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-game-replicatorgit 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-game-replicator)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-kickart-game-replicator"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-kickart-game-replicator/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-game-replicator"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-kickart-game-replicator.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 | $0.00093 | $0.02989 |
| Opus 5 | $0.00046 | $0.01494 |
| Sonnet 5 | $0.00019 | $0.00598 |
| Haiku 4.5 | $0.00009 | $0.00299 |
Grade A, and why
byted-kickart-game-replicator 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 8d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
游戏视频复刻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火山鉴权校验，不得跳过：
- 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（KICKART_ACCESS_KEY/KICKART_SECRET_KEY 或 ACCESS_KEY_ID/SECRET_ACCESS_KEY） - 未配置：引导用户按指南完成密钥配置，终止流程
- 配置后：通过
core/core.py的token()函数获取 x-muse-token，作为后续 OpenAPI 调用的凭证
- 读取
🎯 意图识别与任务执行指南（基于对话历史自动识别）
结合当前用户输入和历史记录判断意图后，必须严格读取并遵循对应的执行依据指南，不可凭空猜测执行步骤。
| 任务类型 | 触发意图与关键词 | 执行依据 (强制首要读取) | 输出要求 | 前置要求 |
|---|---|---|---|---|
| 进度查询 | 【最高优先级】用户提及「查询进度」「查看结果」「生成怎么样了」「好了吗」或查询某个具体任务ID的状态时。 | 读取 references/任务查询指南.md。⚠️绝对禁止不阅读指南直接调用任何脚本，严禁使用未经指南允许的内部 poll 命令！ |
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及本次提交所使用的 template_id，无有效ID时直接告知用户未查询到相关任务 |
| 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」 | 读取 references/素材上传指南.md |
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 |
| 游戏视频复刻 | 用户提及「游戏视频裂变」「游戏视频克隆」「复制游戏视频」「克隆游戏视频」「同款游戏视频」等，或者表达希望制作和某热门游戏视频一样的内容的等价意图时。 | 读取 references/游戏视频复刻指南.md |
输出复刻成片视频下载链接，确认结果并询问下一步需求 | 必须严格按照指南 Phase 0 逐步收集必填信息：参考视频（必填，MP4/MOV、>5s 且 ≤60s、≤50MB、≥480p）、角色图片（必填，1-10 张 JPEG/PNG、单张 ≤8MB、≥480p）、游戏名称（必填，≤500 字符）、语言（必填，必须列出指南中支持的全部语言供用户选择，不得省略或者自行编造）、模板 ID（必填，604911874 专业模式 / 463631106 进阶模式，二选一，必须由用户明确输入，不得由技能自行选择或复用历史）。场景参考图（0-3 张）和创意 prompt 为可选。用户不得以任何理由绕过必填步骤，未完成前严禁提交任务。🚨 强制二次确认要求：在完成所有必填信息收集后、提交任务前，必须按指南步骤 8「展示成片信息」和步骤 9「二次确认与合规提示」向用户展示成片信息并等待用户明确确认。此步骤为强制要求，不可因为鉴权失败重试、参数调整或其他任何原因跳过。 即使用户已完成鉴权或之前已确认，每次提交新任务前都必须重新展示成片信息并获取用户确认。 |
| 视频参考 | 用户主动提供参考视频、视频链接，或表示要上传视频时 | 读取 references/视频参考指南.md |
获取符合规范的参考视频链接或素材ID，为复刻做准备 | 用户触发游戏视频复刻意图时首要的前置步骤 |
| 数字形象 | 用户提及「添加模特」「自定义角色」「模特出镜」「数字人」「自定义模特」时 | 读取 references/数字形象指南.md |
获取符合规范的角色图片媒资ID，作为必填的 role_images 传入 |
用户在游戏视频复刻任务中获取角色图片时触发；本任务角色图片为必填项 |
⚠️ 错误处理规范
所有错误必须明确告知原因和可执行解决方案，禁止模糊提示！！！
通用错误码
| 错误码 | 错误类型 | 错误描述 | 详细说明 | 用户处理建议 |
|---|---|---|---|---|
| 0 | Success | 任务成功 | 任务处理完成，结果已生成 | - |
| 1000 | AsyncTaskRunning | 任务运行中 | 任务正在处理，请稍后通过查询接口轮询结果 | - |
| 1300 | AuthFailed | 认证失败 | token 无效、过期或未激活 | 请检查您提供的火山鉴权 AK/SK 是否正确，可访问火山引擎控制台确认 |
| 1400 | ParamErr | 参数错误 | 请求中包含无效或缺失的参数 | 请对照文档检查请求体结构、字段类型和必填项 |
| 1401 | ConcurrentErr | 并发超限 | 当前的并发请求数超过了约定的上限 | 请降低请求频率，或联系商务代表调整并发额度 |
| 1402 | InsufficientPoints | 创点不足 | 账户余额不足以支付本次任务消耗 | 请前往 创点充值页面 充值创点或升级套餐 |
| 1403 | QuotaErr | 无权限 | 账户没有调用此接口的权限 | 请联系企业管理员为您开通相关服务的访问权限 |
| 1500 | InternalErr | 内部错误 | 服务端发生未知错误 | 请记录 request_id 并联系技术支持 |
What ships with it
27 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.
- config.json 108 B
- LICENSE 9.9 KB
- references/kickart接口协议.md 10 KB
- references/任务查询指南.md 4.1 KB
- references/数字形象指南.md 4.3 KB
- references/游戏视频复刻指南.md 8.2 KB
- references/火山鉴权指南.md 2.7 KB
- references/视频参考指南.md 3.4 KB
- references/素材上传指南.md 3.2 KB
- scripts/core/__init__.py 1.7 KB runs code
- scripts/core/api/call_api.py 7.2 KB runs code
- scripts/core/api/meida/chunks.py 17 KB runs code
- scripts/core/api/meida/media.py 11 KB runs code
- scripts/core/auth/__init__.py 0 B runs code
- scripts/core/auth/strategy.py 1007 B runs code
- scripts/core/avatar.py 2.0 KB runs code
- scripts/core/core.py 7.8 KB runs code
- scripts/core/refer.py 2.0 KB runs code
- scripts/core/upload.py 2.0 KB runs code
- scripts/core/utils/downloader.py 9.1 KB runs code
- scripts/core/utils/extractor.py 4.7 KB runs code
- scripts/core/utils/hash.py 1.4 KB runs code
- scripts/core/utils/matriel.py 867 B runs code
- scripts/core/utils/validator.py 2.8 KB runs code
- scripts/query.py 4.4 KB runs code
- scripts/requirements.txt 189 B
- scripts/submit.py 10 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.
- 8d ago First seen · 94 lines · 93 tokens per session scan A eb280ab173c3
byted-kickart-game-replicator is a skill published in the GitHub repository bytedance/agentkit-samples (450 stars, last pushed 5d ago), licensed Apache-2.0. It adds 93 tokens to every session and 2,989 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
image-generation
Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.
podcast-generation
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.
brandkit
Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional…
sn-image-base
Base-layer skill for the SenseNova-Skills project, providing low-level APIs for image generation, recognition (VLM), and text optimization (LLM). This skill does not preprocess inputs; it only calls backend services and returns results. This skill is not user-facing and is intended for upper-layer skills only.
video-still-animator
Turn a single still image (PNG/JPG) into a short MP4 with a slow Ken-Burns zoom and a silent audio track. Pure ffmpeg wrapper. Designed as the onfailure substitute for AI video-gen steps that get blocked by content moderation: when seedance refuses, this skill emits a valid replacement clip from the already-generated…
spotify-player
Terminal Spotify playback/search via spogo (preferred) or spotifyplayer. Use when the user asks to play music, search for a song, skip a track, pause playback, check what is currently playing, control Spotify, list audio devices, or manage a Spotify queue from the terminal.