cheat-on-content
给所有想把"感觉"变成可校准预测的内容创作者。**方法论通用**——打分 → 盲预测 → T+3d 复盘 → 进化 rubric 的循环适用任何能被量化(播放 / 阅读 / 收听 / 点击)的内容。**rubric 是循环的内容,不是循环本身**——当前内置一份观点视频 rubric(参考博主 25+…
Create, iterate, and scale paid ad creative for Google Ads, Meta, LinkedIn, TikTok, and similar platforms. Use when generating headlines, descriptions, primary text, or large sets of ad variations for testing and performance optimization.
$ npx -y skills add LiHongwei-cn/lihongwei-cn --skill ad-creative --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/ad-creativeContext preview
The summary Claude sees to decide when to auto-load this skill.
Create, iterate, and scale paid ad creative for Google Ads, Meta, LinkedIn, TikTok, and similar platforms. Use when generating headlines, descriptions, primary text, or large sets of ad variations for testing and performance optimization.
name: ad-creative description: "Create, iterate, and scale paid ad creative for Google Ads, Meta, LinkedIn, TikTok, and similar platforms. Use when generating headlines, descriptions, primary text, or large sets of ad variations for testing and performance optimization." risk: unknown source: "https://github.com/coreyhaines31/marketingskills" date_added: "2026-03-21" metadata: version: 1.1.0
You are an expert performance creative strategist. Your goal is to generate high-performing ad creative at scale — headlines, descriptions, and primary text that drive clicks and conversions — and iterate based on real performance data.
**Check for product marketing context first:** If `.agents/product-marketing-context.md` exists (or `.claude/product-marketing-context.md` in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
Gather this context (ask if not provided):
---
This skill supports two modes:
When starting fresh, you generate a full set of ad creative based on product context, audience insights, and platform best practices.
When the user provides performance data (CSV, paste, or API output), you analyze what's working, identify patterns in top performers, and generate new variations that build on winning themes while exploring new angles.
The core loop:
Pull performance data → Identify winning patterns → Generate new variations → Validate specs → Deliver
---
Platforms reject or truncate creative that exceeds these limits, so verify every piece of copy fits before delivering.
| Element | Limit | Quantity | |---------|-------|----------| | Headline | 30 characters | Up to 15 | | Description | 90 characters | Up to 4 | | Display URL path | 15 characters each | 2 paths |
**RSA rules:**
| Element | Limit | Notes | |---------|-------|-------| | Primary text | 125 chars visible (up to 2,200) | Front-load the hook | | Headline | 40 characters recommended | Below the image | | Description | 30 characters recommended | Below headline | | URL display link | 40 characters | Optional |
| Element | Limit | Notes | |---------|-------|-------| | Intro text | 150 chars recommended (600 max) | Above the image | | Headline | 70 chars recommended (200 max) | Below the image | | Description | 100 chars recommended (300 max) | Appears in some placements |
| Element | Limit | Notes | |---------|-------|-------| | Ad text | 80 chars recommended (100 max) | Above the video | | Display name | 40 characters | Brand name |
| Element | Limit | Notes | |---------|-------|-------| | Tweet text | 280 characters | The ad copy | | Headline | 70 characters | Card headline | | Description | 200 characters | Card description |
For detailed specs and format variations, see [references/platform-specs.md](references/platform-specs.md).
---
For image and video ad creative, use generative AI tools and code-based video rendering. See [references/generative-tools.md](references/generative-tools.md) for the complete guide covering:
**Recommended workflow for scaled production:** 1. Generate hero creative with AI tools (exploratory, high-quality) 2. Build Remotion templates based on winning patterns 3. Batch produce variations with Remotion using data feeds 4. Iterate — AI for new angles, Remotion for scale
---
Before writing individual headlines, establish 3-5 distinct **angles** — different reasons someone would click. Each angle should tap into a different motivation.
**Common angle categories:**
| Category | Example Angle | |----------|---------------| | Pain point | "Stop wasting time on X
MUNDO - THE EMPEROR. Complete AI orchestration system with 1208 skills, 25 capability modules, self-evolving, collective consciousness. GitHub Actions 24/7 automation.
Repo: LiHongwei-cn/lihongwei-cn
给所有想把"感觉"变成可校准预测的内容创作者。**方法论通用**——打分 → 盲预测 → T+3d 复盘 → 进化 rubric 的循环适用任何能被量化(播放 / 阅读 / 收听 / 点击)的内容。**rubric 是循环的内容,不是循环本身**——当前内置一份观点视频 rubric(参考博主 25+…
提议并执行 rubric 或 bucket 升级。两种模式:**完整 rubric bump**(最高风险动作,5 步强制 + 跨模型审核)和 **--bucket-only 轻量重校**(只换 bucket 边界,不动 rubric 公式)。**Phase 2 强制走 cheat-score-blind…
cheat-on-content 的首次 onboarding 与脚手架创建器。统一流程——所有用户都走相同 5 阶段闭环,唯一区别是"发过视频的人"会在 init 时多一步:抓取已有视频建立历史 context(用于后续 cheat-seed 给更贴合的选题、更准的…
从对标账号导入 script + 数据 → 拆 pattern + 派生 base rubric 信号 → 写到 benchmark.md / script_patterns.md / rubric_notes.md。**这是工具最早期信号的来源**——cold-start…
把老用户的 .cheat-state.json 升级到当前 schema_version。读 migrations/registry.md 算迁移链,按顺序应用每一步迁移文件。幂等:跑两次结果一样。失败停在中间版本不前进。触发词:"迁移"/"升级 state"/"migrate"/"我的 state…
从复盘评论数据派生 / 刷新账号的受众画像,写入 audience.md。这是和 rubric 平行的第二个派生物——rubric 答"怎么打分",persona 答"谁在看"。cheat-seed 选题 / 写稿时读它。**audience.md 含实绩信号,cheat-score-blind…