bytedance/agentkit-samples is a collection of examples and tutorials for Volcengine AgentKit, an AI-agent development platform for building, deploying, and operating agent applications. Developers use the samples to learn agent creation, multi-agent collaboration, memory, retrieval, MCP integrations, media generation, customer service, and other workflows. The catalogue skills provide agent workflows based on these examples.
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 bytedance/agentkit-samples --skill byted-kickart-marketing-material-generatorgit clone --depth 1 https://github.com/bytedance/agentkit-samplesWrote 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/bytedance/agentkit-samples/byted-kickart-marketing-material-generator)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-kickart-marketing-material-generator"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-kickart-marketing-material-generator/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/bytedance/agentkit-samples/byted-kickart-marketing-material-generator"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-kickart-marketing-material-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00120 | $0.02718 |
| Opus 5 | $0.00060 | $0.01359 |
| Sonnet 5 | $0.00024 | $0.00544 |
| Haiku 4.5 | $0.00012 | $0.00272 |
Grade A, and why
byted-kickart-marketing-material-generator 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 11d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
抖店营销短视频生成SKILL
🚨 强制前置校验流程（必须按顺序执行，任意不通过直接终止流程）
所有用户请求必须先完成以下4步校验，不得跳过：
- 模型输入能力校验
- 读取openclaw.json配置文件，检查当前默认使用的模型input配置是否包含"image"
- 若不包含image输入支持：提示用户需要为模型添加image输入支持，否则会影响图片/视频素材上传和处理功能，并询问用户是否需要帮助配置image输入，终止流程
- 火山鉴权校验
- 读取
./references/火山鉴权指南.md，检查本地是否已配置环境变量 - 未配置：引导用户按指南完成密钥配置，终止流程
- 读取
- 套餐有效性校验
- 读取
./references/套餐开通指南.md，调用套餐查询接口检查用户套餐是否在有效期内、创点余额充足 - 套餐失效/余额不足：引导用户按指南升级/充值套餐，终止流程
- 读取
🚫 任务提交与重试铁则（强制遵守，零例外）
- 绝对禁止主动重新提交任务：所有异步任务（素材分析/创意分析/故事板/视频生成）提交成功后，必须立即将后端返回的全局唯一
Task ID持久化存储（保留72小时，与后端任务结果有效期一致）。无论本地exec会话/状态是否丢失、异常中断，都只会通过已持久化的Task ID查询后端真实任务状态，永远不会自行发起重复提交。 - 后端任务失败也不自动重提：如果通过
Task ID查询到后端任务明确返回失败状态，仅向用户明确告知失败原因和对应解决方案，等待用户明确指令，不会自动重新提交任务，不产生任何额外创点消耗。 - 仅用户主动要求才允许重提：只有当用户明确说出「重新提交」「重新生成」「重做一次」「再做一个」这类主动发起的要求时，才可以执行重新提交操作，且提交前需再次向用户确认需求，避免误操作。
🎯 意图判断与依赖处理规则（基于对话历史自动识别）
结合当前用户输入和历史记录，按以下优先级判断意图：
- 进度查询最高优先级匹配：
- 用户提及「查询进度」「查看结果」「生成怎么样了」「好了吗」等关键词时，优先触发进度查询流程，强制加载
./references/任务查询指南.md，无需依赖其他任务上下文判断，直接执行标准化查询流程
- 用户提及「查询进度」「查看结果」「生成怎么样了」「好了吗」等关键词时，优先触发进度查询流程，强制加载
- 明确关键词匹配（次优先级）：
- 素材上传：用户提及「上传素材」「添加图片」「添加视频」「自定义素材」
- 素材分析：用户提及「素材分析」「分析商品」「拉取素材」
- 创意分析：用户提及「创意分析」「卖点分析」「受众分析」「创作方向」
- 故事板创作：用户提及「故事板」「分镜」「脚本」「故事构思」
- 视频生成：用户提及「生成视频」「成片」「导出视频」「制作短视频」
- 视频发布：用户提及「生成发布二维码」「视频发布」「发布抖音」「跳转发布」
- 无明确意图处理：
- 用户仅发送商品链接未说明需求：询问用户需要的操作（素材分析/创意分析/故事板创作/直接生成短视频）
🛠️ 各任务执行指南
| 任务类型 | 执行依据 | 输出要求 | 前置要求 |
|---|---|---|---|
| 进度查询 | 读取references/任务查询指南.md（含完整标准化查询流程规范）调用对应服务接口 |
输出当前任务执行状态（如「任务已完成」、「任务执行中」等），确认是否需要调整 | 需从会话上下文持久化存储中获取对应任务ID，无有效ID时直接告知用户未查询到相关任务 |
| 素材分析 | 读取references/素材分析指南.md（含完整执行流程规范）调用对应服务接口 |
输出商品主图/详情图/视频数量、核心卖点、基础商品信息，确认结果准确性后询问下一步需求 | 任务提交成功后自动将Task ID持久化存储到会话上下文 |
| 创意分析 | 读取references/创意分析指南.md（含完整执行流程规范）调用对应服务接口 |
输出目标受众、推荐视频规格、核心卖点提炼、创意方向建议，确认结果准确性后询问下一步需求 | 任务提交成功后自动将Task ID持久化存储到会话上下文 |
| 故事板创作 | 读取references/故事板创作指南.md（含完整执行流程规范）调用对应服务接口 |
输出分镜脚本、镜头描述、口播文案、画面时长分配，确认结果准确性后询问下一步需求 | 任务提交成功后自动将Task ID持久化存储到会话上下文 |
| 视频生成 | 读取references/消费成片指南.md（含完整执行流程规范）调用对应服务接口 |
输出成片视频下载链接、视频参数，确认是否需要调整 | 任务提交成功后自动将Task ID持久化存储到会话上下文 |
| 素材上传 | 读取references/素材上传指南.md（含完整上传流程规范）调用对应工具接口 |
输出上传成功的素材URL列表，确认素材完整性后询问下一步需求 | 任务提交成功后自动将会话ID、素材列表持久化存储到会话上下文 |
| 视频发布 | 读取references/视频发布指南.md（含完整二维码生成和发布流程规范）调用对应脚本接口 |
输出抖音发布跳转二维码（图片形式）、使用说明，提醒用户扫码即可跳转发布 | 前置要求：已获取到成片视频公网下载链接，且用户提供了发布文案内容 |
What ships with it
22 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.
- LICENSE 9.9 KB
- references/graph.md 1.3 KB
- references/任务查询指南.md 4.3 KB
- references/创意分析指南.md 5.9 KB
- references/套餐开通指南.md 3.2 KB
- references/故事板创作指南.md 3.4 KB
- references/消费成片指南.md 3.7 KB
- references/火山鉴权指南.md 2.3 KB
- references/视频发布指南.md 3.6 KB
- references/素材上传指南.md 4.1 KB
- references/素材分析指南.md 3.1 KB
- scripts/base.py 1.0 KB runs code
- scripts/chunks.py 32 KB runs code
- scripts/consumption.py 6.2 KB runs code
- scripts/creative.py 3.2 KB runs code
- scripts/material.py 3.1 KB runs code
- scripts/media.py 5.8 KB runs code
- scripts/publish.py 2.5 KB runs code
- scripts/requirements.txt 141 B
- scripts/service.py 7.0 KB runs code
- scripts/servicev1.py 4.6 KB runs code
- scripts/storyboard.py 2.1 KB runs code
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.
- 11d ago First seen · 89 lines · 120 tokens per session scan A 7d844b1c6007
byted-kickart-marketing-material-generator is a skill published in the GitHub repository bytedance/agentkit-samples (450 stars, last pushed yesterday), licensed Apache-2.0. It adds 120 tokens to every session and 2,718 once invoked, about $0.0006 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
build-monetized-app
Use when the task is building a new app on Eliza Cloud that earns money — chat apps, agent apps, MCP-backed tools, anything that calls the cloud's chat/messages/inference endpoints on behalf of users. Covers app registration, container deploy, markup configuration, affiliate header, app charge requests, x402 payment…
eliza-cloud-buy-domain
Use whenever a user wants to register or buy a custom domain for an Eliza Cloud app — including in the same request as building the app ("build me X and put it on Y.com"). Uses Cloudflare as registrar after explicit user confirmation, paid from the user's existing cloud credit balance. Pairs with build-monetized-app…
ordercli
Foodora CLI for checking past orders and active order status. Use when the user asks to check food delivery orders, track a Foodora delivery, view order history, reorder a meal, look up past food orders, check delivery status, or manage Foodora sessions and authentication.
personal-shopper
Personal advisor for a problem that might be solved by buying something — diagnoses the real need through conversation, then recommends products from the user's configured stores only when a purchase is the right answer. Recalls the user's sizes, budget, brands and restrictions across sessions, and records new ones as…
meituan-deals
A Meituan assistant for finding food deals, collecting coupons, and placing restaurant group-buy orders. Meituan is a Chinese local-services platform for dining and other everyday purchases.
ecom-details-image
A planning tool for e-commerce product visuals, including main-image concepts, scene ideas, detail-page directions, and prompts for image-generation systems.