Your AI feed says everything happened. It never says what mattered. This Agent searches live across model releases, funding, regulation, research and tooling, then grades each item by signal strength and names who it hits. Every claim carries a source link. Primary sources beat aggregator rewrites. At most two items a day can be graded high signal, and most days that is zero — it says so, instead of inflating a quiet day into a crisis. Ends with what to do this week.
Tracks official monthly revenue disclosures for 50 Taiwan AI compute and server supply-chain companies across systems, semiconductors and ASIC, memory, PCB and interconnect, power, thermal, and networking. Reports revenue, YoY growth, historical percentile, effective sample size, issuer statements, reporting period, and official sources. No price forecasts or trading advice.
AI Integration — Plans and builds LLM API connections (OpenAI, Anthropic, and more) into real apps. Covers model selection, cost estimation, key safety, error handling, and working code. Adapts to non-engineers and developers alike. Stops the #1 mistake: shipping your API key to the browser.
Turns scattered AI tool intel — tweets, launch posts, screenshots — into a ready-to-use directory database and a publish-ready weekly digest. Give it a niche, get back 15 tools with pricing, use cases, and alternatives, formatted for direct import into Notion, Airtable, or Excel. Or paste this week's findings and get an IG, LinkedIn, or newsletter-ready digest in one pass. Bilingual output, no separate translation pass needed.
Research the open web and 15 major platforms with intelligent multi-backend routing. 智能连接搜索、社交媒体、GitHub、视频、招聘、RSS 与市场信息源，让跨平台调研更高效。
Paste news (headlines, body text, multiple articles) and instantly get a clean digest structured as key points, background, impact on life/business, and what to watch next. Formats for stand-ups, internal sharing, newsletters, and social. Source text is never copied — summarized and paraphrased only; speculation and facts are kept distinct, and investment/medical/legal topics avoid advice. Turn daily news triage into seconds.
日々AIの回答・ニュース・SNSの言説を実務で扱う中で、出典のない数値や「最新」を装った古い情報に何度も振り回された経験から、このSkillを設計しました。主張を安定/不安定に分類し、不安定な情報ほど一次ソースを最優先で確認、重要な主張は独立した複数ソースでクロスチェックする手順を体系化しています。AI生成記事が引用元の主張を実際には支持していないという罠も検出します。
你把影片網址丟給 AI，它讀了標題就開始講——那不叫看過影片，那叫猜。 這支讓 AI 真的看：抽出去重複的關鍵幀、產九宮格 contact sheet（一次讀九張省 9 倍圖片量）、另外跑高準度中文逐字稿，三樣一起讀完才回答。 差別很具體：沒看過畫面的 AI 說「內容豐富值得參考」，看過的說「0–2 秒用失敗畫面當 hook，全片 6 個鏡位平均 2.4 秒換一次」。