diff --git a/README.md b/README.md index 75179e4..6bc9d6e 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,9 @@ + +> [!NOTE] +> 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。 +> [English](./README.en.md) · [原始项目](https://github.com/XBuilderLAB/cheat-on-content) · [上游 README](https://github.com/XBuilderLAB/cheat-on-content/blob/HEAD/README.md) +> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。 +

Cheat on Content

@@ -5,9 +11,9 @@

Cheat on Content

- English -  ·  简体中文 +  ·  + English

@@ -23,94 +29,94 @@

-For content creators — a skill that turns every post into a calibrated experiment. +面向内容创作者——一项能将每一篇作品变成可校准实验的技能。

-You're reading this. The skill predicted it.
-It turns every "I feel this will go viral" into a calibrated experiment.
-It took me from zero to 1M followers in a month. It said I'd write this. I did.
-Your doubt — predicted too. +你正在阅读这段文字。这项技能早就预测到了。
+它把每一次「我感觉这篇会爆」都变成一场可校准的实验。
+它帮我在一个月内从零涨到 100 万粉丝。它说我会写这篇 README。我写了。
+你的怀疑——也被预测到了。

--- -## 🎬 What it actually does +## 🎬 它到底在做什么 -Most creators live in the same gambling loop: +大多数创作者困在同一条赌博循环里： -> Publish → Numbers come in → Learn nothing → Roll the dice again +> 发布 → 数据进来 → 学不到东西 → 再掷一次骰子 -A creator who's shipped 200 pieces is barely 10% sharper than someone who's shipped 1 — because they never **kept books** after each round. +发了 200 篇作品的创作者，判断力只比发了 1 篇的人强不到 10%——因为他们每轮结束后从不**记账复盘**。 -**Cheat on Content** makes every judgment get logged, retrospected, absorbed into the next: +**Cheat on Content** 让每一次判断都被记录、复盘，并沉淀进下一轮： -📊 Score → 🎯 Blind-predict → 🚀 Publish → 📈 T+3d retro → 🧬 Evolve your rubric +📊 打分 → 🎯 盲测预测 → 🚀 发布 → 📈 T+3 天复盘 → 🧬 进化你的评分标准（rubric） -This isn't motivation. It's **compounding** — every piece you don't retro is silently eroding your ability to see yourself. +这不是励志话术。这是**复利**——每一篇不复盘的作品，都在悄悄侵蚀你认识自己的能力。 -One month in = you have a hit-formula that's **only yours**. -Three months in = you're 10× sharper than your first-day self. +一个月后 = 你拥有一套**只属于你**的爆款公式。 +三个月后 = 你比第一天的自己敏锐 10 倍。 --- -## 🌀 Origin +## 🌀 缘起 -> I never believed in fate. Until this skill made me film a video — and predicted exactly how much traffic that video would pull. +> 我从不信命。直到这项技能让我拍了一条视频——并准确预测了那条视频能拉来多少流量。 > -> I tried to break it. I told my audience. I hoped collective observation would collapse the wave function and shift the trajectory. +> 我试图打破它。我告诉了我的观众。我希望集体观测能坍缩波函数、改变轨迹。 > -> The data was accurate. +> 数据依然准确。 > -> I didn't escape fate. I just moved from first-order to second-order. +> 我没逃过命运。我只是从「一阶」跃迁到了「二阶」。 > -> If even my awakening — even my audience's observation — was already in its prediction, then right now, reading this: -> are you here out of curiosity, or just closing the algorithm's last move? +> 如果连我的觉醒——连观众的观测——都已在它的预测之中，那么此刻，读着这段话的你： +> 是出于好奇而来，还是只是在完成算法的最后一步？ > -> — *the creator* +> — *创作者* --- -## ⚖️ How it differs from other "creator tools" +## ⚖️ 与其他「创作者工具」有何不同 -| Others | This | +| 其他工具 | 本技能 | |---|---| -| Give you "inspiration" | Make **your own intuition** measurable | -| AI writes for you | AI **judges** for you — the script stays yours | -| Ship 10 versions, A/B test | Ship one — **bet** in writing, settle the books with data | -| Static dashboard | An **evolving rubric** — your formula 3 months from now isn't the starting one | +| 给你「灵感」 | 让**你自己的直觉**可量化 | +| AI 替你写稿 | AI **替你评判**——脚本仍是你写的 | +| 发 10 个版本做 A/B 测试 | 只发一版——**书面下注**，用数据结账 | +| 静态仪表盘 | **进化的评分标准**——三个月后的公式不是起点那一版 | -In a sentence: other tools help you "ship more." This helps you "judge sharper." +一句话：其他工具帮你「多发」；这个帮你「判得更准」。 --- -## 🤔 Can't I just use ChatGPT / DeepSeek / Doubao? +## 🤔 我直接用 ChatGPT / DeepSeek / Doubao 不行吗？ -Those are **general assistants** — they tell everyone the same thing. You ask "will this go viral?" and the answer is fitted to global average opinion, not your channel. Ask again tomorrow — same answer. **It doesn't remember you. It doesn't change because of you.** +那些是**通用助手**——对所有人说同样的话。你问「这篇会爆吗？」，答案贴合的是全球平均意见，不是你的频道。明天再问——还是同一个答案。**它不记得你。也不会因为你而改变。** -This is **your own ops expert** — serving only your one channel: +这是**你自己的运营专家**——只服务你这一个频道： -- The scoring formula is reverse-engineered from **your** history, not the global training distribution -- Every piece you ship updates its understanding — by month three, judgment accuracy is 10× sharper than day one (**auto-evolving**) -- It knows your benchmark account, your cadence, the last three reasons you flopped — things ChatGPT forgets after the first reply +- 打分公式是从**你的**历史数据反推出来的，不是全球训练分布 +- 你每发一篇，它就更新理解——到第三个月，判断准确度比第一天敏锐 10 倍（**自动进化**） +- 它知道你的对标账号、你的更新节奏、最近三次扑街的原因——ChatGPT 在第一次回复后就忘了的事 -General LLMs help everyone. This helps **your** account. +通用大模型帮所有人。这个帮**你的**账号。 --- -## 🛡️ Why the loop actually evolves +## 🛡️ 循环为何真的能进化 -📝 **Every piece is logged**: Score and prediction get written before publish, archived end-to-end. Three days later you settle accounts — you see exactly where you were sharp, where you were off. No more vague "I feel this one didn't land." +📝 **每篇都入账**：发布前写下分数与预测，全程归档。三天后结账——你能精确看到哪里判准了、哪里偏了。不再有模糊的「我感觉这篇没起量」。 -🔁 **It gets sharper**: Three same-direction misses in a row, the tool actively prompts you to upgrade your scoring formula. **You don't have to remember — it remembers for you.** +🔁 **它会越来越准**：连续三次同向失误，工具会主动提示你升级打分公式。**你不用记——它替你记。** -🛡️ **Upgrades have a brake**: Switching the formula requires re-scoring all historical samples — only released if it ranks more accurately than the old. Plus a cross-model independent audit — **so you can't fool yourself.** +🛡️ **升级有刹车**：换公式要对全部历史样本重新打分——只有新公式排序更准才会放行。还有跨模型独立审计——**让你没法自欺欺人。** -🪒 **The rubric is a workbench, not a museum**: Observations refuted by data get deleted; observations absorbed into formal dimensions also get deleted. It only holds what's most useful right now. +🪒 **评分标准是工作台，不是博物馆**：被数据推翻的观察会删掉；已吸收进正式维度的观察也会删掉。它只保留当下最有用的东西。 --- -## 📦 Install +## 📦 安装 ```bash git clone https://github.com/XBuilderLAB/cheat-on-content.git @@ -118,33 +124,33 @@ cd cheat-on-content bash install.sh ``` -> ⚠️ **Upgrading from v0.x?** Run `/cheat-migrate` in your content project after `git pull`. The 1.3 → 1.4 migration is **BREAKING for blind-channel integrity** — it splits `rubric_notes.md` so the blind sub-agent can't leak actuals. Without migrate, blind scoring will keep flagging `non_blind_warning`. See [CHANGELOG](CHANGELOG.md) and [migrations/1.3-to-1.4.md](migrations/1.3-to-1.4.md). +> ⚠️ **从 v0.x 升级？** 在 `git pull` 之后，于你的内容项目中运行 `/cheat-migrate`。1.3 → 1.4 迁移对**盲测频道完整性**是**破坏性变更**——它会拆分 `rubric_notes.md`，使盲测子代理无法泄露真实结果。不执行 migrate，盲测打分会持续标记 `non_blind_warning`。详见 [CHANGELOG](CHANGELOG.md) 与 [migrations/1.3-to-1.4.md](migrations/1.3-to-1.4.md)。 -14 sub-skills are symlinked into your agent's skill directory. One install, every content project gets it. +14 个子技能会符号链接到你的 agent 技能目录。一次安装，每个内容项目都能用。 -**Supported agents**: Claude Code (default) · Codex (`bash install.sh --codex`) · Both (`bash install.sh --all`) +**支持的 agent**：Claude Code（默认）· Codex（`bash install.sh --codex`）· 两者兼有（`bash install.sh --all`） -> Frozen version: `bash install.sh --copy` / `bash install.sh --codex --copy` +> 冻结版本：`bash install.sh --copy` / `bash install.sh --codex --copy` > -> Uninstall: `bash uninstall.sh` / `bash uninstall.sh --codex` (your content data is not touched) +> 卸载：`bash uninstall.sh` / `bash uninstall.sh --codex`（你的内容数据不会被触碰） --- -## 🚀 First run +## 🚀 首次运行 -In your content project directory, open a skill-compatible agent and say: +在你的内容项目目录中，打开支持技能的 agent，然后说： ``` 初始化 cheat-on-content ``` -(or `init cheat-on-content`) +（或 `init cheat-on-content`） -Five yes/no questions complete onboarding. **Strongly recommend importing a benchmark account** — 5–10 samples and the tool gets an anchor immediately. Without one, your first 5 predictions land at ±50% precision. +五个是/否问题即可完成入门。**强烈建议导入对标账号**——5–10 个样本后工具立刻有锚点。没有对标账号，前 5 次预测的精度大约在 ±50%。 --- -## ⚡ Daily use +## ⚡ 日常使用 ``` score this scripts/<...>.md → grade only @@ -155,13 +161,13 @@ retro videos/<...>/ → T+3d data + retrospective status / fetch trends / find topic / bump rubric / find benchmark ``` -Hook-aware agents auto-report buffer + pending retros + top candidates at every session start — no need to ask. Other agents: just say `status`. +支持 Hook 的 agent 会在每次会话开始时自动汇报 buffer、待复盘项与头部候选——无需主动询问。其他 agent：直接说 `status`。 -Full workflow + sub-skill details: see [SKILL.md](SKILL.md). +完整工作流与子技能细节：见 [SKILL.md](SKILL.md)。 --- -## 📈 Star History +## 📈 Star 历史 Star History Chart @@ -169,13 +175,13 @@ Full workflow + sub-skill details: see [SKILL.md](SKILL.md). --- -## 📜 License +## 📜 许可证 -MIT. Commercial use, modification, closed-source integration — all fine. +MIT。商业使用、修改、闭源集成——均可。 --- -*Is this cheating? So was the calculator. So was Google.* -*The future doesn't reward effort — it rewards those who see the pattern first.* +*这算作弊吗？计算器当年也算。Google 也算。* +*未来奖励的不是努力——而是最先看清规律的人。* -*You reading this line — that's predicted too.* +*你读到这一行——也被预测到了。*