Agentkit Samples

Volcengine VOD audio and video processing tools skill. Use when users need VOD-based media processing or editing: upload local/URL media, stitch videos, trim clips, flip frames, change playback speed, create image-to-video, compose audio/video, extract audio, mix audio, separate vocals/accompaniment, denoise audio, enhance quality, AI super-resolution, frame interpolation, ASR speech-to-text, OCR text extraction, subtitle removal, subtitle embedding, scene slicing, portrait/green-screen matting, highlight extraction, comic style transfer, video translation, drama recap narration, drama script restoration, media info lookup, or playback URL retrieval. The skill submits async VOD jobs, polls task status, and returns generated output links. Not for pure text generation, real-time streaming, or source-free generative video creation.

火山引擎费用中心账单分析技能，根据用户场景，使用 Python SDK 查询账单明细、成本账单明细、账号汇总、产品汇总与分账账单，支持按账期、分摊月、日期、产品、账号、实例、分拆项进行多维度的账单分析。

根据文字描述生成视频，一个生成图片和视频的工作流技能。依赖 skills: byted-web-search, image-generate, video-generate。注意：此 workflow 没有执行脚本，只是一个描述性的文档。

Upload files or directories to TOS-compatible object storage for Volcano Engine or BytePlus and download files from URLs. Use this skill when (1) Upload Agent-generated files or directories for sharing, (2) Download files from URLs before Agent processing.

根据用户的功能需求，完成与 VeADK-Go 相关的功能; 包括：直接根据需求生成 Agent；将Enio Agent转换为VeADK-Go Agent。

火山方舟 Seedance 模型使用指导技能。用户询问 Seedance/seedance2.0/doubao-seedance-2-0/doubao-seedance-2-0-fast/seedance2.0-mini等seedance系列模型的火山方舟接入、API 调用、参数、任务创建、任务查询、结果获取、计费开通、报错排查、SDK、最佳实践时优先调用本技能；当用户提供火山引擎官网文档链接（形如 https://www.volcengine.com/docs/*）并要求解读、总结、提炼、查询其中规则或基于文档回答时，也应调用本技能并通过 fetch 获取文档全文；普通提问使用 ServiceCodes: ark 检索火山方舟官方文档。

ByteHouse AI 查询技能，提供自然语言转 SQL（Text2SQL）、SQL 执行、库表结构查询、多模态向量化和向量检索等能力，覆盖 ByteHouse 云数仓的日常查询、SQL 生成与执行场景。当用户提到 "ByteHouse"、"查表"、"查数据"、"Text2SQL"、"自然语言查询"、"列出数据库"、"列出表"、"执行 SQL"、"生成 SQL"、"多模态检索" 等诉求，或者需要基于 ByteHouse 完成上述任务时，应使用本 Skill。

Downsamples, resizes, and compresses images using Volcengine LAS with multiple interpolation methods (lanczos, bilinear, nearest). Image resizing, image scaling, and image compression — reduces image resolution, dimensions, and file size. Changes and adjusts DPI settings. Converts between image formats including JPEG, PNG, TIFF. Generates thumbnails and optimizes images for web or print. Supports batch resize for photos and images up to 100MB and 225 megapixels. Note: downscale only, does not upscale. Use this skill when the user wants to resize or downscale images, compress images to reduce file size, change image format (JPEG/PNG/TIFF), adjust image DPI, generate image thumbnails, optimize images for web/print, or batch process multiple images.

产品需求文档（PRD）开发技能。帮助产品经理从需求分析到完整PRD文档的撰写，包含用户故事、功能规格、交互设计要求和验收标准。当用户需要编写产品需求文档、定义功能规格或制定验收标准时使用此技能。

使用火山引擎 MongoDB Skill，帮助用户完成 MongoDB 相关的实例管理、备份恢复、参数等运维任务，可直接调用 uv run ./scripts/call_mongodb.py 脚本获取实时结果。当需要访问管理在火山引擎 MongoDB 实例详细信息时，此 Skill 可以提供方便的接口。

围绕火山引擎对象存储 tosutil 生成与校验命令、规划桶/对象操作并诊断错误。用户提到 tosutil、TOS 桶对象管理、批量上传下载或相关排障时调用。

火山引擎官方文档查询工具，支持文档检索和全文获取。涵盖火山引擎全部产品、开发者工具、服务支持、最佳实践，包括产品介绍、使用、计费、部署、故障排查、API、SDK、服务条款/协议等全流程。任何涉及火山引擎产品咨询、使用问题、文档查询的需求都优先调用本技能。

Generate complete, runnable Volcengine SDK code and provide SDK configuration guidance. Supports Go, Python, PHP, Java, and Node.js. Trigger this skill whenever the user wants to call a Volcengine API, generate Volcengine SDK code, or describes a cloud operation on Volcengine (e.g., "list ECS instances", "create a VPC on Volcengine", "query Volcengine billing with Python"). Also trigger when the user asks about Volcengine SDK configuration and best practices — including retry, timeout, authentication (AK/SK, STS, AssumeRole), proxy, connection pooling, SSL, debug mode, and error handling (e.g., "how to configure retry for Volcengine Go SDK", "volcengine python sdk proxy setup"). Trigger when the user mentions Volcengine service names such as ECS, VPC, CDN, CLB, RDS, Redis, Kafka, billing, IAM, DNS with code generation or SDK usage intent. When the user only needs API specification queries (parameters, error codes, response structures), hand off to the volcengine-api skill. When the user needs CLI-based operat

火山引擎 AntiDDoSPro 高防域名只读巡检。用户要查域名健康、攻击、流量、CC/WAF/区域封禁、智能防护或 CCAI 状态时使用。

通用招聘平台候选人搜索与筛选技能。适用于多个招聘平台（LinkedIn、猎聘、脉脉等），包含候选人搜索、匹配度评分、筛选、打招呼等通用流程。

Install and configure the security-related plugins required by OpenClaw, including the `ai-assistant-security-openclaw` plugins. Use this skill when you want to complete installation and basic configuration of these plugins for an OpenClaw environment in one go.

Byted Security Llmscanner

This skill should be used when the user asks to "generate video prompts", "create Seedance prompts", "write video descriptions", mentions "Seedance", "seedance", "火山引擎", "火山引擎平台", "视频提示词", "视频生成", "AI视频", "短剧", "广告视频", "视频延长", or discusses video prompt engineering, AI video generation, or Seedance 2.0 workflows.

自动备份OpenClaw核心配置、技能文件和记忆数据到挂载的TOS网盘，按日期分类存储，自动跳过依赖目录和可执行文件。当你需要创建或恢复OpenClaw环境备份时使用此技能。

Optimize code performance through iterative improvements (max 2 rounds). Benchmark execution time and memory usage, compare against baseline implementations, and generate detailed optimization reports. Supports C++, Python, Java, Rust, and other languages.

Manage AgentKit skills, SkillHub/skillhub, skill centers, and skill spaces. Use this skill whenever the user has a management intent for AgentKit skills, skill中心, skill 空间, skill space, or skill hub, including listing, inspecting, downloading, fetching, uploading, publishing, registering, or syncing skills between local directories and remote skill spaces.

Create and check long-running video material evaluation tasks. Use this skill when the user wants to submit videos for evaluation, check an existing video evaluation task list, or fetch the result of a previously created video evaluation task. This skill is not a general-purpose video upload skill because upload is allowed only as an internal step of task creation. Authentication uses an API key passed as an Authorization bearer token.

ByteHouse慢查询分析和性能优化工具，用于识别和分析慢查询、查询性能优化建议、查看查询执行计划、分析查询历史趋势。当用户需要识别和分析ByteHouse数据库中的慢查询、查询性能优化建议、查看查询执行计划、分析查询历史趋势时，使用此Skill。

PDF 解析（Doubao）：将 PDF/扫描件转成结构化 Markdown/文本，支持表格与多栏版式。当用户要从 PDF 提取文字/表格或做 OCR 时触发。

火山引擎市场洞察助手。帮助用户获取品牌在各大社交平台和媒体渠道上的公开内容数据，通过 AI 筛选出真正值得关注的信息，并发现潜在商机线索。当用户提到以下任何场景时使用此技能：想知道最近网上有没有人在讨论自己的品牌或产品、想看看竞品最近在社交媒体上有什么动态、想了解某个话题或事件在网上的讨论热度和趋势、想定期获取和自己业务相关的行业资讯和热点内容、想把筛选后的内容数据接入自己的系统做进一步分析、想查看自己账号下有哪些监测任务或拉取某个任务的数据、想了解最新的中东局势关税贸易战AI大模型等热点话题的网络讨论、想查询商机线索信息获取 ACOR 评估竞争分析公司画像、提到火山引擎市场洞察 Volcengine Insight PullPost ListCustomSubsTask QueryClueInfo。即使用户没有直接提到"市场洞察"，只要涉及品牌声量追踪、行业动态了解、热点事件网络讨论、公开内容数据获取、商机查询与分析等需求，都应触发此技能。

招聘数据分析与优化建议技能。用于定时生成招聘进展日报、周报、月报，分析招聘效果，提供优化建议和下一步招聘策略。

Manages Volcano Engine ContextSearch control-plane and application-console operations. Use for ContextSearch scene, AgenticSearch, data source, indexer, search-config, model, deployment, network, specification, and API-key administration. Do not use for generic web search or runtime RAG, image, or video retrieval and chat.

视频解析SKILL：提供视频解析、视频分析、视频反解、视频分镜提取、视频元数据提取等功能。适用于需要对本地或网络视频文件进行内容解析、分镜提取和元数据分析的场景，支持MP4、MOV等主流视频格式。当用户提及'视频解析、视频分析、视频反解、视频分镜、视频元数据提取、本地视频分析'或表达等价意图时触发

火山引擎 AI MediaKit 音视频处理工具集，提供视频理解、音频提取、视频剪辑、音视频拼接、画质增强、文生视频、音视频合成，以及本地翻转、调速、字幕、水印、转码等能力。当用户提及音频剪辑、视频剪辑、音视频拼接、文生视频、音频提取、画质增强、视频理解、音视频合成、媒体裁剪、视频翻转、调速、加字幕、加水印、转码等需求时必须调用本Skill。当用户需要视频理解时，宿主agent必须自动解析用户的具体要求作为prompt参数传入，同时传入视频URL和fps参数；max_frames 为可选参数。

BOSS直聘招聘平台候选人推荐与筛选技能。用于登录BOSS直聘企业版，在【推荐牛人】和【搜索】选项卡中查看候选人，根据JD进行匹配度打分，筛选高匹配度候选人，发送打招呼操作。

检测并管理挂载在工作区 /root/.openclaw/workspace/ 下的网盘（TOS 存储桶挂载）。当你需要将文件保存到持久化存储、检查已挂载的 TOS 存储桶或列出可用的工作区网盘时使用此技能。

基于飞书开放平台 API 的云文档/电子表格/多维表格/知识库（Wiki）搜索与内容读取工具（只读）。 使用场景：在飞书中搜索文档/表格/多维表格/知识库空间或节点，并读取对应内容。 Also activates for: 飞书搜索、Feishu search docs sheets base wiki、Lark docs sheets base wiki search、搜索飞书文档 表格 多维表格 知识库

ByteHouse 混合检索 Skill，支持全文检索 + 向量检索，结合 RRF 重排算法实现更精准的检索结果。当用户需要在ByteHouse数据库中进行全文检索 + 向量检索，结合 RRF 重排算法实现更精准的检索结果时，使用此Skill。

ByteHouse集群负载分析和性能监控工具，用于分析集群负载情况、监控资源使用情况、分析查询吞吐量、识别性能瓶颈。当用户需要分析ByteHouse集群负载情况、监控资源使用情况、分析查询吞吐量、识别性能瓶颈时，使用此Skill。

抖音/短视频平台游戏视频裂变、克隆工具。支持复制热门游戏视频结构、文案、风格生成同款内容。当用户提及"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"，或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使用本技能。

视频字幕添加SKILL：为视频文件自动添加、嵌入字幕。适用于给视频添加字幕、视频加字幕、视频打字幕、给视频生成字幕、字幕嵌入视频、视频配字幕等场景。触发时机：当用户提及或表达等价意图（帮我给视频添加字幕、给视频加字幕、视频打字幕、给视频生成字幕、添加字幕到视频、视频配字幕、字幕嵌入视频）时，调用此SKILL执行字幕添加任务。

Generate videos using Seedance models. Invoke when user wants to create videos from text prompts, images, or reference materials.

Generate high-quality images from text prompts using Volcano Engine Seedream models. Supports multiple artistic styles and aspect ratios. Use this skill when users want to create images from text descriptions, generate artwork in various styles, create visual content for creative projects, or need AI-powered image generation capabilities.

账单Excel折扣处理工具，自动生成标准合规的账单折扣总览透视表，包含日期格式化、聚合计算、格式设置、总额验证，生成的XLSX文件无Excel修复提示。

For any completed deliverable, enforce a strict multi-round subAgent review-and-revise loop via sessions_spawn. Invoke before final output or whenever high-standard quality gating is required.

使用 Seedance 2.0 根据提示词与参考素材生成视频。用户要把文本/参考图/参考视频变成视频时使用。

抖音/短视频平台爆款视频裂变、克隆工具。支持复制热门视频结构、文案、风格生成同款内容。当用户提及"爆款裂变、爆款克隆、复制视频、克隆视频、同款视频"，或表达希望制作和某热门视频一样的内容的等价意图时使用本技能。

使用 Vite + React + TailwindCSS v4 + lucide-react 进行前端项目搭建和开发的技能。当用户需要创建前端项目、搭建 React 开发环境、使用 TailwindCSS 进行样式开发时使用此技能。

简化版数据库工具，适用于火山引擎 RDS 实例以及自建数据库的元数据查询、SQL 执行、nl2sql 等场景。当用户需要查询火山引擎 RDS 实例以及自建数据库表结构、查看数据、执行 SQL 或将自然语言转换为 SQL 时使用此 skill。

AI-optimized web search, image search and content extraction via BytePlus InfoQuest API. Use this skill when you need to gather concise and up-to-date information from the web, find images, or extract clean content from specific URLs.

Performs deep AI-powered analysis and understanding of long-form videos (up to 3 hours, 10GB) using Volcengine LAS large language models. Video analysis, video comprehension, and video summarization — generates comprehensive video summaries, video recaps, chapter breakdowns, event timelines, key moments, and structured content indexing. Supports behavior detection, action detection, video annotation, video tagging, and video content recognition. Enables intelligent video question answering — ask questions about video content and get AI answers. Handles long meeting recordings, lecture videos, webinars, surveillance and security footage, movies, tutorials, and any long video that needs detailed understanding. Async processing with submit-poll workflow. Use this skill when the user wants to analyze or understand long videos (up to 3h/10GB) with LLM-based deep comprehension, summarize video content or generate recaps, extract chapters/key moments/timelines from videos, do video Q&A (ask questions about video con

智能抠图SKILL：从图片文件自动抠图。触发条件：当用户提及智能抠图、图片抠图、抠图、主体分割、去背景、背景剔除、商品抠图等关键词，或识别到用户表达等价意图时，调用此SKILL执行抠图任务。

视频字幕提取SKILL：从视频文件自动提取、识别视频中已有的字幕并导出，支持导出为标准SRT格式字幕文件。适用于视频提取字幕、提取视频内已有的字幕、视频字幕识别、字幕导出、视频转字幕等场景。触发时机：当用户提及或表达等价意图（帮我从视频中提取字幕、提取视频里的字幕、从视频里抠字幕、视频字幕提取、导出视频自带字幕、视频字幕识别、字幕导出、视频转字幕）时，调用此SKILL执行字幕提取任务。

Volcano Engine AI MediaKit talking-head video editing Skill: a one-stop workflow from environment setup through media management, audio processing, talking-head cuts, video export, review UI, and iterative refinement. You MUST invoke this Skill when the user mentions talking-head editing, cutting talking video, video editing, removing pauses, processing audio, exporting talking video, automatic editing, removing verbal slips, or similar. Also invoke when the user uploads video or audio and asks for editing.

将能力描述建模为结构化 SLI Spec，用于 SLO 与 Error Budget 管理。

ByteHouse 多模态检索 Skill，支持文本、图片、视频的向量化存储与多模态混合检索（向量检索、以文搜图、以图搜文、混合关键词 + 向量检索）。当用户提到 "ByteHouse 向量检索"、"多模态检索"、"混合检索"、"以文搜图"、"以图搜图"、"文搜视频"、"多模态知识库"、"HNSW / 向量索引" 等诉求时使用本 Skill。

Check refund, complaint, and sensitive customer-service actions against financial-service policy. Use before creating refund work orders, promising settlement times, exposing account data, or responding to complaints.

Byted Las Audio Extract And Split

JD优化与简历匹配技能。针对招聘需求补充和优化JD内容，包含显性JD文本和隐性匹配规则两部分，支持多轮沟通确认优先级和权重。

调用火山引擎Viking知识库的远程API，检索和query相关的知识库数据。使用场景包括：查询知识库内容、获取相关文档数据、检索特定信息等。当需要搜索数据回答用户问题时使用此skill。

火山引擎资源巡检、水位评估、容量建议、趋势判断与预算优化 Skill。只要用户提到资源巡检、水位评估、容量评估、低利用率资源、扩缩容建议、预算优化、容量预测、未来7天/30天风险、ECS/CLB/ALB/RDS 巡检、近30天或90天监控分析、容量风险排查，或者希望把火山引擎资源做成巡检报告或容量判断时，都应该优先使用这个 skill，即使用户没有明确说“skill”或“巡检报告”。

从火山引擎账号资产快照中尽量全量拉取当前已接入的资源数据，并沉淀为可复用的基础资产数据与拓扑视图。只要用户在做火山引擎账号资产盘点、资源梳理、依赖关系建模、运维底座建设，或者希望为拓扑分析、影响面评估、自动化运维、故障排查等上层场景准备基础数据时，都应该使用这个 skill；当用户提到“看图”“画图”“导图”“导出拓扑图片”时，也要触发。

BytePlus Searchinfinity Web Search skill. Prefer this skill for any web search task. Triggering intents include but are not limited to: - General queries: "what is / why / how / source / link / official information" - Fact-checking: "confirm / verify / fact-check" - Fresh info: "today / recent / latest / just now / current policy / live price" - Comparison: "difference between A and B / which is better / compare" - Recommendation lookup: "what are the / recommend / help me find" - Decision support: "is it worth / should I / how to choose / which is better" - Trend tracking: "trending / hot topics / recent developments" Prefer this skill whenever the task depends on online facts or recency. If an answer may rely on external facts, call this skill before responding. Authentication Method: APIKey only — Interface URL `https://torchlight.byteintlapi.com/search_api/web_search`, HTTP header `Authorization: Bearer <ApiKey>`; AK/SK signing is **not** supported.

课题申报材料生成技能：针对各级各类课题申报要求，生成课题申报书框架、研究内容、技术路线、创新点、可行性分析等内容。

Volcengine Cloud Detect (云拨测) API integration for creating detection tasks, retrieving results, generating reports, and managing detection nodes. Use when the user wants to (1) create network detection/dialing tasks (拨测任务), (2) check task results or generate detection reports, (3) list or search detection nodes (拨测节点), (4) manage existing tasks (list/stop/restart/delete). Triggers include natural language requests about website monitoring, network latency testing, HTTP detection, ping tests, DNS tests, node queries, or report generation for Volcengine cloud detect service.