1254 hand-tested AI prompts across image, video, and music — each with full context, variables, and a sample output. Content is authored in Traditional Chinese; the UI here is English.
Five quantifiable techniques from an AI engineer's hundreds of hours testing across GPT-4, Claude, and Gemini: CoT scaffolding, persona + goal + anti-goal, XML being 28% more accurate than markdown, negative examples outperforming positive ones, and prompt chaining beating the mega-prompt.
Three patterns shared by the HackAPrompt 2.0 champion: frame the task as an audit, make the abstraction level explicit, and stage the context like production. They work on Claude, GPT, and Gemini alike.
Mitchell Hashimoto's "Agent = Model + Harness" framework. The reason 88% of enterprise AI agents never reach prod isn't the prompt — it's the missing deterministic orchestration layer. Four CS primitives you can't skip: state machine, idempotency, DAG, DLQ.
Scores every claim on three axes (A: sources / B: counterevidence / C: completeness), plus a 4-tier source hierarchy, adversarial self-poking, and 4 output modes.
Stop picking a role for every decision (financial planner / career coach / relationship coach) — one universal prompt, four steps. The regret line is the core — it forces the model from "it depends" to "actually do this."
The pain of writing a CV isn't the layout — it's listing duties instead of achievements, then having AI pile on and turn you into a "dynamic team player." This ruleset forbids AI from drafting anything until it has your evidence and positioning, and walks you through one question at a time.
Before you log off, ramble into your phone mic for 2 minutes, hand it to Claude, and get back a sorted list: first thing tomorrow morning + ranked to-dos + waiting-on + can-defer. Auto-detects daily vs. weekly mode.
The author wrote this after 30% of their heated replies made them wince the next day — costing a few deals and a friendship. The trick: don't let AI rewrite it, let it show you what the calm version would look like. Once you see it, you usually can't go back to the original.
Instead of telling AI to write code directly, have it translate a vague goal into an executable prompt structure first, then use that structure to drive code generation. Phase 1 Intent → Phase 2 Structuring → Phase 3 Tool-Level → Phase 4 Implementation.
Upload the repo and Claude returns an architectural map, the top 5 fixes to prioritize, and the file paths to back them up.
給 CEO / BoD / VC 的一頁決策備忘錄。把你 30 頁的分析壓縮成一頁能在會議前 5 分鐘看完的清晰文件。Amazon PRFAQ / McKinsey SCQA 風格。
Product Requirements Document 第一版。3 句話問題陳述 → 5 個 user stories → API contract → 成功指標。工程師看了可以直接開工的 spec。
給 Claude 30 個 SKU 的基本資料(名稱、品類、賣點、材質),一次產出 30 組「標題 + 賣場摘要 + 3 個 bullet feature + 詳情段落」— 小品牌上架效率 10 倍。
給目標職缺 JD + 你的 5 個實際工作事件,Claude 產出 5 組 STAR 格式的面試回答 — 面試前一晚準備、腦袋裡預演。
給 Claude 你過去 90 天的郵件 / 會議筆記 / Slack 訊息摘要,它產出一份「季度自我檢討」— 成就、失敗、學習、下季目標。績效考核前 30 分鐘搞定。
客訴信進來、你 5 分鐘要回覆。Claude 用「同理 → 擔責 → 具體補償 → 預防」四步驟框架產出回信 — 客戶覺得被聽見、不會升級到 Google 1 星。
給 Claude 來賓 bio + 節目主題 + 你想挖的角度,它產出完整 60 分鐘訪談提綱 — 15 個主問題 + 預備追問 + 開場 / 結尾設計。
你有一份通用履歷、同時想投 10 間公司。Claude 幫你針對每家 JD 重新編排重點,不變事實。
不是「幫我看這段 code」這種類似小朝六。一個動作拿到 PR 動規模、安全、性能、可讀性四個面向的評評。
面對恃怒客戶、投訴、退款要求。Claude 幫你寫不卑不亢、有同理心、但不隨便吐錢的回信。
自由工作者 / 創業者 / PM 適用。用問答法而不是填表法,逼出真實反省。
給 AI 你的爛 prompt,讓它變成結構化的進階 prompt + 告訴你為什麼。
給產品經理、創業者。把多份訪談的雜訊去掉,萃取共通模式與痛點。
把冗長的會議逐字稿濃縮成三個層次:決議、行動項、懸而未決。