{"id":50057551,"url":"https://github.com/XBuilderLAB/cheat-on-content","last_synced_at":"2026-05-25T13:01:41.903Z","repository":{"id":355825214,"uuid":"1229729956","full_name":"XBuilderLAB/cheat-on-content","owner":"XBuilderLAB","description":"You're reading this. The skill predicted it. A workflow that turns every post into a calibrated experiment—score, blind-predict, retro, evolve. The future doesn't reward effort, it rewards those who see the pattern first. 1M followers in a month — not luck, system.","archived":false,"fork":false,"pushed_at":"2026-05-14T08:54:08.000Z","size":297,"stargazers_count":1950,"open_issues_count":5,"forks_count":367,"subscribers_count":4,"default_branch":"main","last_synced_at":"2026-05-14T10:42:38.379Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Shell","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/XBuilderLAB.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-05-05T10:28:33.000Z","updated_at":"2026-05-14T10:28:18.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/XBuilderLAB/cheat-on-content","commit_stats":null,"previous_names":["xbuilderlab/cheat-on-content"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/XBuilderLAB/cheat-on-content","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XBuilderLAB%2Fcheat-on-content","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XBuilderLAB%2Fcheat-on-content/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XBuilderLAB%2Fcheat-on-content/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XBuilderLAB%2Fcheat-on-content/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/XBuilderLAB","download_url":"https://codeload.github.com/XBuilderLAB/cheat-on-content/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XBuilderLAB%2Fcheat-on-content/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33475746,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-25T06:32:55.349Z","status":"ssl_error","status_checked_at":"2026-05-25T06:32:35.322Z","response_time":57,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-05-21T15:00:44.305Z","updated_at":"2026-05-25T13:01:41.897Z","avatar_url":"https://github.com/XBuilderLAB.png","language":"Shell","funding_links":[],"categories":["开源工具","🧠 Agent Skills"],"sub_categories":["好用工具"],"readme":"\u003ch1 align=\"center\"\u003e\n  \u003cimg src=\"docs/logo.svg\" alt=\"Cheat on Content\" width=\"720\"\u003e\n\u003c/h1\u003e\n\n\u003ch2 align=\"center\"\u003eCheat on Content\u003c/h2\u003e\n\n\u003cp align=\"center\"\u003e\nFor content creators — a skill that turns every post into a calibrated experiment.\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\nYou're reading this. The skill predicted it.\u003cbr\u003e\nIt turns every \"I feel this will go viral\" into a calibrated experiment.\u003cbr\u003e\nIt took me from zero to 1M followers in a month. It said I'd write this. I did.\u003cbr\u003e\nYour doubt — predicted too.\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003eEnglish\u003c/strong\u003e\n  \u0026nbsp;·\u0026nbsp;\n  \u003ca href=\"docs/README_CN.md\"\u003e\u003cstrong\u003e简体中文\u003c/strong\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n\u003ca href=\"CHANGELOG.md\"\u003e\u003cimg src=\"https://img.shields.io/badge/version-v0.1.0-orange\" alt=\"Version\"\u003e\u003c/a\u003e\n\u0026nbsp;\n\u003ca href=\"LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/badge/license-MIT-blue.svg\" alt=\"License\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n---\n\n## 🎬 What it actually does\n\nMost creators live in the same gambling loop:\n\n\u003e Publish → Numbers come in → Learn nothing → Roll the dice again\n\nA creator who's shipped 200 pieces is barely 10% sharper than someone who's shipped 1 — because they never **kept books** after each round.\n\n**Cheat on Content** makes every judgment get logged, retrospected, absorbed into the next:\n\n📊 Score → 🎯 Blind-predict → 🚀 Publish → 📈 T+3d retro → 🧬 Evolve your rubric\n\nThis isn't motivation. It's **compounding** — every piece you don't retro is silently eroding your ability to see yourself.\n\nOne month in = you have a hit-formula that's **only yours**.\nThree months in = you're 10× sharper than your first-day self.\n\n---\n\n## 🌀 Origin\n\n\u003e I never believed in fate. Until this skill made me film a video — and predicted exactly how much traffic that video would pull.\n\u003e\n\u003e I tried to break it. I told my audience. I hoped collective observation would collapse the wave function and shift the trajectory.\n\u003e\n\u003e The data was accurate.\n\u003e\n\u003e I didn't escape fate. I just moved from first-order to second-order.\n\u003e\n\u003e If even my awakening — even my audience's observation — was already in its prediction, then right now, reading this:\n\u003e are you here out of curiosity, or just closing the algorithm's last move?\n\u003e\n\u003e — *the creator*\n\n---\n\n## ⚖️ How it differs from other \"creator tools\"\n\n| Others | This |\n|---|---|\n| Give you \"inspiration\" | Make **your own intuition** measurable |\n| AI writes for you | AI **judges** for you — the script stays yours |\n| Ship 10 versions, A/B test | Ship one — **bet** in writing, settle the books with data |\n| Static dashboard | An **evolving rubric** — your formula 3 months from now isn't the starting one |\n\nIn a sentence: other tools help you \"ship more.\" This helps you \"judge sharper.\"\n\n---\n\n## 🤔 Can't I just use ChatGPT / DeepSeek / Doubao?\n\nThose 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.**\n\nThis is **your own ops expert** — serving only your one channel:\n\n- The scoring formula is reverse-engineered from **your** history, not the global training distribution\n- Every piece you ship updates its understanding — by month three, judgment accuracy is 10× sharper than day one (**auto-evolving**)\n- It knows your benchmark account, your cadence, the last three reasons you flopped — things ChatGPT forgets after the first reply\n\nGeneral LLMs help everyone. This helps **your** account.\n\n---\n\n## 🛡️ Why the loop actually evolves\n\n📝 **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.\"\n\n🔁 **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.**\n\n🛡️ **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.**\n\n🪒 **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.\n\n---\n\n## 📦 Install\n\n```bash\ngit clone https://github.com/XBuilderLAB/cheat-on-content.git\ncd cheat-on-content\nbash install.sh\n```\n\n\u003e ⚠️ **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).\n\n14 sub-skills are symlinked into your agent's skill directory. One install, every content project gets it.\n\n**Supported agents**: Claude Code (default) · Codex (`bash install.sh --codex`) · Both (`bash install.sh --all`)\n\n\u003e Frozen version: `bash install.sh --copy` / `bash install.sh --codex --copy`\n\u003e\n\u003e Uninstall: `bash uninstall.sh` / `bash uninstall.sh --codex` (your content data is not touched)\n\n---\n\n## 🚀 First run\n\nIn your content project directory, open a skill-compatible agent and say:\n\n```\n初始化 cheat-on-content\n```\n\n(or `init cheat-on-content`)\n\nFive 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.\n\n---\n\n## ⚡ Daily use\n\n```\nscore this scripts/\u003c...\u003e.md       → grade only\nstart prediction scripts/\u003c...\u003e.md → blind prediction + decision log\nshot scripts/\u003c...\u003e.md             → create video folder + buffer +1\nshipped https://...                → buffer -1\nretro videos/\u003c...\u003e/                → T+3d data + retrospective\nstatus / fetch trends / find topic / bump rubric / find benchmark\n```\n\nHook-aware agents auto-report buffer + pending retros + top candidates at every session start — no need to ask. Other agents: just say `status`.\n\nFull workflow + sub-skill details: see [SKILL.md](SKILL.md).\n\n---\n\n## 📈 Star History\n\n\u003ca href=\"https://star-history.com/#XBuilderLAB/cheat-on-content\u0026Date\"\u003e\n  \u003cimg src=\"https://api.star-history.com/svg?repos=XBuilderLAB/cheat-on-content\u0026type=Date\" alt=\"Star History Chart\" width=\"720\"\u003e\n\u003c/a\u003e\n\n---\n\n## 📜 License\n\nMIT. Commercial use, modification, closed-source integration — all fine.\n\n---\n\n*Is this cheating? So was the calculator. So was Google.*\n*The future doesn't reward effort — it rewards those who see the pattern first.*\n\n*You reading this line — that's predicted too.*\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FXBuilderLAB%2Fcheat-on-content","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FXBuilderLAB%2Fcheat-on-content","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FXBuilderLAB%2Fcheat-on-content/lists"}