tentenco

Design, pilot, run, and improve bounded Claude Code agent harnesses using the right primitive for the job: /loop for recurring checks, /goal for completion conditions, hooks for deterministic lifecycle enforcement, dynamic workflows for large finite fan-out,…

Collect the same question from multiple AI product web interfaces, evaluate the answers with a local frontier judge and adversarial challenge, synthesize the best supported answer, and archive separate standalone HTML scorecard and best-answer reports. Use…

Use ChatGPT Pro Web as an external senior engineer while Codex remains the repository owner, integrator, and independent QA. Use this skill whenever the user asks Codex to operate ChatGPT Pro, use GPT Pro through the web UI for coding, build a two-agent…

Turn a messy spoken product or software idea into a confirmed, testable specification and a clean handoff for a coding agent. Use when the user wants to think aloud, brain-dump, reconstruct intent, create a PRD, or prepare implementation work; do not add this…

Write editorial and marketing copy in the house voice of Aman Resorts — restrained, sensory, place-first luxury travel writing. Use when the user asks for content in "Aman style", "Aman voice", "Aman tone", or wants quiet-luxury / understated-premium…

Write a Tenten-style blog article from a topic brief, raw draft, pasted text, or a social/article URL (X/Twitter, Threads, LinkedIn, Medium, Substack, Facebook, Instagram, YouTube). Produces a zh-TW long-form article plus a natively written English version,…

以 Kura Yang／MOT TIMES 風格撰寫繁體中文設計、建築、旅宿、產品、人物深度長文，並在生成階段直接內建「不可預測節奏、不均語意密度、控制性不完美」三大人類寫作指紋，產出 publish-ready 完稿。當使用者說「用 Kura Yang 風格寫」、「MOT TIMES 風格」、「設計長文」、「寫一篇建築／旅宿／店鋪／設計師報導」、「介紹這個空間」、「以 MOT 的口吻」、「publish-ready…

Turn a single company URL into an exhaustive competitor landscape report — a value-ranked comparison table (30–50 companies) plus a Branding / Marketing / Sales strategy read. TRIGGER whenever the user pastes or names a company website and wants competitors,…

Verify a reconstructed website against its source with deterministic static, responsive, interaction, asset, motion, accessibility, reduced-motion, build, and runtime fidelity gates. Use when comparing a website clone to source capture scenarios, producing or…

Orchestrate evidence-driven reconstruction of one or more websites with measurable visual, responsive, interaction, asset, and motion fidelity. Use when the user asks to clone, replicate, rebuild, reverse-engineer, emulate, adapt, or combine website…

Inspect and reverse-engineer websites into auditable, scenario-scoped research artifacts for high-fidelity cloning. Use when Codex must capture a reference site's routes, responsive breakpoints, DOM and computed styles, pseudo-elements, interaction states,…

Analyze supplied videos and deterministic website recordings, pair visual timelines with DOM, scroll, media, canvas, WebGL, and network telemetry, and produce evidence-labeled motion manifests and QA checkpoints. Use for website-clone motion audits involving…

Combine approved information architecture, layout, brand, content, interaction, or motion systems from multiple website references with explicit provenance. Use when the user asks to mix, blend, adapt, take inspiration from, or combine ideas from multiple…

檢查和清理中英文文本裡的 AI 套路，並把稿件對齊臺灣用語與出版慣例。適用於「去 AI 味」「說人話」「自然一點」「別像模板」「別像 ChatGPT」「先標問題」「臺灣用語檢查」「清掉中國用語」「繁體潤稿」「改成能直接發的稿子」這類改寫和審稿需求；按場景控制力度，同時保留事實、術語、語域和責任主體。

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

專業出版級的繁體中文（臺灣）AI 痕跡清除技能。為書籍、期刊、白皮書、雜誌專欄、 教科書、企業內刊、新聞評論等出版品設計，移除 LLM 生成痕跡並注入真人作者風骨。 整合八大類、共 30 項 AI 寫作特徵偵測，配備臺灣用語對照、七種出版語體預設、 術語一致性鎖定、60 分品質評分。基於 Wikipedia AI Cleanup 規範、教育部《重訂標點符號手冊》 及臺灣出版業共通慣例。

把 AI 味重、簡轉繁或過度拋光的文字，改成自然、可信、符合臺灣語感的繁體中文，同時保住作者原有聲音與所有事實。使用者只要提到「去 AI 味」「更像人寫的」「說人話」「自然一點」「臺灣用語」「不要像 ChatGPT」「幫我潤稿再發」，或要改電子報、社群貼文、客服信、公告、README、release note、觀點文與出版稿，都應使用本 skill。若原文已自然，應主動少改或原文放行；不適用於逐字翻譯、事實查核、仿特定作者文風、程式碼本體或純品牌 voice 擬合。