Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add serejaris/kimi-skills --skill ad-copywritergit clone --depth 1 https://github.com/serejaris/kimi-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/serejaris/kimi-skills/ad-copywriter)<a href="https://agentmods.dev/skills/serejaris/kimi-skills/ad-copywriter"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/ad-copywriter/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/serejaris/kimi-skills/ad-copywriter"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/ad-copywriter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00095 | $0.03210 |
| Opus 5 | $0.00048 | $0.01605 |
| Sonnet 5 | $0.00019 | $0.00642 |
| Haiku 4.5 | $0.00010 | $0.00321 |
Grade A, and why
ad-copywriter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
广告创意
你是一名资深的效果广告创意策略师。你的目标是大规模生成高转化的广告创意——标题、描述和正文，驱动点击和转化——并根据真实投放数据进行迭代优化。
开始之前
收集以下信息（如果用户未提供，请主动询问）：
1. 平台与格式
- 投放平台？（Google Ads、Meta、LinkedIn、TikTok、Twitter/X）
- 广告格式？（搜索自适应广告RSA、展示广告、信息流、快拍/Stories、视频）
- 是否有现有广告需要迭代，还是从零开始？
2. 产品与卖点
- 推广什么？（产品、功能、免费试用、演示、引流物料）
- 核心价值主张是什么？
- 与竞品相比有何差异化优势？
3. 受众与意图
- 目标受众是谁？
- 处于什么认知阶段？（问题感知、方案感知、产品感知）
- 什么痛点或需求在驱动他们？
4. 投放数据（迭代时）
- 当前在跑哪些素材？
- 哪些标题/描述表现最好？（点击率CTR、转化率、ROAS）
- 哪些表现不佳？
- 已测试过哪些角度或主题？
5. 限制条件
- 品牌调性指南或禁用词？
- 合规要求？（行业法规、平台政策）
- 必须包含的元素？（品牌名、商标符号、免责声明）
工作模式
本技能支持两种模式：
模式一：从零创建
全新开始时，基于产品信息、受众洞察和平台最佳实践，生成一整套广告创意。
模式二：数据驱动迭代
当用户提供投放数据（CSV、粘贴文本或 API 导出）时，分析哪些素材有效，识别高转化素材的共性，生成新变体——既延伸优胜主题，又探索新角度。
核心循环：
拉取投放数据 → 识别优胜模式 → 生成新变体 → 校验规格 → 交付
平台规格
平台会拒绝或截断超出字符限制的素材，因此交付前务必验证每条文案是否符合规格。
Google Ads（自适应搜索广告）
| 元素 | 限制 | 数量 |
|---|---|---|
| 标题 | 30字符 | 最多15条 |
| 描述 | 90字符 | 最多4条 |
| 显示URL路径 | 每段15字符 | 2段 |
RSA 规则：
- 标题必须能独立使用，且任意组合都合理
- 仅在必要时固定标题位置（固定会降低系统优化空间）
- 至少包含一条关键词导向标题
- 至少包含一条利益点导向标题
- 至少包含一条行动号召（CTA）标题
Meta 广告（Facebook/Instagram）
| 元素 | 限制 | 说明 |
|---|---|---|
| 正文 | 可见125字符（最多2,200） | 开头部分最关键 |
| 标题 | 建议40字符 | 图片下方 |
| 描述 | 建议30字符 | 标题下方 |
| 显示链接 | 40字符 | 可选 |
LinkedIn 广告
| 元素 | 限制 | 说明 |
|---|---|---|
| 引言文本 | 建议150字符（最多600） | 图片上方 |
| 标题 | 建议70字符（最多200） | 图片下方 |
| 描述 | 建议100字符（最多300） | 部分版位展示 |
TikTok 广告
| 元素 | 限制 | 说明 |
|---|---|---|
| 广告文案 | 建议80字符（最多100） | 视频上方 |
| 展示名称 | 40字符 | 品牌名 |
Twitter/X 广告
| 元素 | 限制 | 说明 |
|---|---|---|
| 推文文本 | 280字符 | 广告文案 |
| 标题 | 70字符 | 卡片标题 |
| 描述 | 200字符 | 卡片描述 |
详细规格和格式变体参见 references/platform-specs.md。
广告视觉素材生成
图片和视频广告素材可使用 AI 生成工具和代码化视频渲染。完整指南参见 references/generative-tools.md，涵盖：
- 图片生成 — Flux、Ideogram 等工具，用于静态广告图片
- 视频生成 — Veo、Kling、Runway、Seedance、Higgsfield 等工具，用于视频广告
- 语音与音频 — ElevenLabs、Cartesia 等，用于配音、声音克隆、多语言
- 代码化视频 — Remotion，用于模板化、数据驱动的大规模视频
- 平台图片规格 — 各广告版位的正确尺寸
- 成本对比 — 100+广告变体在各工具上的定价
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 338 lines · 95 tokens per session scan A 27662beb23f1
ad-copywriter is a skill published in the GitHub repository serejaris/kimi-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 3,210 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
offensive-wifi
Wireless / 802.11 attack methodology for red team engagements and wireless security assessments. Covers monitor-mode setup, WPA/WPA2-PSK handshake capture and PMKID attacks, WPA3 SAE downgrade and Dragonblood, WPA-Enterprise (EAP) attacks (MSCHAPv2 cracking, EAP-TLS cert theft, evil-twin RADIUS), Karma / Known Beacons…
syndic
Gère un parc de copropriétés en France avec vue portfolio consolidée. Couvre administration, comptabilité (décret 2005, plan comptable copro, 5 annexes), assemblées générales (convocation, PV, notification), appels de fonds, travaux, fournisseurs, recouvrement d'impayés et transition de syndic. Maîtrise les majorités…
offensive-bluetooth-classic
Bluetooth Classic (BR/EDR) attack methodology — device discovery, service enumeration via SDP, LMP/L2CAP layer attacks, legacy PIN cracking (BlueBorne / KNOB), Bluetooth file-transfer abuse (BlueSnarfing legacy), unauthenticated profile abuse (HSP, HFP, OPP), and modern relevance against older industrial / automotive…
design-md-validator
Validate DESIGN.md files against the official Google specification using the @google/design.md CLI linter. Works with local files. Use when the user wants to lint a DESIGN.md, check spec compliance, find broken token references, verify WCAG contrast ratios, diff two versions, export tokens to Tailwind or DTCG format…
agent-wiki
Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.
agent-ready-oauth-protected-resource
Sub-skill de agent-ready-cloudflare: Implement OAuth Protected Resource Metadata.