Content Forecast
Colinjqq/content-forecast
Helps video creators pick topics from their own experience, diagnose how a script may spread and compare its expected performance with their own baseline.
Turns content creation into a calibrated loop of scoring, blind prediction, post-publish review and rubric evolution, with a built-in rubric for opinion videos.
SKILL.md written in Chinese; this summary is our English description.
$ npx skills add XBuilderLAB/cheat-on-content --skill cheat-on-content -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install XBuilderLAB/cheat-on-content cheat-on-content --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "cheat-on-content" agent skill from https://github.com/XBuilderLAB/cheat-on-content/tree/main into .claude/skills/cheat-on-content/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cheat-on-content", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add XBuilderLAB/cheat-on-content --skill cheat-on-content -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install XBuilderLAB/cheat-on-content cheat-on-content --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cheat-on-content" agent skill from https://github.com/XBuilderLAB/cheat-on-content/tree/main into .agents/skills/cheat-on-content/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cheat-on-content", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add XBuilderLAB/cheat-on-content --skill cheat-on-content -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install XBuilderLAB/cheat-on-content cheat-on-content --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cheat-on-content" agent skill from https://github.com/XBuilderLAB/cheat-on-content/tree/main into .cursor/skills/cheat-on-content/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cheat-on-content", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add XBuilderLAB/cheat-on-content --skill cheat-on-content -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install XBuilderLAB/cheat-on-content cheat-on-content --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "cheat-on-content" agent skill from https://github.com/XBuilderLAB/cheat-on-content/tree/main into .gemini/skills/cheat-on-content/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cheat-on-content", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install XBuilderLAB/cheat-on-content cheat-on-contentInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add XBuilderLAB/cheat-on-content --skill cheat-on-content -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "cheat-on-content" agent skill from https://github.com/XBuilderLAB/cheat-on-content/tree/main into .github/skills/cheat-on-content/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cheat-on-content", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add XBuilderLAB/cheat-on-content --skill cheat-on-content -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install XBuilderLAB/cheat-on-content cheat-on-content --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cheat-on-content" agent skill from https://github.com/XBuilderLAB/cheat-on-content/tree/main into .opencode/skills/cheat-on-content/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cheat-on-content", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
cheat-on-contentTurns content creation into a calibrated loop of scoring, blind prediction, post-publish review and rubric evolution, with a built-in rubric for opinion videos.
The method is a five-stage loop of scoring a draft, predicting its performance, publishing, reviewing the result and evolving the rubric, and it applies to anything measurable, such as video views, article reads, podcast listens or clicks. The built-in rubric is for opinion videos, with seven dimensions fitted from more than 25 reference posts; other formats need their own rubric, using a starter file as the format guide. A newcomer with no posts gets a simplified seven-dimension score and a one-line bet, and a creator with five or more posts moves to calibration mode.
Three principles are non-negotiable, and the skill refuses requests to break them. Predictions are blind and written before any real data, after which the prediction section is immutable and only the review section can be appended, enforced by a hook. A rubric upgrade re-scores every sample that has real results and is rejected if the new ranking disagrees with actual performance on at least four of five samples. The rubric is a workbench, not a museum, so disproved or absorbed observations are deleted and git history is the archive.
Sub-skills handle initialization, learning from benchmark accounts, topic seeding, scoring, prediction, shoot and publish logging, review, rubric upgrades and status. On Codex, where slash commands are missing, the same routing is triggered by plain-language phrases. Performance-data adapters, including a Bilibili stats crawler, are bundled.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 2d8211e. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
Bash(*)ReadWriteEditGrepGlobSkillmcp__llm-chat__chatFrom allowed-tools in the SKILL.md frontmatter.
Ships script files (Python and Shell, from the files we listed), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Cheat on Content Calibration loads about 2.7k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 410 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, Skill, mcp__llm-chat__chatAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from XBuilderLAB/cheat-on-content at commit 2d8211e, republished under its MIT licence (© XBuilderLAB). 410 words, ~2,720 tokens.
.claude/skills/cheat-on-content/SKILL.md (or your agent's skills folder). This skill also uses 120 other files; get the full folder from GitHub.🎯 方法论通用,rubric 当前内置观点视频版
方法论(5 阶段闭环):任何能被量化的内容形态都适用——视频 / 文章 / 播客 / Newsletter / 短文 thread。
当前内置 rubric:观点类视频(评论 / 时评 / 论说 / 议题讨论 / 个人观点表达),7 个维度由参考博主 25+ 已发样本拟合而来。如果你做其他形态,需要:
- 自己写一份 rubric(参照 starter-rubrics/opinion-video-zero.md 的格式)
- 或等内置扩展(长文 / 短文 / 播客 starter 在批次 3 路线图)
默认假设:用户是从零开始的新人(一条视频都没发过)——cold-start 期的预测会简化,只要 7 维打分 + 一句话 bet,不强求 bucket 数字(避免 false precision)。已有 5+ 篇数据的老手走 calibration 模式解锁完整 7 组件预测。
把内容创作变成可校准预测循环:打分 → 预测 → 发布 → 复盘 → 进化 rubric。
本文件是总协议 + 路由器。具体每个阶段的工作流在 skills/cheat-*/SKILL.md 各子 skill 里。
Codex 没有 Claude Code 的 slash-command harness。安装到 Codex 后,按自然语言触发同一套路由即可:
初始化 cheat-on-content → 读取并执行 skills/cheat-init/SKILL.md打分这篇 scripts/foo.md → 读取并执行 skills/cheat-score/SKILL.md启动预测 scripts/foo.md → 读取并执行 skills/cheat-predict/SKILL.md拍了 ... / 已发布 ... / 复盘 ... / 升级 rubric / 状态 → 分别读取对应 skills/cheat-*/SKILL.md执行时遵循本文件的三条原则和路由表;不要依赖 /cheat-* 命令是否存在。Claude Code 专用 hook(.claude/settings.json)仍只在 Claude Code 里自动触发;Codex 中需要用户主动说 状态 查看 buffer、待复盘和候选池。
任何一条被违反,整个校准循环退化为"凭直觉的自我安慰"。如果用户要求打破其中任何一条,拒绝执行并说明原因。
盲预测(Blind prediction):预测必须在看到任何实际数据之前写完。一旦写完,## 预测 段是 immutable——只能往 ## 复盘 段追加。完整规范:shared-references/blind-prediction-protocol.md。hooks/prediction-immutability.sh 在 harness 层强制执行。
升级 = 全量重打(Bump = full re-score):rubric 升级时,校准池所有有实绩数据的样本必须用新公式重打分;新排序与实际表现排序若在 ≥4/5 样本上不一致,升级被拒;升级必须经跨模型独立审核。完整规范:shared-references/bump-validation-protocol.md。
rubric 是工作台,不是博物馆:被新数据推翻或被吸收为正式维度的观察,删掉。绝不留"我曾经以为 X,但其实..."的考古层。git history 才是档案。完整规范:shared-references/observation-lifecycle.md。
| 用户说 | 调用 | 前置条件 |
|---|---|---|
| "初始化" / "init" / "首次使用" | /cheat-init | 无(这是入口) |
| "找对标" / "学这个账号" / "拆这几个对标视频" / "learn from" / "导入对标账号" | /cheat-learn-from | 已 init;cold-start 强烈建议;后续可随时 --append / --replace |
| "找选题" / "我不知道拍什么" / "seed" / "找前 5 个选题" | /cheat-seed | 已 init(cold-start 用户专用一次性种子动作) |
| "打分这篇 [path]" / "score this [path]" | /cheat-score | rubric_notes.md 存在 |
| "启动预测" / "start prediction" / "给这稿子打分并预测" | /cheat-predict | 已 init + 有最终稿 |
| "拍了 X" / "shot it" / "录完了" | /cheat-shoot | 对应预测已写(buffer +1) |
| "已发布" / "I shipped it" / "发布链接是 X" | /cheat-publish | 对应预测文件存在(buffer -1) |
| "复盘" / "retro this" / "T+3d 数据来了" | /cheat-retro | 对应预测文件存在 + 已过 RETRO_WINDOW_DAYS |
| "构造受众画像" / "更新 persona" / "我的观众是谁" / "build persona" | /cheat-persona | 已 init;有复盘评论数据(或 benchmark seed) |
| "升级 rubric" / "bump rubric" / "更新公式" | /cheat-bump | 校准池 ≥ MIN_SAMPLES_FOR_BUMP |
| "推荐选题" / "next topic" | /cheat-recommend | candidates.md 存在且非空 |
| "抓热点" / "fetch trends" / "今天有什么可做的" | /cheat-trends | trend-sources adapter 已配置(日常补充候选池) |
| "状态" / "status" / "看板" | /cheat-status | 任意时刻可调 |
| "迁移" / "升级 state" / "schema 版本不对" / "migrate" | /cheat-migrate | 已 init;用户 git pull 拉了新版后;SessionStart hook 提示 schema mismatch 后 |
拍 vs 发分两个动作:buffer 警戒系统需要明确知道"拍了但没发"vs"已发"两种状态。详见 shared-references/cadence-protocol.md。
Mode detection(首次接到非 init 触发词时执行):
.cheat-state.json → 没有 → 强制路由到 /cheat-initpredictions/ 下有几个文件含完整 ## 复盘 段填了真实数据 → 决定 mode: cold-start | calibration.cheat-state.json 后再路由到目标 skill下列模式会直接破坏三条原则之一,无论用户怎么说,都拒绝执行:
_redo.md 路径记为 reconstructedCROSS_MODEL_AUDIT=false 显式设置且 state file 标记自审时允许_redo.md,原版必须保留详细的拒绝场景在每个子 skill 的 Refusals 段。
skill 期望用户的项目布局如下。/cheat-init 会创建缺失项;绝不在没确认的情况下覆盖。
<user-content-project>/
├── .gitignore # cheat-init 创建;挡住 .auth*/.cheat-secrets.json 等凭证
├── rubric_notes.md # 评分规则的真实来源
├── WORKFLOW.md # 5 阶段流程文档(cheat-init 创建)
├── STATUS.md # 看板(cheat-status 维护)
├── .cheat-state.json # 状态文件,子 skill 共享上下文
├── .cheat-cache/ # 不入版本控制
│ ├── usage.jsonl # 钩子被动记录的使用日志
│ └── trends-history.jsonl # cheat-trends 的去重缓存
├── .claude/
│ └── settings.json # 含 prediction-immutability hook
├── benchmark.md # 对标账号信息(cheat-learn-from 维护)
├── audience.md # 受众画像(cheat-persona 派生;blind 硬禁读)
├── scripts/ # 拍前的所有草稿(cheat-seed 写或用户写)
│ └── YYYY-MM-DD_<id>_<short>.md
├── predictions/ # immutable 预测日志(hook 保护)
│ └── YYYY-MM-DD_<id>_<short>.md # 与 scripts/ 同 id
├── videos/ # 拍后才建(cheat-shoot 创建)
│ └── YYYY-MM-DD_<id>_<short>/
│ ├── script.md # 用户提供的最终拍摄稿(cheat-shoot 时询问"和 scripts/ 一致吗")
│ └── report.md # T+3d 抓的数据 + 评论(cheat-retro 写)
├── samples/ # 对标账号视频 / 转录(cheat-learn-from 创建)
│ └── <账号名>/<video-id>/{source.mp4 (可选), transcript.md, meta.md}
├── candidates.md # 选题池(可选)
└── content.db # 可选 SQLite,校准池规模化后启用cheat-on-content/
├── SKILL.md # 本文件(总协议 + 路由)
├── README.md # 营销门面
├── skills/ # 子 skill 集
│ ├── cheat-init/SKILL.md # ✅ 入口:onboarding 与脚手架
│ ├── cheat-learn-from/SKILL.md # ✅ 对标账号导入(拆 pattern + 派生 base rubric 信号)
│ ├── cheat-seed/SKILL.md # ✅ Cold-start 选题启动器(brainstorm + 可选 draft)
│ ├── cheat-score/SKILL.md # ✅ 单稿打分(不写文件)
│ ├── cheat-predict/SKILL.md # ✅ 盲预测 + immutable 日志
│ ├── cheat-shoot/SKILL.md # ✅ 登记拍摄(buffer +1)
│ ├── cheat-publish/SKILL.md # ✅ 发布元数据登记(buffer -1)
│ ├── cheat-retro/SKILL.md # ✅ 数据回收 + 复盘
│ ├── cheat-persona/SKILL.md # ✅ 受众画像派生(从复盘评论聚类)
│ ├── cheat-bump/SKILL.md # ✅ rubric 升级(含跨模型审)
│ ├── cheat-recommend/SKILL.md # ✅ 候选池排序推荐(按 buffer 颜色 + 1 稳 + 1 实验)
│ ├── cheat-trends/SKILL.md # ✅ 热点抓取(日常补充候选池,多 adapter)
│ ├── cheat-status/SKILL.md # ✅ 状态看板(含 buffer 警戒)
│ ├── cheat-migrate/SKILL.md # ✅ schema 升级(老用户 git pull 后用)
│ └── cheat-score-blind/SKILL.md # ✅ Channel B 隔离打分 sub-agent(仅 Task tool 调用)
├── migrations/ # schema 演进单一来源
│ ├── registry.md # ✅ LATEST_SCHEMA + 版本链表
│ └── <from>-to-<to>.md # ✅ 每步迁移的 WHAT/WHY/HOW/Manual fallback
├── shared-references/ # 跨 skill 共享协议
│ ├── blind-prediction-protocol.md # ✅ 原则 #1
│ ├── bump-validation-protocol.md # ✅ 原则 #2
│ ├── observation-lifecycle.md # ✅ 原则 #3
│ ├── prediction-anatomy.md # ✅ 一份合格预测的 7 个组件
│ ├── candidate-schema.md # ✅ 候选项统一 schema
│ ├── cadence-protocol.md # ✅ 节奏协议(buffer 警戒 + 选题策略)
│ ├── state-management.md # ✅ .cheat-state.json 读写约定
│ └── migration-protocol.md # ✅ schema 演进哲学 + maintainer checklist
├── starter-rubrics/ # 各内容形态的先验 rubric
│ ├── opinion-video.md # ✅ 观点视频(中文,已校准 25+ 样本)
│ ├── opinion-video-zero.md # ✅ v0 等权占位(cold-start)
│ ├── long-form-essay.md # ⬜ 公众号 / Substack
│ └── short-form-text.md # ⬜ X thread / 微博长文
├── templates/ # skill 写进用户 repo 的文件骨架
│ ├── gitignore.template # ✅ 用户项目 .gitignore(护凭证,保留 predictions/ 入库)
│ ├── rubric_notes.template.md # ✅
│ ├── prediction.template.md # ✅ 统一版(所有阶段,含 confidence header)
│ ├── retro.template.md # ✅
│ ├── candidates.template.md # ✅
│ ├── candidates.template.json # ✅
│ ├── script_patterns.template.md # ✅ 写作 pattern 沉淀(含 benchmark 借鉴段说明)
│ ├── benchmark.template.md # ✅ 对标账号 reference
│ ├── audience.template.md # ✅ 受众画像骨架
│ ├── workflow.template.md # ✅
│ ├── status.template.md # ✅
│ └── content.db.schema.sql # ✅
├── hooks/ # harness 强制层
│ ├── prediction-immutability.json # ✅ 阻塞型钩子(拦预测段编辑)
│ ├── prediction-immutability.sh # ✅ 拦截脚本
│ ├── session-start.json # ✅ SessionStart 自动报告 hook
│ ├── session-start.sh # ✅ 状态报告渲染脚本
│ ├── meta-logging.json # ✅ 被动记录配置
│ └── log-event.sh # ✅ meta-logging 脚本
├── tools/ # 独立 CLI 脚本
│ ├── score-curve.py # ⬜ 预测精度收敛曲线
│ ├── md-to-sqlite.py # ⬜ markdown → content.db 升级(批次 3)
│ └── validate-bump.py # ⬜ 校准池全量重打(批次 3)
├── adapters/ # 数据源适配
│ ├── perf-data/ # 复盘数据源(含 douyin-session)
│ ├── candidate-pool/ # 候选池数据源
│ ├── trend-sources/ # 热点抓取源
│ └── script-extraction/ # 视频/音频转 script(含 whisper for cheat-learn-from)
└── examples/
├── reference-implementation/ # 视频分析脱敏快照(待)
└── script_patterns.example.md # script_patterns 全填示例(参考用,不复制)✅ = 当前批次(v1 骨架)已完成 / ⬜ = 后续批次
写面向用户的文案(commit message / 复盘小结等)时,匹配项目的 直白克制(reflective-irreverent) voice:
rubric_notes.md 或预测日志starter-rubrics/<form>.mdadapters/trend-sources/<name>.md,符合 candidate-schema.md 输出契约shared-references/<protocol>.md,所有引用它的 skill 自动跟进skills/cheat-*/SKILL.md完整开发指南见 README.md。
© XBuilderLAB, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 120 other files in the repository root of XBuilderLAB/cheat-on-content.
Open the folder on GitHubat commit 2d8211e
Cheat on Content Calibration next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Cheat on Content Calibration this skillXBuilderLAB/cheat-on-content | 7.2k | — | ~2.7k | Automated safety check: Notes | MIT | |
| Content ForecastColinjqq/content-forecast | 189 | — | ~412 | Automated safety check: Pass | MIT | |
| WeChat Hot Article AnalysisSpaceZephyr/creator-buddy | 1.6k | — | ~847 | Automated safety check: Pass | None | |
| AI Design Teamjinggreen15/ai-design-team | 194 | — | ~614 | Automated safety check: Pass | None | |
| X Algorithm Post Writingcarson2222/skills | 113 | — | ~3.8k | Automated safety check: Pass | Apache-2.0 | |
| Content Calendar Plannerholaboss-ai/holaOS | 11k | — | ~568 | Automated safety check: Pass | Custom licence |
Colinjqq/content-forecast
Helps video creators pick topics from their own experience, diagnose how a script may spread and compare its expected performance with their own baseline.
SpaceZephyr/creator-buddy
Fetches hot WeChat Official Account articles by sector or keywords and produces a data file and an HTML report with rankings, style patterns and writing references.
jinggreen15/ai-design-team
Coordinates nine creative roles, from brief analyst to project manager, so a brand, content or design task reaches the right specialist in a sensible order.
carson2222/skills
Writes and reviews X posts, threads and replies using what the open-sourced For You ranking system rewards, and explains why a post may have underperformed.
holaboss-ai/holaOS
Builds a weekly or monthly content calendar with topics, platforms, formats and posting times, anchored to a stated goal, content mix and cadence.
manojbajaj95/claude-gtm-plugin
Comprehensive social media management for all platforms (LinkedIn, Twitter/X, Instagram, TikTok, Facebook, Pinterest, YouTube).
XBuilderLAB/cheat-on-content
Proposes and applies upgrades to a content-scoring rubric: a full formula bump with blind re-scoring and a cross-model audit, or a lighter bucket-boundary recalibration.
XBuilderLAB/cheat-on-content
Onboards a new user to the cheat-on-content workflow with a short question flow, creating the project scaffolding and optionally importing past video history.
XBuilderLAB/cheat-on-content
Imports scripts and engagement numbers from an account you want to emulate, then extracts content patterns and starting scoring signals from them.
XBuilderLAB/cheat-on-content
Upgrades an older .cheat-state.json to the current schema version by applying migration files in order, with dry-run, backup and stop-on-failure behavior.
XBuilderLAB/cheat-on-content
Builds or refreshes an account's audience profile from the comments in its post retrospectives and writes it to audience.md for later topic and script work.
XBuilderLAB/cheat-on-content
Writes an immutable blind prediction log for a finished content draft: a seven-dimension score, bucket, probability distribution and counterfactuals, scored blind by a sub-agent.
Works with
Categories
Turns content creation into a calibrated loop of scoring, blind prediction, post-publish review and rubric evolution, with a built-in rubric for opinion videos. The method is a five-stage loop of scoring a draft, predicting its performance, publishing, reviewing the result and evolving the rubric, and it applies to anything measurable, such as video views, article reads, podcast listens or clicks. The built-in rubric is for opinion videos, with seven dimensions fitted from more than 25 reference posts; other formats need their own rubric, using a starter file as the format guide.
Cheat on Content Calibration fits situations like: scoring a video script against a rubric before filming; writing a blind prediction of how a post will perform; reviewing real results after publishing and updating the rubric; learning from benchmark accounts to set initial signals.
Run `npx skills add XBuilderLAB/cheat-on-content --skill cheat-on-content -a claude-code`. Or copy the skill folder (the XBuilderLAB/cheat-on-content repository) into .claude/skills/cheat-on-content in your project. Claude Code loads it when a task matches its description.
Run `npx skills add XBuilderLAB/cheat-on-content --skill cheat-on-content -a codex`. Or copy the skill folder (the XBuilderLAB/cheat-on-content repository) into .agents/skills/cheat-on-content in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add XBuilderLAB/cheat-on-content --skill cheat-on-content -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cheat-on-content, .gemini/skills/cheat-on-content, .github/skills/cheat-on-content and .opencode/skills/cheat-on-content in your project.
Going by SKILL.md and its folder, Cheat on Content Calibration needs Python and a shell for the scripts in its folder. Our summary lists: Python, for the bundled performance-data adapters; Performance numbers from the platform after publishing, such as views, reads, listens or clicks. Its frontmatter pre-approves these tools: Bash(*), Read, Write, Edit, Grep, Glob, Skill, mcp__llm-chat__chat.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Cheat on Content Calibration is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Cheat on Content Calibration: Content Forecast (Colinjqq/content-forecast, 189 stars), WeChat Hot Article Analysis (SpaceZephyr/creator-buddy, 1.6k stars), AI Design Team (jinggreen15/ai-design-team, 194 stars) and X Algorithm Post Writing (carson2222/skills, 113 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
XBuilderLAB (a GitHub organization) maintains it in XBuilderLAB/cheat-on-content, which has 7,225 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 5, 2026.
Source: XBuilderLAB/cheat-on-content on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.