Agnes AI 免费图片视频生成：在 Agent 里接 Agnes 文生图与视频
介绍 SkillHub 社区 Skill「Agnes AI 免费图片视频生成」（@user_cdd89df6/agnes-gen，v1.0.0）。它通过 SKILL.md 在 Cursor、Claude Code、Codex 等 Agent 中接入 Agnes AI 模型 agnes-image-2.0-flash、agnes-image-2.1-flash、agnes-video-v2.0，支持文生图、改图及文本/图片生视频；触发词含「生图」「生视频」等。说明 skillhub CLI 安装、--dir 指向各客户端 skills 目录，以及 requires_api_key 配置注意。不含未核实 API 字段与编造示例。
Read Moreveo 3.1：在 Agent 里调用 Google Veo 3.1 生成电影级视频
veo 3.1 是 SkillHub 社区技能（@user_f95f21b8/dlazy-veo-3-1，v1.0.9），基于 SKILL.md 约定，通过 @dlazy/cli@1.0.9 调用 dLazy 托管的 Google Veo 3.1，支持文生视频与图生视频。文章说明其定位、frames/components 模式、分辨率与异步参数，并给出 skillhub install、Cursor 等 skills 目录、dlazy auth set 与典型 dlazy veo-3.1 命令。适用已配置 dLazy API Key 的开发者；需注意云端上传、余额与内容策略。
Read Morewan2.7：在 Agent 里调用通义万相 2.7 做视频生成
wan2.7 是 SkillHub 社区 Skill（@user_f95f21b8/dlazy-wan2-7，v1.0.9），封装 Tongyi Wanxiang 2.7，经 dLazy CLI 对接 api.dlazy.com，支持文生视频、参考图/视频生视频与首尾帧模式。文章说明 skillhub install、@dlazy/cli@1.0.9 与 dlazy auth set 的配置路径，并给出 dlazy wan2.7 示例命令、generation_mode 与异步轮询要点，以及 API Key、余额与上传媒体的注意事项。
Read Morekling v3 omni：在 Agent 中接入可灵 v3 Omni 多模态视频生成
kling v3 omni（@user_f95f21b8/dlazy-kling-v3-omni，v1.0.9）是 SkillHub 上的 design-media 类社区 Skill，通过 dLazy CLI 调用 Kling v3 Omni，支持提示词与图片等多模态输入生成动态视频。文章说明 Skill 定位、核心 CLI 参数、SkillHub 与 @dlazy/cli@1.0.9 安装路径、API Key 配置，以及官方命令示例与异步、计费相关注意点。
Read Morevideo generate：用自然语言驱动 dlazy CLI 自动选模型生成视频
video generate（@user_f95f21b8/dlazy-video-generate，v1.0.9）是 SkillHub 社区 design-media 类 Skill，根据用户提示词在多条 dlazy 视频子命令间自动选型，再执行 dlazy CLI 调用 dLazy API。文章说明其定位、模型列表、SkillHub 与 @dlazy/cli@1.0.9 安装、API Key 配置，以及 Agent 先 -h 再执行的典型流程与余额/鉴权注意事项。
Read More一人成军视频生成：用 Skill 串起 AI 制片全流程
「一人成军视频生成」是 SkillHub 社区 Skill @user_ac2e846a/ai-film-production（design-media，v1.0.0），提供一人成军 AI 制片流程指导：双主线与闭环反馈，覆盖分镜创作、定调筹备、动态制作及剪辑粗剪与定剪。标签 requires_api_key=false。可通过 skillhub CLI 安装到 Cursor 等客户端 skills 目录，或按官方提示词让 Agent 参照 skillhub.md 安装。适合需要分阶段、可迭代推进短片的个人与小团队；具体工具链需自行对接。
Read Moreseedance 2.0：在 Agent 里调用 ByteDance Seedance 2.0 视频生成
seedance 2.0 是 SkillHub 社区 Skill（@user_f95f21b8/dlazy-seedance-2-0，v1.0.9），通过 dLazy CLI 调用托管 API，对接 modelId doubao-seedance-2_0。支持多模态参考（图/视频/音频）、首尾帧与文生视频，可配置分辨率、画幅与时长。安装需 skillhub install 到 Agent skills 目录，并安装 @dlazy/cli@1.0.9、配置 dLazy API Key。适合在 Cursor 等环境中用自然语言驱动成片，需注意云端上传与账户余额。
Read MoreSeedance 2.0 提示词专家：把 Seedance 2.0 当导演场用的 Skill
Seedance 2.0 提示词专家是 SkillHub 社区 Skill（v2.1.7），面向 Seedance 2.0 60 秒 2K 视频生成，以女娲方法论与四层建筑法参数化编写提示词，并提供八大模板、反模式过滤、问题诊断、多模态绑定与能力边界校验。本文说明其定位、核实过的核心能力、skillhub 安装命令与各 Agent skills 目录，以及典型对话用法与适用边界；无需 API Key。
Read MoreVideo Generation: Calling Volcano Engine SD1.5pro in an Agent for Text-to-Video and Image-to-Video
Introduces the SkillHub community skill “Video Generation” (@user_cb5e2841/openclaw-v3, v1.0.0). It supports text-to-video, image-to-video, and asynchronous task processing via the Volcano Engine SD1.5pro API, and requires configuring an API key. The article describes the skill’s positioning, core capabilities, the skillhub CLI installation command, and the skills directories for each Agent, and provides typical conversational usage and suitable scenarios. See skillhub.cn for the official page.
Read MoreASCII H3 Director
ASCII H3 Director is a zero-dependency preview tool developed for MiniMax H3 to address the pain points of validating prompts and motion logic. It compiles free-form descriptions into structured plans and supports deterministic previews in terminals, SVG, and PNG through handcrafted bitmap font libraries. Its core features include motion syntax, continuity contracts, and quality gates. Users can debug quickly without calling paid APIs. Once installed, it can be used both as a DeepSeek Harness plugin and as an Agent Skill in combination with mmx-cli for paid generation.
Read MoreDeepSeek Harness Plugin: yu-wenchao/dsh-tool-lipsync (A Keyless and Login-Free AI Lip-Sync Video Generation Tool)
The DeepSeek Harness plugin dsh-tool-lipsync is designed to simplify video generation in multimedia agent development. It requires no account registration or API key configuration and, by registering five tools, enables users to directly generate lip-sync videos within a conversation. It provides audio, asset management, and task submission capabilities, supports generating videos up to 20 seconds long, and automatically monitors download progress. Relying on free third-party services, it also involves considerations such as version limitations, paid high-definition access, and copyright compliance, while lowering the barrier to AI video generation.
Read Moredsh-video-gen: One-Click Access to MiniMax H3 Video Generation
dsh-video-gen is a video generation plugin for DeepSeek Harness that encapsulates the MiniMax H3 model to provide text-to-video, image-to-video, and visual workbench features for Web Profile. It supports multiple generation modes, parameter configuration, and asynchronous task management, and can present generated MP4 files as preview cards within the conversation. Users need to configure an easyframe API key and restart DSH after installation to use it. The plugin aims to simplify the video generation workflow and provide a convenient experience for uploading assets and optimizing prompts.
Read Moredsh-comfy-video-studio: A ComfyUI Dynamic Video Workflow Plugin for DeepSeek Harness
dsh-comfy-video-studio is an open-source plugin developed by a1303845406, designed to address the lack of persistent management and the cumbersome multi-server scheduling of ComfyUI in DeepSeek Harness. The plugin supports importing any ComfyUI API-format JSON, performs automatic runtime compatibility checks, and converts it into a visual workflow page. Core features include importing and parsing API JSON, pre-run checks for missing nodes or models, customizable management of workflow pages, and support for concurrent multi-server scheduling and task queue management. The plugin persistently stores workflows, connection settings, and task status, with the ability to archive video outputs. It handles tasks beyond active slots using a FIFO queue and is configured via a YAML configuration file.
Read MoreDSH Skill Hell Grind Video Prompt
`dsh-skill-hell-grind-video-prompt` is a DeepSeek Harness (DSH) plugin designed to improve the consistency and quality of video prompt generation by encapsulating the 29 rules of the "Hell Grind" methodology. It covers four stages—assets, scenes, character performance, and video generation—and includes multiple key examples. After installation, users or models can automatically trigger or manually invoke this skill when handling requests related to video generation, storyboarding, or character performance.
Read MoreDeepSeek Harness (DSH) Video and Image Generation Plugin (dsh-vidgen-plugin)
The official DeepSeek Harness (DSH) plugin, dsh-vidgen-plugin, provides a comprehensive video and image generation solution for Web interfaces. It includes a ComfyUI-style node-based canvas studio supporting text-to-image, image-to-video, and keyframe synthesis; offers multi-provider configuration management and OpenAI-style API compatibility. In addition, it exposes three Agent tools for programmatic invocation and supports features such as canvas snapshots and local image uploads, aiming to streamline visual output workflows in agent development.
Read Moredsh-seedance2: Seedance 2 Image and Video Generation on DeepSeek Harness
`dsh-seedance2` is a plugin for DeepSeek Harness (DSH) that integrates Seedance 2 AI's image and video generation capabilities. After installation, the environment variable `SEEDANCE2_PUBLIC_API_KEY` must be configured. The plugin supports image and video generation as well as task queries, and includes built-in retry, backoff, timeout, and idempotency handling. When using it, prompts should include elements such as subject, action, and scene, and parameters can be adjusted via a configuration file. It leverages the Harness credential system to secure keys, reducing the risk and cost associated with integrating external models.
Read Moredsh-nanobananapro: NanoBananaPro Image and Video Generation Plugin for DeepSeek Harness
`dsh-nanobananapro` is a DeepSeek Harness plugin maintained by SynMind AI, designed to integrate NanoBananaPro's image and video generation capabilities directly into the DSH toolchain. The plugin provides native interfaces through a public API, enabling users to call models such as Veo 3 for content generation, while also offering balance inquiry and task management tools. It can be installed using the `npx` command and is ready for direct use in DSH conversations or workflows. Users should note that the plugin consumes only API wallet balance, does not support local asset uploads, and paid tools require manual approval by default. Timeout policies can be adjusted via configuration files.
Read MoreAngles for DeepSeek Harness
`anglesvideo-dsh-plugin` is an open-source plugin for DeepSeek Harness that leverages the Angles Developer API to transform local software repository context into executable video concepts and rendered results. The plugin provides a one-stop toolchain covering repository analysis, concept generation, template selection, rendering previews, and final video output. During installation, an API key must be configured, and after setup, an automated video production workflow is performed through a series of tool calls (such as `inspect_repository`, `create_launch_concepts`, and `render_launch_video`). This plugin is a developer preview and includes privacy protection mechanisms at runtime to ensure that sensitive data is not uploaded.
Read More