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-ark-seedance-pegit 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-ark-seedance-pe)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-ark-seedance-pe"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-ark-seedance-pe/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-ark-seedance-pe"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-ark-seedance-pe.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 | $0.00099 | $0.02602 |
| Opus 5 | $0.00049 | $0.01301 |
| Sonnet 5 | $0.00020 | $0.00520 |
| Haiku 4.5 | $0.00010 | $0.00260 |
Grade A, and why
byted-ark-seedance-pe 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Seedance PE - 原始视频提示词优化技能
核心功能
本技能接收用户提供的原始、非正式的视频提示描述,进行分析,并将其优化整理为符合 Seedance 2.0 工程化要求的标准结构化提示词。
使用场景
- 用户提供了一段粗糙的视频描述,要求"帮我优化这个提示词"
- 用户分享了一段无结构的原始提示词,希望打磨它以获得更好的视频生成结果
- 需要从杂乱输入中提取关键要素(主体、动作、风格、氛围、构图、光影、运镜等)并正确组织
- 用户提供可公开分享的完整请求体内容,希望提取其中的文本提示词并优化
⚠️ 重要前置要求(必须遵守)
每次收到用户的提示词优化请求,在开始优化前,必须完整阅读以下六个参考文档的内容,确保掌握所有规则、最佳实践和典型效果问题处理案例后再进行优化工作。这是保证输出质量的核心前提,不可跳过。
参考资料
本技能依赖以下参考资料,优化时必须结合所有资料中的最佳实践:
references/prompt-guide.md- Seedance 2.0 官方提示词指南,包含各类场景基础句式references/api-doc-rules.md- API 文档中的规则总结references/business-guide-examples.md- 各行业优秀提示词示例集锦references/engineering-prompt-methodology.md- 工程化提示词方法论references/seedance-2-troubleshooting-guide.md- Seedance 2.0 参考生视频常见问题与处理指南references/typical-effect-cases.md- Seedance 2.0 典型效果问题调优案例参考,包含人首部、音频台词、整体画质、多人、风格、字幕、视频编辑、视频延长、道具动物、比例参数等典型问题的原因与优化建议
硬性要求:六个文档是本技能的知识基础,每次优化前都必须重读,确保规则不遗忘、示例可借鉴、典型问题处理策略可复用、输出质量稳定。
工作流程
第一步:判断输入类型
首先判断用户输入是原始提示词、完整请求体,还是仅有任务 ID:
- 原始提示词:直接进入第二步解析。
- 完整请求体:从请求体中提取文本提示词,并仅保留公开 API 需要的通用字段(如
model/content/ratio/duration/resolution/generate_audio)用于后续生成;不要保留或依赖内部字段。 - 仅有 Task ID(如
cgt-xxx):不要尝试通过 task id 查询原始提示词或请求体。请告知用户不具备任务查询能力,并请用户直接提供原始提示词或可公开分享的完整请求体内容。
第二步:接收并解析原始提示词
仔细阅读用户的原始输入,识别所有提到的关键要素:
- 主体:视频的主要拍摄对象
- 动作/剧情:视频中正在发生什么
- 场景/位置:事件发生在哪里
- 风格:艺术风格、视频类型(电影感、动漫、写实等)
- 情绪/氛围:整体情感基调(戏剧性、平静、活力等)
- 光影:光照条件(黄金时刻、柔光、戏剧性、霓虹等)
- 运镜:镜头类型、运动方式(远景、特写、推镜等)
- 时长/节奏:时间分配、节奏快慢
- 其他细节:任何其他特定要求
第三步:分析缺口和歧义
检查哪些信息缺失会帮助生成更好的视频:
- 描述不清晰的地方
- 对视频重要的关键要素缺失
- 模糊词汇,可以更具体
- 指示冲突
如果缺失重要信息,询问用户澄清。对于微小缺口,根据上下文做出合理假设并在输出中说明。
第四步:构建优化后的提示词
按照 Seedance 官方标准三段论结构组织信息,融合工程化方法论中的最佳实践:
标准结构(严格遵守):
- 全局基础设定:锁定角色、环境与核心资产,使用
@图N语法明确声明映射关系- 如果有首尾帧约束,在此处声明
- 必须明确
@图N对应的角色/场景名称
- 时间片分镜脚本:按时间切片(如 0-3s, 3-10s),每个切片包含:
- 谁在哪做什么
- 一种运镜方式
- 必须使用带有
@图N的强视觉指代,指代后紧跟名称防止歧义
- 编辑指令(仅视频编辑场景需要):
- 增删改:明确时间段和空间位置
- 延长/拼接:使用标准语法
- 文字生成:明确内容、时机、位置
- 画质、风格与约束:自动挂载:
- 画质增强:
4K 高清,细节丰富 - 防崩坏兜底约束:
面部稳定不变形、五官清晰、人体结构正常、动作自然流畅、不僵硬、画面无卡顿、无闪烁
- 画质增强:
What ships with it
6 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.
- 11d ago First seen · 188 lines · 99 tokens per session scan A 13c91fb97797
byted-ark-seedance-pe is a skill published in the GitHub repository bytedance/agentkit-samples (450 stars, last pushed yesterday), licensed Apache-2.0. It adds 99 tokens to every session and 2,602 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
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
sn-image-imitate
An image tool that creates new content while following the visual style and layout of a single reference image.