dense metaphors (natural imagery + abstract concepts), expressive exclamatory rhythm, and a tragic-conflict spine. Primarily targets the four great tragedies (Hamlet / King Lear / Othello / Macbeth). Drama formatting (character-prefixed dialogue, stage directions, asides) is Soft-rule: required for outputs ≥500 chars, optional for shorter prose-style outputs that retain the dramatic register. Primarily user-invoked via "/shakespeare-style"; also triggers on "改寫成莎劇", "莎翁腔", "朱生豪式", "rewrite as Shakespearean tragedy".

Transform text into Shanghainese （上海話 / 滬語） — the Wu Chinese variety spoken in Shanghai, belonging to the Taihu subgroup （太湖片） of Wu （吳語）. Features Wu pronouns （儂/阿拉/伊/伊拉）, Wu negation （弗/勿/覅）, sentence-final particles （呃/嘞/伐/哦呦）, Wu adverbs （蠻/老/嘎）, signature lexicon （結棍/霞氣/嗲/戇/洋盤/淘漿糊/軋鬧猛/噶三胡）, cultural vocabulary （弄堂/石庫門/阿婆/爺叔/小囡）, and 海派 register（派頭/有腔調）. Three intensity levels from light Wu-flavored Mandarin (sprinkled markers) up to heavy 滬語書寫 (in the manner of 金宇澄《繁花》). Useful for creative writing, cultural appreciation, language education, or dialogue craft. Triggers on "/shanghainese", "寫成上海話", "滬語化", "翻成上海話", "translate to shanghainese", "make it shanghainese", "上海話", "滬語", "吳語", "儂", "阿拉", "海派", "周立波", "繁花".

Transform any article into 朱生豪式中譯維多利亞偵探小說腔——Traditional Chinese rendering of late-19th-century Conan Doyle detective fiction (Sherlock Holmes canon). 第一人稱華生回憶體開場 + 福爾摩斯演繹獨白 + 案件三幕（委託登門→現場勘察→演繹揭曉）+ 維多利亞物件詞彙（煤氣燈／懷錶／菸斗／馬車／哈德森太太／蘇格蘭場）+ 中譯翻譯腔為 feature。世界觀層走西洋通名（倫敦／貝克街／鄉間別莊／ 火車車廂），不可換為中華具體專名。風格參照《血字的研究》《四簽名》 《冒險史》《回憶錄》。Primarily user-invoked via "/sherlock-holmes-style"; also triggers on "改寫成福爾摩斯", "福爾摩斯體", "華生視角", "演繹推理小說腔", "中譯維多利亞偵探", "貝克街 221B", "rewrite as Sherlock Holmes", "Holmes-style detective fiction".

Transform text into Sichuan Mandarin （四川話 / 川渝話） — a Southwestern Mandarin variety of the 成渝片 zone covering Sichuan and Chongqing, marked by light 「兒」化，莫/莫得 negation, abundant sentence-final particles （嘛/噻/嘞/哈/撒）, signature lexicon （巴適/安逸/莫得/搞快點/龜兒/撇脫/擺龍門陣/牙尖/假打/鬼火冒）, blunt 江湖 humor, and a self-mocking 川劇丑角 voice. Three intensity levels from light Sichuan flavor on a Putonghua backbone to heavy 張麻子-style 江湖 cadence. Useful for creative writing, cultural appreciation, language education, or humor. Triggers on "/sichuan-mandarin", "寫成四川話", "川話化", "翻成川話", "重慶話", "translate to sichuan mandarin", "make it sichuan", "巴適", "龜兒", "西南官話", "火鍋英雄風", "讓子彈飛口吻".

Transform text into Singapore Mandarin (新加坡華語) — the Mandarin variety used in Singapore, shaped by Hokkien/Malay/English contact, with its own administrative vocabulary (組屋/德士/樂齡/客工/新生水/易通卡), phonological-spoken carryovers (幾時/不懂/做工/青菜/頭家/燒), Malay loanwords (甘榜/巴剎/沙爹/atas/bodoh), word-order flips (先後置: 吃先), special classifiers (一粒/一間), and distinctive numerical conventions (99 千 = 99,000). Three intensity levels from formal Lianhe Zaobao register down to heavy code-mixed social-media 華語. Distinct from Singlish (English-based creole) — this skill's output keeps a Mandarin grammatical backbone. Useful for creative writing, cultural appreciation, language education, or humor. Triggers on "/singapore-mandarin", "寫成新加坡華語", "新加坡華語化", "翻成新加坡華語", "translate to singapore mandarin", "make it singapore mandarin", "新加坡中文", "SG 華語", "Huayu".

Transform text into Singlish (Colloquial Singaporean English) — an English-based creole shaped by Hokkien, Malay, Cantonese, Mandarin, and Tamil. Features discourse particles (lah, lor, meh, hor, leh), topic-comment structure, zero copula, optional tense/plural marking, "got" for existence, "kena" passive, verb reduplication, and multilingual loanwords. Applies a 27-item checklist covering grammar, discourse particles, vocabulary, and structure. Useful for creative writing, cultural appreciation, language education, or humor. Triggers on "/singlish", "寫成新加坡英語", "translate to singlish", "make it singlish", "singlish this", "新加坡式英文", "write in singlish".

Transform any modern article into a 宋詞 (Song-dynasty 詞) — a fully metrical ci poem fitted to one of five canonical 詞牌 (tune-titles): 水調歌頭 (95 字 long-medium，宏大思念仕途中秋)、念奴嬌 (100 字 long, 仄韻 throughout，懷古 豪邁史詠)、虞美人 (56 字 small lyric，平仄韻交替，悲愴失去短嘆)、如夢令 (33 字 single-strain 小令，瞬間印象戲劇感)、西江月 (50 字 mid-tier，平韻 + 末仄叶，田園議論旁觀). Output strictly obeys character count, line-length sequence, rhyme positions (平韻 / 仄韻 / 平仄交替) and 平仄譜 of the chosen tune; faction tag [豪放派] or [婉約派] declared and consistent; classical imagery only (月 / 風 / 江 / 樓 / 酒 / 笛 / 燕 / 梅), modern vocabulary (電腦 / 飛機 / 咖啡 / 手機) categorically banned. Use this skill whenever the user asks for 宋詞、詞牌、填詞、水調歌頭、念奴嬌、虞美人、如夢令、 西江月、豪放派、婉約派、改寫成詞、Song ci poem, "fill a ci to this tune", or any request mentioning 宋詞 / 詞牌 / 填詞 with a rewrite intent. Primarily user-invoked via "/song-ci-style".

Transform text into Taiwan Mandarin (台灣國語) — a sociolect of Mandarin shaped by prolonged contact with Taiwanese Hokkien, featuring Hokkien/Japanese loanwords, phonologically-motivated respellings (偶/粉/素/降), sentence-final particles (啦/喔/齁/耶), and BBS-era net culture spellings (注音文 such as ㄉ/ㄇ/ㄅ/3Q). Applies a checklist covering grammar, particles, vocabulary, and structure, with three intensity levels from light colloquial chat to heavy 2000s netizen style. Useful for creative writing, cultural appreciation, language education, or humor. Triggers on "/taiwan-mandarin", "寫成台灣國語", "台灣國語化", "翻成台灣國語", "translate to taiwan mandarin", "make it taiwan mandarin", "台灣腔", "台式中文".

Transform any modern article into a 唐詩 — Tang-style classical Chinese regulated poem chosen from four canonical formats: 五言絕句 (5-char quatrain, 20 chars), 七言絕句 (7-char quatrain, 28 chars), 五言律詩 (5-char regulated, 40 chars with parallelism in middle two couplets), and 七言律詩 (7-char regulated, 56 chars with parallelism). Output strictly observes 平仄 tonal patterns (平起／仄起 schemata per format), 押韻 rhyme rules (平水韻 — same rhyme group, 平聲 only, on lines 2/4 of jueju and lines 2/4/6/8 of lüshi), 對仗 antithetical parallelism for the 頷聯 and 頸聯 of 律詩, and the 「一三五不論、二 四六分明」 mnemonic with its caveats (孤平、三仄尾、三平尾 to be avoided or rescued via 拗救). Output is full-width-punctuated Traditional Chinese verse drawing imagery from the classical inventory (山／月／江／雲／風／雪／鳥／馬／酒). Use this skill whenever the user asks for 唐詩、絕句、律詩、五言、七言、平仄、對 仗、押韻、平水韻、寫成唐詩、寫一首詩、改寫成詩、改寫成絕句、改寫 成律詩、tang poem、Chinese regulated verse、quatrain、jueju、lüshi. Primarily user-invoked via "/tang-poem-style".

Transform any article into 凡爾賽文學（Versailles Literature, 凡學）— the Chinese social-media humblebrag genre popularised in 2020 by Weibo user 蒙淇淇77（綽號出自《凡爾賽玫瑰》漫畫對 Marie Antoinette 凡爾賽宮 生活的描繪）. Output is Traditional Chinese, 200–500 字, structured as the canonical three-part formula: 抱怨開端 + 細節暴擊 + 反問收尾. Surface complaint must completely envelop the underlying boast — readers should finish thinking "wait, did she just mention Birkin?" rather than "she is showing off." Triggers on "/versailles-literature", "改寫成 凡爾賽", "凡爾賽文學", "假裝抱怨真炫耀", "蒙淇淇體", "rewrite as Versailles literature", "humblebrag this", "Versailles flex".

Rewrite modern Chinese text into Tang-Song classical prose style (唐宋古文體), emulating the essay voice of 韓愈, 柳宗元, 歐陽修, and 蘇軾. Applies a 20-item checklist covering classical function words, single-character verbs, thesis-driven structure, varied rhythm, literary allusion, and register markers. Works on markdown files or inline text. Triggers on "/wenyan-guwen", "寫成古文", "寫成文言文", "用文言文寫", "古文體", "唐宋風格", "韓愈體", "蘇軾體", "classical Chinese prose", "Tang-Song style".

Rewrite modern Chinese text into Han-Wei historical narrative prose style (漢魏史傳體), emulating the biographical voice of 司馬遷《史記》, 班固《漢書》, and 陳壽《三國志》. Applies a 20-item checklist covering biographical formula, chronological narration, dialogue as characterization, precise action verbs, implicit moral judgment, and historian's commentary. Works on markdown files or inline text. Triggers on "/wenyan-hanwei", "史傳體", "史記風格", "漢書體", "三國志體", "historical narrative", "biographical prose", "Han-Wei style".

Rewrite modern Chinese text into Song-Ming-Qing vernacular fiction style (話本小說體 / 章回小說體), emulating the storyteller's voice of 水滸傳, 三國演義, 紅樓夢, and 金瓶梅. Applies a 20-item checklist covering storyteller's frame, classical-vernacular code-switching, formulaic transitions, embedded poetry, and chapter-return structure. Works on markdown files or inline text. Triggers on "/wenyan-huaben", "話本體", "說書體", "水滸傳風格", "三國演義體", "章回小說", "vernacular fiction", "storyteller style".