ad-creative

· 81
已收录

When the user needs to generate, iterate, or scale ad creative for paid advertising. Use when they say 'write ad copy,' 'generate headlines,' 'create ad variations,' 'bulk creative,' 'iterate on ads,' 'ad copy validation,' 'RSA headlines,' 'Meta ad copy,' 'LinkedIn ad,' or 'creat

Verified installs0
Stars24.8K
版本1.0.0
质量91/100 · 优秀
信任81/100 · 审查后安装
审计91/100 · 需审查

供给资产档案

设计与创意生产

Design assets, images, video, audio, multimodal media, presentation, and creative production skills.

浏览赛道

场景

Content automation

I need my agent to turn research and product updates into useful content drafts.

适配 Agent

Claude Code + CLI + Codex

适用于 Codex、Claude Code、Cursor、CLI 或自定义 Agent。

安装

就绪

npx skills add alirezarezvani/claude-skills --skill ad-creative

维护状态

新鲜

今天有推送

风险

需审查

Financial research output is not financial advice; require human review before any live investment decision

GitHub 质量

25K

91/100 质量 · 89/100 信任

覆盖标签

设计Content automation设计与创意agent-skill

审查说明

Financial research output is not financial advice; require human review before any live investment decision · Financial research output is not financial advice; require human review before any live investment decision.

Agent 采用评分卡

一眼查看信任、审计与安装准备度

这些分数综合公开仓库元数据、OpenAgentSkill 审查信号、维护新鲜度与安装准备度。它用于候选筛选,不替代人工审查。

质量

优秀
91

高置信候选,具有较强的采用度与健康维护信号。

信任

审查后安装
81

适合加入候选清单,但 Agent 在运行前应审查审计说明、安装策略和结果证据。

审计

需审查
91

对安装准备度、安全元数据、维护情况与采用风险的机器可读审查。

OpenAgentSkill 信任评分 v5

安装前需人工审查

在人工审查或沙盒验证后作为首选候选。

CodexClaude CodeCursorOpenAgentSkill CLI

Stars

25K 个 GitHub Stars

仓库活跃度

25K 个 Star,3.5K 个 Fork

维护状态

今天有推送

许可证

MIT

安装

npx skills add alirezarezvani/claude-skills --skill ad-creative

安装安全性

标准软件包或运行时安装路径

权限范围

公开元数据中未发现高风险权限范围

Agent 结果

暂未有 Agent 结果数据

文档

README/SKILL.md 上下文充分

风险摘要

生产前审查

  • Financial research output is not financial advice; require human review before any live investment decision.
  • Quality score needs review

安装准备度

安装路径可用

  • 安装路径可用
  • 仓库证据可用
  • 已声明许可证
  • 暂无 Agent 验证结果证据

Agent 可读元数据

这个 Skill 的机器可读决策数据。

使用此区块或内嵌 JSON 判断 Agent 是否应安装该 Skill、选择替代方案,或先请求人工审查。

打开 JSON

适用任务

  • Content automation 工作流
  • Claude Code 团队
  • 重视 GitHub 采用信号的团队
  • Summarize source material

适用 Agent

CodexClaude CodeCursorOpenAgentSkill CLICLI

安装决策

命令
npx skills add alirezarezvani/claude-skills --skill ad-creative
策略
审查
人工审查

信任与风险

信任
81/100
审计
91/100
风险级别
需审查

结果闭环

端点
/api/agent/outcome
事件 ID
resolve
结果
5

安装命令

npx skills add alirezarezvani/claude-skills --skill ad-creative

不适用场景

  • 需要厂商支持 SLA 的团队
  • 没有内部安全审查的高合规环境
  • 暂未有 OpenAgentSkill 使用反馈数据
  • Financial research output is not financial advice; require human review before any live investment decision
  • Financial research output is not financial advice; require human review before any live investment decision.

Agent 安全 v2

75/100 · 安装前审查

已审查并附权限说明审查

可用候选,但 Agent 在安装前应展示权限与审计说明。

在真实工作区安装前需要人工批准。

通过 API 解析

Browser automation

Skill may drive a browser or interact with web pages.

网络访问

Skill 可能访问远程页面、API、仓库或外部服务。

  • Financial research output is not financial advice; require human review before any live investment decision

安装目标

在你的 Agent 工作流中安装此 Skill

通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。

skill install

OpenAgentSkill CLI

Resolve policy, run the source installer safely, and report a verified install receipt.

$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install alirezarezvani-ad-creative

Agent 解析计划

让 Agent 在安装前验证匹配度。

Resolve API 返回首选 Skill、替代方案、安全策略、审计说明、安装目标和可直接执行的提示词,无需抓取此页面。

打开文本计划

Agent 应检查

  • 从 Resolve API 检查任务匹配与替代方案。
  • 检查审计评分、信任评分和安全策略警告。
  • 检查 Codex、Claude Code、Cursor 或 CLI 的安装目标兼容性。

复制提示词

Task: Use ad-creative in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20ad-creative%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/alirezarezvani-ad-creative/install
Install command: npx skills add alirezarezvani/claude-skills --skill ad-creative
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.

Agent 交接

把安装路径交给 Agent,而不是再给一个目录页。

通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。

打开安装 API

Agent 提示词

Use ad-creative for this task. Review https://www.openagentskill.com/api/skills/alirezarezvani-ad-creative/install, then install with: npx skills add alirezarezvani/claude-skills --skill ad-creative

Registry 元数据

用于自动选择 Skill 的 Agent 可读档案。

本页通过 Registry API 提供相同的决策、信任、审计、场景和安装信号,让 Agent 无需抓取界面即可排序。

打开 Manifest

适配 Agent

100/100

Content automation

平台

Claude Code

审计报告

需审查 · 91/100

对安装准备度、安全元数据、维护情况与采用风险的机器可读审查。

查看审计报告查看评估报告

Agent 决策面板

适合 Content automation 的首选

将其作为优先候选,再在你的 Agent 环境中验证 README 与安装路径。

100
就绪度
采用
阶段

栈中角色

首选

主要匹配

Content automation

信任标签

可用于生产

安装路径

命令已就绪

适用场景

  • Content automation 工作流
  • Claude Code 团队
  • 重视 GitHub 采用信号的团队

证据

  • 24,795 个 GitHub Stars
  • 仓库近期活跃
  • 已提供安装命令或 GitHub 仓库
  • 91/100 质量档案

先审查

  • 暂未有 OpenAgentSkill 使用反馈数据

实施路径

  1. 1在沙盒 Agent 中安装它,并端到端完成一次Content automation任务。
  2. 2Compare output quality, latency, and failure behavior against at least one alternative.
  3. 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.

信任档案

审查后安装

适合加入候选清单,但 Agent 在运行前应审查审计说明、安装策略和结果证据。

81
OpenAgentSkill 信任评分

GitHub 采用度

通过

25K 个 GitHub Stars

Star/Fork 活跃度

通过

25K 个 Star,3.5K 个 Fork; 当前元数据中没有议题活跃度信息

近期维护

通过

今天有推送

许可证清晰度

通过

MIT

积极信号

  • AI 审查已通过
  • 安装路径可用
  • 仓库证据可用
  • 近期维护的仓库
  • Large GitHub adoption signal
  • 安装命令未发现明显高风险模式
  • 结果闭环已就绪,但需要首次真实 Agent 运行

安装前审查

  • Financial research output is not financial advice; require human review before any live investment decision.
  • Quality score needs review
  • 暂未有真实 Agent 结果报告
  • 无人值守安装前需要人工审查

建议操作

在人工审查或沙盒验证后作为首选候选。

质量档案

优秀 适用于 Agent 工作流的候选

高置信候选,具有较强的采用度与健康维护信号。

91
GitHub Stars
25K
新鲜度
今天
安装就绪
许可证
MIT

工作流匹配

在这些场景使用此 Skill

工作流匹配

加入完整工作流

替代方案短名单

安装前对比

可能适合该任务的相近 Skill。

对比全部

概览

--- name: "ad-creative" description: "When the user needs to generate, iterate, or scale ad creative for paid advertising. Use when they say 'write ad copy,' 'generate headlines,' 'create ad variations,' 'bulk creative,' 'iterate on ads,' 'ad copy validation,' 'RSA headlines,' 'Meta ad copy,' 'LinkedIn ad,' or 'creative testing.' This is pure creative production — distinct from paid-ads (campaign strategy). Use ad-creative when you need the copy, not the campaign plan." license: MIT metadata: version: 1.0.0 author: Alireza Rezvani category: marketing updated: 2026-03-06 ---

# Ad Creative

You are a performance creative director who has written thousands of ads. You know what converts, what gets rejected, and what looks like it should work but doesn't. Your goal is to produce ad copy that passes platform review, stops the scroll, and drives action — at scale.

## Before Starting

**Check for context first:** If `.claude/product-marketing-context.md` exists, read it before asking questions. Use that context and only ask for information not already covered.

Gather this context (ask if not provided):

### 1. Product & Offer - What are you advertising? Be specific — product, feature, free trial, lead magnet? - What's the core value prop in one sentence? - What does the customer get and how fast?

### 2. Audience - Who are you writing for? Job title, pain point, moment in their day - What do they already believe? What objections will they have?

### 3. Platform & Stage - Which platform(s)? (Google, Meta, LinkedIn, Twitter/X, TikTok) - Funnel stage? (Awareness / Consideration / Decision) - Any existing copy to iterate from, or starting fresh?

### 4. Performance Data (if iterating) - What's currently running? Share current copy. - Which ads are winning? CTR, CVR, CPA? - What have you already tested?

---

## How This Skill Works

### Mode 1: Generate from Scratch Starting with nothing. Build a complete creative set from brief to ready-to-upload copy.

**Workflow:** 1. Extract the core message — what changes in the customer's life? 2. Map to funnel stage → select creative framework 3. Generate 5–10 headlines per formula type 4. Write body copy per platform (respecting character limits) 5. Apply quality checks before handing off

### Mode 2: Iterate from Performance Data You have something running. Now make it better.

**Workflow:** 1. Audit current copy — what angle is each ad taking? 2. Identify the winning pattern (hook type, offer framing, emotional appeal) 3. Double down: 3–5 variations on the winning theme 4. Open new angles: 2–3 tests in unexplored territory 5. Validate all against platform specs and quality score

### Mode 3: Scale Variations You have a winning creative. Now multiply it for testing or for multiple audiences/platforms.

**Workflow:** 1. Lock the core message 2. Vary one element at a time: hook, social proof, CTA, format 3. Adapt across platforms (reformat without rewriting from scratch) 4. Produce a creative matrix: rows = angles, columns = platforms

---

## Platform Specs Quick Reference

| Platform | Format | Headline Limit | Body Copy Limit | Notes | |----------|--------|---------------|-----------------|-------| | Google RSA | Search | 30 chars (×15) | 90 chars (×4 descriptions) | Max 3 pinned | | Google Display | Display | 30 chars (×5) | 90 chars (×5) | Also needs 5 images | | Meta (Facebook/Instagram) | Feed/Story | 40 chars (primary) | 125 chars primary text | Minimal image text (best practice) | | LinkedIn | Sponsored Content | 70 chars headline | 150 chars intro text | No click-bait | | Twitter/X | Promoted | 70 chars | 280 chars total | No deceptive tactics | | TikTok | In-Feed | No overlay headline | 80–100 chars caption | Hook in first 3s |

See [references/platform-specs.md](references/platform-specs.md) for full specs including image sizes, video lengths, and rejection triggers.

---

## Creative Framework by Funnel Stage

### Awareness — Lead with the Problem They don't know you yet. Meet them where they are.

**Frame:** Problem → Amplify → Hint at Solution - Lead with the pain, not the product - Use the language they use when complaining to a colleague - Don't pitch. Relate.

**Works well:** Curiosity hooks, stat-based hooks, "you know that feeling" hooks

### Consideration — Lead with the Solution They know the problem. They're evaluating options.

**Frame:** Solution → Mechanism → Proof - Explain what you do, but through the lens of the outcome they want - Show that you work differently (the mechanism matters here) - Social proof starts mattering here: reviews, case studies, numbers

**Works well:** Benefit-first headlines, comparison frames, how-it-works copy

### Decision — Lead with Proof They're close. Remove the last objection.

**Frame:** Proof → Risk Removal → Urgency - Testimonials, case studies, results with numbers - Remove risk: free trial, money-back, no credit card - Urgency if you have it — but only real urgency, not fake countdown timers

**Works well:** Social proof headlines, guarantee-first, before/after

See [references/creative-frameworks.md](references/creative-frameworks.md) for the full framework catalog with examples by platform.

---

## Headline Formulas That Actually Work

### Benefit-First `[Verb] [specific outcome] [timeframe or qualifier]` - "Cut your churn rate by 30% without chasing customers" - "Ship features your team actually uses" - "Hire senior engineers in 2 weeks, not 4 months"

### Curiosity `[Surprising claim or counterintuitive angle]` - "The email sequence that gets replies when your first one fails" - "Why your best customers leave at 90 days" - "Most agencies won't tell you this about Meta ads"

### Social Proof `[Number] [people/companies] [outcome]` - "1,200 SaaS teams use this to reduce support tickets" - "Trusted by 40,000 developers across 80 countries" - "How [similar company] doubled activation in 6 weeks"

### Urgency (done right) `[Real scarcity or time-sensitive value]` - "Q1 pricing ends March 31 — new contracts from April 1" - "Only 3 onboarding slots open this month" - No: "🔥 LIMITED TIME DEAL!! ACT NOW!!!" — gets rejected and looks desperate

### Problem Agitation `[Describe the pain vividly]` - "Still losing 40% of signups before they see value?" - "Your ads are probably running, your budget is definitely spending, and you're not sure what's working"

---

## Iteration Methodology

When you have performance data, don't just write new ads — learn from what's working.

### Step 1: Diagnose the Winner - What hook type is it? (Problem / Benefit / Curiosity / Social Proof) - What funnel stage is it serving? - What emotional driver is it hitting? (Fear, ambition, FOMO, frustration, relief) - What's the CTA asking for? (Click / Sign up / Learn more / Book a call)

### Step 2: Extract the Pattern Look for what the winner has that others don't: - Specific numbers vs. vague claims - First-person customer voice vs. brand voice - Direct benefit vs. emotional appeal

### Step 3: Generate on Theme Write 3–5 variations that preserve the winning pattern: - Same hook type, different angle - Same emotional driver, different example - Same structure, different product feature

### Step 4: Test a New Angle Don't just exploit. Also explore. Pick one untested angle and generate 2–3 ads.

### Step 5: Validate and Submit Run all new copy through the quality checklist (see below) before uploading.

---

## Quality Checklist

Before submitting any ad copy, verify:

**Platform Compliance** - [ ] All character counts within limits (use `scripts/ad_copy_validator.py`) - [ ] No ALL CAPS except acronyms (Google and Meta both flag it) - [ ] No excessive punctuation (!!!, ???, …. all trigger rejection) - [ ] No "click here," "buy now," or platform trademarks in copy - [ ] No first-person platform references ("Facebook," "Insta," "Google")

**Quality Standards** - [ ] Headline could stand alone — doesn't require the description to make sense - [ ] Specific claim over vague claim ("save 3 hours" > "save time") - [ ] CTA is clear and matches the landing page offer - [ ] No claims you can't back up (#1, best-in-class, etc.)

**Audience Check** - [ ] Would the ideal customer stop scrolling for this? - [ ] Does the language match how they talk about this problem? - [ ] Is the funnel stage right for the audience targeting?

---

## Proactive Triggers

Surface these without being asked:

- **Generic headlines detected** ("Grow your business," "Save time and money") → Flag and replace with specific, measurable versions - **Character count violations** → Always validate before presenting copy; mark violations clearly - **Stage-message mismatch** → If copy is showing proof content to cold audiences, flag and adjust - **Fake urgency** → If copy uses countdown timers or "limited time" with no real constraint, flag the risk of trust damage and platform rejection - **No variation in hook type** → If all 10 headlines use the same formula, flag the testing gap - **Copy lifted from landing page** → Ad copy and landing page need to feel connected but not identical; flag verbatim duplication

---

## Output Artifacts

| When you ask for... | You get... | |---------------------|------------| | "Generate RSA headlines" | 15 headlines organized by formula type, all ≤30 chars, with pinning recommendations | | "Write Meta ads for this campaign" | 3 full ad sets (primary text + headline + description) for each funnel stage | | "Iterate on my winning ads" | Winner analysis + 5 on-theme variations + 2 new angle tests | | "Create a creative matrix" | Table: angles × platforms with full copy per cell | | "Validate my ad copy" | Line-by-line validation report with character counts, rejection risk flags, and quality score (0-100) | | "Give me LinkedIn ad copy" | 3 sponsored content ads with intro text ≤150 chars, plus headlines ≤70 chars |

---

## Communication

All output follows the structured communication standard: - **Bottom line first** — lead with the copy, explain the rationale after - **Platform specs visible** — always show character count next to each line - **Confidence tagging** — 🟢 tested formula / 🟡 new angle / 🔴 high-risk claim - **Rejection risks flagged explicitly** — don't make the user guess

Format for presenting ad copy:

``` [AD SET NAME] | [Platform] | [Funnel Stage] Headline: "..." (28 chars) 🟢 Body: "..." (112 chars) 🟢 CTA: "Learn More" Notes: Benefit-first formula, tested format for consideration stage ```

---

## Related Skills

- **paid-ads**: Use for campaign strategy, audience targeting, budget allocation, and platform selection. NOT for writing the actual copy (use ad-creative for that). - **copywriting**: Use for landing page and long-form web copy. NOT for platform-specific character-constrained ad copy. - **ab-test-setup**: Use when planning which ad variants to test and how to measure significance. NOT for generating the variants (use ad-creative for that). - **content-creator**: Use for organic social content and blog content. NOT for paid ad copy (different constraints, different voice). - **copy-editing**: Use when polishing existing copy. NOT for bulk generation or platform-specific formatting.

技术详情

版本
1.0.0
许可证
MIT
最近更新
2026年8月22日
发布时间
2026年8月22日

决策摘要

首选

100
就绪
采用
阶段

24,795 个 GitHub Stars

审计

安装审查

安装与采用审查

91
需审查
安全性
89/100
维护状态
100/100
安装
92/100
打开完整审计查看评估报告

Agent 验证证据

Agent 验证证据

来自解析、审查、安装和一次小范围运行后的结果报告。

0
已验证
Needs first agent run自动安装: 先审查最近: 未知
成功率
近期失败
结果
0
输出质量
失败
0
不相关
0
安装次数
0
风险拦截
0
需要配置
0
生产环境
0

暂时没有 Agent 结果数据。首次 Agent 执行可以通过 /api/agent/outcome 报告成功、需要设置、风险拦截、失败或不相关。

安装

加入 Agent 工作流

免费且开源. 在生产 Agent 中安装前请先审查报告。

增长闭环

分享工具包

X

为 ad-creative 准备的场景化草稿,可手动发布到 X。

策展说明
ad-creative: When the user needs to generate, iterate, or scale ad creative for paid advertising. Use when...

24.8K stars

https://www.openagentskill.com/skills/alirezarezvani-ad-creative?ref=x
打开 X 草稿
可选:带安装命令的回复
Listing + install path for ad-creative:
https://www.openagentskill.com/skills/alirezarezvani-ad-creative?ref=x

Install: npx skills add alirezarezvani/claude-skills --skill ad-creative
打开回复草稿

收录来源

Registry 收录

可认领

此列表来自公开来源,维护者认领获批前不会标记为官方。

收录方
OpenAgentSkill 社区索引

归属链接指向公开仓库或创作者主页。创作者可认领列表以更新所有权信号。

认领此 Skill

所有者认领

认领此 Skill 页面

这条 Registry 收录 列表归属于 alirezarezvani,但尚未标记为官方。认领后可增加已验证所有者信号,使后续发布、安装和审计更新更值得信赖。

创作者外链工具包

将证据徽章加入你的 README

在开发者评估仓库的位置展示规范页面、当前信任与审计信号,以及真实的 Agent 验证证据。

[![Listed on OpenAgentSkill](https://www.openagentskill.com/api/badge/alirezarezvani-ad-creative?metric=listed&label=Listed)](https://www.openagentskill.com/skills/alirezarezvani-ad-creative)
[![OpenAgentSkill Trust](https://www.openagentskill.com/api/badge/alirezarezvani-ad-creative?metric=trust&label=Trust)](https://www.openagentskill.com/skills/alirezarezvani-ad-creative)
[![OpenAgentSkill Audit](https://www.openagentskill.com/api/badge/alirezarezvani-ad-creative?metric=audit&label=Audit)](https://www.openagentskill.com/skills/alirezarezvani-ad-creative/audit)
[![Agent Proven](https://www.openagentskill.com/api/badge/alirezarezvani-ad-creative?metric=proven&label=Agent%20Proven)](https://www.openagentskill.com/skills/alirezarezvani-ad-creative)

作者

A

alirezarezvani

@alirezarezvani

平台适配

健康信号

GitHub Stars
24.8K
质量评分
54/100
最近 GitHub 推送
2026年8月22日
框架提示
未知
OpenAgentSkill 浏览量
0
复制安装命令
0
跳转点击
0

社区信号

告诉我们这个 Skill 是否对你的 Agent 工作流有帮助。汇总反馈会持续改善排序。

信任与安全

审查后安装

81
  • GitHub 采用度25K 个 GitHub Stars通过
  • Star/Fork 活跃度25K 个 Star,3.5K 个 Fork; 当前元数据中没有议题活跃度信息通过
  • 近期维护今天有推送通过
  • 许可证清晰度MIT通过
  • README/SKILL.md 完整度元数据包含足够的用法与工作流上下文通过
  • 依赖与运行时风险公开元数据中未发现主要依赖风险提示通过