コンテンツファクトリー Skill
記事や文字起こし1本を、AI の声ではなくあなたの声で書いた1週間分の投稿に変えます。
出品者：GetKits
その違いをご覧ください
ブログ記事を入れると、あなたの声の投稿が出てくる
ビフォー
Lena Zhou の1,400語の Fernway ブログ記事：タイマーで送る7通のオンボーディングメールはクリック率9%。短くしても変わらず。オンボーディング通話11件で、つまずく箇所が2つ判明。ユーザーが止まった時に送る4通は31%。
アフター
オンボーディングメールを短くしました。クリック率は動きませんでした。 そこでセットアップ通話11件を聞き直しました。メールの話をした人はゼロ。みんなが口にしたのは、つまずいた2つの画面でした。 直す場所を間違えていたんです。 X 投稿4本中の3本目（告白、215字）。同じパックに7投稿スレッド、LinkedIn 投稿、ニュースレターのセクション、動画スクリプト、RED ノートが加わります：做SaaS的，新手引导邮件我只留了4封
Panel transcript in, 7 pieces out
ビフォー
Mode B, Lena's VOICE PROFILE loaded. Source: Agency Ops Live panel transcript, Toronto, Thu 2026-10-22, 34 min. Speakers: Dana Ruiz (host), Lena Zhou, Jun Park (Lumen). [06:10] LENA: We looked at the 61 agencies that cancelled Fernway this year. 40 of them, their clients never logged in a second time. [11:45] LENA: We had a monthly usage report, um, 12% opened it. So now the agency gets one line when a client hasn't logged in for 14 days. Since August, 23 agencies got it, and 11 messaged their client that same day. [14:20] LENA: I thought churn was pricing. We offered 30 agencies a discount to stay. 4 stayed, and three of those left by [inaudible]. [16:02] LENA: A discount just tells them the price was the problem. It never was. [22:40] JUN: Churn shows up in your client's inbox before it shows up in your dashboard. Settings: all six channels, week of Nov 2, America/Toronto.
アフター
Voice: Lena Zhou, last updated 2026-10-08 | Pack ID: 2026-W45-client-logins SOURCE BRIEF Thesis: Most agencies we lost had a client who never logged in twice. Watch the second login. Ideas: 1. The client's second login predicts churn | Proof: 40 of 61 cancelled agencies (06:10) | Type: number 2. One 14-day line instead of a monthly report | Proof: report opened by 12%; 11 of 23 agencies messaged their client the same day (11:45) | Type: number 3. A discount did not keep them | Proof: 30 offered, 4 stayed, 3 of the 4 left later (14:20) | Type: story Quotable lines: "A discount just tells them the price was the problem. It never was." (Lena, 16:02); "Churn shows up in your client's inbox before it shows up in your dashboard." (Jun Park, 22:40) To confirm: when the 3 agencies left (14:20, [inaudible, confirm]); Jun Park's line [confirm permission] X THREAD Skipped: no idea has 4 or more steps. Ideas 1 to 3 went to X posts. X POSTS Post 1 | Specific result | 159 chars 40 of the 61 agencies that cancelled Fernway this year had one thing in common. Their clients logged in once and never came back. Watch for the second login. (Posts 2 to 4: the discount story, Lena's 16:02 line, the 14-day line) LINKEDIN POST Hook formula: Teardown list | 1,084 chars We went through every agency that cancelled Fernway this year. 61 of them. In 40, the client had logged in once and never again. (4 more paragraphs. Ends: "Watch the second login.") NEWSLETTER SECTION Subject line options: The login that predicts churn (29) | 40 of 61 had the same warning sign (34) | What our discount told customers (32) Quotes Jun Park's line. Link line: the panel recording [confirm link] VIDEO SCRIPT Skipped: the most surprising claim (40 of 61) needs a chart, and none exists yet. RED NOTE 标题：客户只登录一次，就要小心了 封面文字：40家的客户没再登录 CALENDAR | Mon 2026-11-02 08:30 | LinkedIn | We went through every agency that cancelled | Retention | Teardown list | 2026-W45-client-logins | Ready for review | (6 more rows: X post Wed, newsletter and X post Thu, X post and RED Fri, X post Sat) OPEN ITEMS - [inaudible, confirm] When the 3 discounted agencies left (X POSTS post 2) - [confirm permission] Jun Park's line (NEWSLETTER SECTION) - [confirm link] Panel recording (NEWSLETTER SECTION) - Asset needed: a chart of the 61 cancellations (RED cover, and the VIDEO SCRIPT if you want one) - 7 pieces: the thread and video were skipped, so Tuesday is open - Anti-AI fixes made: 3
Four samples in, a VOICE PROFILE out
ビフォー
S1 (X): We lost 14 trial accounts in July. Not to a competitor. To a password reset email that landed in spam. Boring problems kill more startups than big ones. S2 (newsletter): I used to think our onboarding problem was copy. So I rewrote the welcome email four times. Same result. Then I watched six agencies set up Fernway on a call... I'd spent a month on adjectives. S3 (LinkedIn): A client asked me last week why Fernway doesn't have a chatbot. Honest answer: we tried one... Not every feature needs to exist. Most need to be shorter. S4 (X): Agency owners don't want "a world-class client experience". They want the client to stop emailing them asking where the files are.
アフター
VOICE PROFILE Name: Lena Zhou (Fernway) Last updated: 2026-10-08 Confidence: medium (4 samples, 3 formats, no video or Chinese sample) Rhythm - Average sentence length: 8 words (range 2 to 24) - Fragments: frequent, used as the turn: "Same result." (S2) Openers - Type: an event with a number or a person - Verbatim: "We lost 14 trial accounts in July." (S1) Closers - Type: one-line principle, under 10 words - Verbatim: "Most need to be shorter." (S3) Signature moves (use at most one per piece) - Self-deprecating cost line: "I'd spent a month on adjectives." (S2) Taboo words - From the user: [ask Lena] - From the anti-AI list, absent from every sample: delve, leverage, journey, seamless, unlock, crucial - Mocked in S4: "world-class" Stances - Small, boring fixes beat big launches (S1, S2) - Shorter beats more (S3) Formatting - Line breaks every 1 to 3 sentences. No lists, emoji, hashtags or bold. Contractions always. Platform adjustments - LinkedIn: one more paragraph of context, ends on a principle, never a question - Video: [unknown] - RED: [unknown, ask for one Chinese sample] Calibration: "Which sounds most like you, A, B or C, and what is off?"
Translated RED note, rewritten for RED readers
ビフォー
Mode C. Channel: RED. Lena's VOICE PROFILE loaded. Facts, from her June LinkedIn post (S3): a support chatbot ran for three weeks and answered "How do I invite a client?" with a 200-word essay from a 40-word help doc. Fernway turned it off. Tickets up 6%, churn flat. A teammate machine-translated that post: 标题：AI客服机器人：一个改变游戏规则的决定？ 在当今这个AI快速发展的时代，客服机器人已经成为每个SaaS产品的标配。但这不是关于拥有机器人，而是关于用户体验。 首先，我们的机器人用200字回答一个40字就能说清的问题。其次，我们决定关掉它。最后，工单只增加了6%，流失率保持不变。 这是我们做过的最正确的决定！想了解更多，欢迎访问 fernway.com 或私信我。 #AI #客服 #SaaS
アフター
REWRITE 标题：我们把客服机器人关了，工单只多了6% 封面文字：答案是文档的5倍长 正文： 有客户问我，Fernway（我们自己做的客户门户工具）为什么没有客服机器人。 老实说，我们上过一个，用了三周。 这三周里，用户问“怎么邀请客户”，它回的是一大段话，篇幅是那篇帮助文档的5倍。 后来我们把它关了。关掉以后： 1. 客服工单多了6% 2. 流失率没有变化 很多功能其实不用做。做了的，大多该再短一点。 你们的产品里，有没有哪个功能其实可以直接关掉？ 话题标签：#SaaS #创业 #产品运营 #独立开发 #客服机器人 #用户体验 Weak spot: the 正文 is about 170 字, under RED's suggested 300 to 600, and RED readers save notes with steps. If you have them, add how you shortened the invite doc: [add your example: what you cut] TELLS REMOVED - 翻译腔 title: "一个改变游戏规则的决定？" became "我们把客服机器人关了，工单只多了6%" - 开头套话: "在当今这个AI快速发展的时代" became the client's question from S3 - Negation flip (翻译腔): "这不是关于拥有机器人，而是关于用户体验" cut - 模板结构: "首先……其次……最后" became the story in the order it happened - Unit error: "用200字回答一个40字" counted English words as Chinese characters. It became "篇幅是那篇帮助文档的5倍" - 广告法极限词: "最正确的决定" removed, since 最 can get a note throttled - 站外导流: "fernway.com" and "私信我" removed. RED notes carry no outside links or contact asks - Hashtags: 3 generic tags became 6 tied to the note (RED range: 5 to 10)
収録内容
- content-factory.zip
この Kit について
Give this skill 3 to 5 things you wrote and it builds a VOICE PROFILE you reuse from then on. Give it one article, transcript or podcast and it returns a week of drafts in that voice: an X thread, four X posts, a LinkedIn post, a newsletter section, a short video script, a Xiaohongshu (RED) note in Chinese and a 7-day calendar. A full pack takes about 10 minutes, and you edit drafts instead of starting from a blank page.
What you get
- The
content-factoryskill folder for Claude, ChatGPT, Codex and Cursor. - Three modes: build a voice profile, build a content pack, and fix a draft that sounds like AI.
- A voice profile template with 18 fields measured from your samples, each one tied to a line you actually wrote, plus a calibration step that checks it with you.
- 13 hook formulas, each with an example, when it works and how it fails, plus a four-question hook test to choose between them.
- Platform formats: limits and structure for X threads and posts, LinkedIn, newsletter sections and short video, and a guide written in Chinese for RED, with 标题 formulas and the words that get notes throttled.
- An anti-AI tells list: more than 70 phrases and words, and 18 patterns readers now spot, each with its fix, in English and Chinese.
- A content calendar template that matches the Notion database used by the Content Factory Bot and Dot.
- A full worked example: one blog post in, the complete pack out, with notes on every judgment call, including the invented details it caught.
Who it is for
- Founders and operators who write from real work and want to post on X and LinkedIn every week.
- Newsletter writers who want each issue to feed a week of social posts.
- Creators who reach Chinese-speaking readers on Xiaohongshu as well as English channels.
- Ghostwriters and content leads who manage someone else's voice and need it to stay consistent.
What it will not do
- Post, schedule or tag anyone. It drafts. You publish.
- Invent numbers, quotes or stories. Anything it cannot trace to your source comes back marked
[confirm]. - Pad a thin source. If there is not enough in it, you get three questions instead of filler.
- Translate your English posts into Chinese word for word. The RED note is written for Chinese readers from the source itself.
- Write long SEO articles, sales pages or ads.
レビュー
まだレビューはありません。
コンテンツ向けのほかの Kit
コンテンツファクトリー Kit
長文1本から、あなたの声そのままの投稿を1週間分。Notion で予定を組み、毎週レビューします。
コンテンツファクトリー Bot
月曜に X で切り口を探し、木曜までに来週の投稿を下書きする Grok Bot です。
コンテンツファクトリー Dot
あなたの dot が Notion のコンテンツカレンダーを埋め続け、共有したインタビューをすべてパックにします。