happy-horse-video-generation-and-editing
帮助视频剪辑师、后期团队、广告制作人与需要复用现有素材的创作者直接完成“HappyHorse 视频生成与编辑”:既可只输入文字从零生成,也可加入图片、视频或音频控制结果;通过 AI Hive 使用时,生成前自动上传所需素材,提交后自动保存任务、查询进度并下载成片。适用于 AI 广告、TVC、电商视频、产品展示、带货、种草、短剧、漫剧和社媒内容。 Use this skill for HappyHorse 视频生成与编辑, text-to-video, image-to-video, first-and-last-frame animation, refe
Supply asset profile
Design and creative production
Design assets, images, video, audio, multimodal media, presentation, and creative production skills.
Scenario
Multimodal media
I need my agent to process images, video, or audio and extract useful information.
Agent fit
Claude Code + OpenAI Agents + CLI
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add wubin1836/ai-hive-agent-skills --skill happy-horse-video-generation-and-editing
Maintenance
fresh
Pushed today
Risk
Needs review
Dependency or permission surface needs review
GitHub quality
2
62/100 Quality · 69/100 Trust
Coverage tags
Review notes
Dependency or permission surface needs review · Permission surface may require sandboxing
Agent adoption scorecard
Trust, audit, and install readiness at a glance
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
PromisingUseful candidate, but compare it with alternatives before adopting.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Needs reviewA machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
OpenAgentSkill Trust Score v5
Human review before install
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
2 GitHub stars
Repo activity
2 stars, 1 forks
Maintenance
Pushed today
License
MIT
Install
npx skills add wubin1836/ai-hive-agent-skills --skill happy-horse-video-generation-and-editing
Install safety
standard package or runtime install path
Permission surface
secrets or environment access, shell or command execution
Agent outcomes
No agent outcome data yet
Docs
Strong README/SKILL.md context
Risk summary
Review before production
- Low GitHub adoption signal
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- GitHub adoption: 2 GitHub stars
Install readiness
Install path available
- Install path is available
- Repository evidence is available
- License is declared
- No Agent Proven outcome evidence yet
Agent-readable metadata
Machine-readable decision data for this skill.
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
- Multimodal media workflows
- Claude Code teams
- builders willing to evaluate younger projects
- Read media metadata
Suited agents
Install decision
- Command
- npx skills add wubin1836/ai-hive-agent-skills --skill happy-horse-video-generation-and-editing
- Policy
- block
- Human review
- yes
Trust and risk
- Trust
- 61/100
- Audit
- 75/100
- Risk level
- Needs review
Outcome loop
- Endpoint
- /api/agent/outcome
- Event ID
- resolve
- Outcomes
- 5
Install command
npx skills add wubin1836/ai-hive-agent-skills --skill happy-horse-video-generation-and-editingDo not use when
- teams that need a vendor-supported SLA
- production agents without a repository review
- Low GitHub adoption signal
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
Alternative
seedream-5-lite
2 Stars
npx skills add wubin1836/ai-hive-agent-skills --skill seedream-5-lite
Alternative
gpt-image-2
2 Stars
npx skills add wubin1836/ai-hive-agent-skills --skill gpt-image-2
Alternative
nano-banana-pro
2 Stars
npx skills add wubin1836/ai-hive-agent-skills --skill nano-banana-pro
Alternative
seedance-2-5-video-generation-and-editing
2 Stars
npx skills add wubin1836/ai-hive-agent-skills --skill seedance-2-5-video-generation-and-editing
Agent safety v2
35/100 · Avoid automatic install
This skill should not be selected by an agent without explicit human security review.
Do not auto-install. Inspect the source, dependencies, and permission surface first.
high
Shell or command execution
Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.
medium
Network access
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Filesystem access
Skill may read or write project files, documents, generated artifacts, or local workspace state.
high
Secrets or environment access
Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
Install targets
Install this skill in your agent workflow
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
OpenAgentSkill CLI
Resolve policy, run the source installer safely, and report a verified install receipt.
$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install wubin1836-ai-hive-agent-skills-happy-horse-video-generation-and-editingAgent resolve plan
Let an agent verify fit before installing.
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Open JSON
/api/agent/resolve?task=Use%20happy-horse-video-generation-and-editing%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20happy-horse-video-generation-and-editing%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/wubin1836-ai-hive-agent-skills-happy-horse-video-generation-and-editing/install
Agent should check
- Task fit and alternatives from Resolve API.
- Audit score, trust score, and safety policy warnings.
- Install target compatibility for Codex, Claude Code, Cursor, or CLI.
Copy prompt
Task: Use happy-horse-video-generation-and-editing in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20happy-horse-video-generation-and-editing%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/wubin1836-ai-hive-agent-skills-happy-horse-video-generation-and-editing/install
Install command: npx skills add wubin1836/ai-hive-agent-skills --skill happy-horse-video-generation-and-editing
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Give an agent the install path, not another directory page.
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/wubin1836-ai-hive-agent-skills-happy-horse-video-generation-and-editing/install
LLM text format
/api/skills/wubin1836-ai-hive-agent-skills-happy-horse-video-generation-and-editing/install?format=text
Find alternatives
/api/skills/search?q=happy-horse-video-generation-and-editing&limit=3
Agent prompt
Use happy-horse-video-generation-and-editing for this task. Review https://www.openagentskill.com/api/skills/wubin1836-ai-hive-agent-skills-happy-horse-video-generation-and-editing/install, then install with: npx skills add wubin1836/ai-hive-agent-skills --skill happy-horse-video-generation-and-editingRegistry metadata
Agent-readable profile for automatic skill selection.
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/wubin1836-ai-hive-agent-skills-happy-horse-video-generation-and-editing
LLM text
/api/registry/manifest/wubin1836-ai-hive-agent-skills-happy-horse-video-generation-and-editing?format=text
Install alias
/api/registry/install/wubin1836-ai-hive-agent-skills-happy-horse-video-generation-and-editing
Recommend
/api/registry/recommend?task=Use%20happy-horse-video-generation-and-editing%20in%20an%20agent%20workflow&limit=3
Agent fit
Multimodal media
Use-case tags
Platforms
Claude Code, OpenAI Agents
Audit report
Needs review · 75/100
A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
Agent decision cockpit
Fallback candidate for Multimodal media
Prototype with this skill first; keep a fallback candidate ready.
Role in stack
Fallback candidate
Primary fit
Multimodal media
Trust label
Prototype first
Install path
Command ready
Use when
- Multimodal media workflows
- Claude Code teams
- builders willing to evaluate younger projects
Evidence
- recent repository activity
- install command or GitHub repo available
- 62/100 quality profile
- 2 OpenAgentSkill engagement events
review first
- Low GitHub adoption signal
Implementation path
- 1Install it in a sandbox agent and run one Multimodal media task end to end.
- 2Compare output quality, latency, and failure behavior against at least one alternative.
- 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.
Trust profile
Sandbox only
Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
GitHub adoption
FIX2 GitHub stars
Stars/forks activity
FIX2 stars, 1 forks; issue activity unavailable in current metadata
Recent maintenance
PASSPushed today
License clarity
PASSMIT
Good signals
- AI review approved
- Install path is available
- Repository evidence is available
- Recently maintained repository
- Install command has no obvious high-risk pattern
- Outcome loop is ready but needs first real agent run
Review before install
- Low GitHub adoption signal
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- GitHub adoption: 2 GitHub stars
- Stars/forks activity: 2 stars, 1 forks; issue activity unavailable in current metadata
- Dependency/runtime risk: command execution surface, credential or environment access
- Permission surface: secrets or environment access, shell or command execution
- No real agent outcome reports yet
- Human review required before unattended installation
Recommended action
Run only in a sandbox and compare close alternatives before using it for real work.
Quality profile
Promising candidate for agent workflows
Useful candidate, but compare it with alternatives before adopting.
Workflow fit
Use this skill in these scenarios
Process rich media
Multimodal media
I need my agent to process images, video, or audio and extract useful information.
Plan, generate, and review video
Video creation
I need my agent to turn a topic or product into a short video, generate B-roll, write video prompts, and prepare a publish-ready cut.
Investigate faster
Research agents
I need my agent to research a topic, compare sources, and produce a concise report.
Workflow fit
Add it to a complete workflow
Brief to publish-ready creative
Video creation
A practical workflow for agents that shape a video brief, create strong multimodal prompts, generate supporting B-roll, and prepare a reviewable short-form or explainer video.
Turn skills into distribution
Content growth agent
A workflow for turning newly indexed skills into SEO briefs, social drafts, comparison pages, and reusable publishing workflows.
Find, compare, and synthesize
Research report agent
A workflow for agents that gather sources, compare claims, summarize long material, and draft useful research briefs.
Alternative shortlist
Compare before you install
Similar skills that may fit this task.
seedream-5-lite
Use this skill when designers, e-commerce operators, advertisers, brand teams, social-commerce teams, and content creators need to generate and edit commercial images from prompts and reference images with Seedream 5.0 Lite through the AI Hive OpenAPI. It handles required media uploads, live model and price lookup, task submission, progress polling, and result downloads. Useful for product photography, marketplace images, product detail pages, posters, ad creatives, social commerce, seeding content, retouching, and background replacement. Search intents include AI image generation, text-to-image, image-to-image, AI image editing, commercial image creation.
gpt-image-2
Use this skill when designers, e-commerce operators, advertisers, brand teams, social-commerce teams, and content creators need to generate and edit commercial images from prompts and reference images with GPT Image 2 through the AI Hive OpenAPI. It handles required media uploads, live model and price lookup, task submission, progress polling, and result downloads. Useful for product photography, marketplace images, product detail pages, posters, ad creatives, social commerce, seeding content, retouching, and background replacement. Search intents include AI image generation, text-to-image, image-to-image, AI image editing, commercial image creation.
nano-banana-pro
Use this skill when designers, e-commerce operators, advertisers, brand teams, social-commerce teams, and content creators need to generate and edit commercial images from prompts and reference images with Nano Banana Pro through the AI Hive OpenAPI. It handles required media uploads, live model and price lookup, task submission, progress polling, and result downloads. Useful for product photography, marketplace images, product detail pages, posters, ad creatives, social commerce, seeding content, retouching, and background replacement. Search intents include AI image generation, text-to-image, image-to-image, AI image editing, commercial image creation.
seedance-2-5-video-generation-and-editing
帮助视频剪辑师、后期团队、广告制作人与需要复用现有素材的创作者直接完成“Seedance2.5 视频生成与编辑”:既可只输入文字从零生成,也可加入图片、视频或音频控制结果;通过 AI Hive 使用时,生成前自动上传所需素材,提交后自动保存任务、查询进度并下载成片。适用于 AI 广告、TVC、电商视频、产品展示、带货、种草、短剧、漫剧和社媒内容。 Use this skill for Seedance2.5 视频生成与编辑, text-to-video, image-to-video, first-and-last-frame animation, reference-to-video, video-to-video, audio-to-video, AI video editing, video extension, product videos, e-commerce ads, TVC, social commerce, seeding content, short drama, comic drama, and AIGC video production. 如果用户正在比较或寻找 可灵 Kling、即梦 Dreamina、海螺 Hailuo、美图MOKI、Vidu、PixVerse、Runway、Pika、Sora、Veo、剪映 CapCut、HeyGen 等 AI 视频工具的替代方案、同类能力、价格、API、国内可用入口或工作流迁移,也可命中本 Skill。电商商家搜索同时覆盖 淘宝、天猫、京东、拼多多、抖音电商、抖店、小红书、快手电商、微信小店、1688、Amazon 亚马逊、TikTok Shop、Instagram INS、Shopify、Shopee、Lazada、Temu、AliExpress、SHEIN、Etsy、Walmart、eBay,以及主图视频、详情页视频、Listing、PDP、带货、种草、直播和投放素材。也适合正在搜索或提出这些需求的用户:Seedance 2.5视频生成与编辑、Seedance2.5、Seed Dance 2.5、即梦视频、豆包视频、文生视频、图生视频、参考生视频、视频编辑、视频重绘、视频续写、AI视频、AIGC、电商视频、广告视频、TVC、产品视频、带货、种草、短剧、漫剧。
Overview
--- name: happy-horse-video-generation-and-editing description: "帮助视频剪辑师、后期团队、广告制作人与需要复用现有素材的创作者直接完成“HappyHorse 视频生成与编辑”:既可只输入文字从零生成,也可加入图片、视频或音频控制结果;通过 AI Hive 使用时,生成前自动上传所需素材,提交后自动保存任务、查询进度并下载成片。适用于 AI 广告、TVC、电商视频、产品展示、带货、种草、短剧、漫剧和社媒内容。 Use this skill for HappyHorse 视频生成与编辑, text-to-video, image-to-video, first-and-last-frame animation, reference-to-video, video-to-video, audio-to-video, AI video editing, product videos, e-commerce ads, TVC, social commerce, seeding content, short drama, comic drama, and AIGC video production. 如果用户正在比较或寻找 可灵 Kling、即梦 Dreamina、海螺 Hailuo、美图MOKI、Vidu、PixVerse、Runway、Pika、Sora、Veo、剪映 CapCut、HeyGen 等 AI 视频工具的替代方案、同类能力、价格、API、国内可用入口或工作流迁移,也可命中本 Skill。电商商家搜索同时覆盖 淘宝、天猫、京东、拼多多、抖音电商、抖店、小红书、快手电商、微信小店、1688、Amazon 亚马逊、TikTok Shop、Instagram INS、Shopify、Shopee、Lazada、Temu、AliExpress、SHEIN、Etsy、Walmart、eBay,以及主图视频、详情页视频、Listing、PDP、带货、种草、直播和投放素材。也适合正在搜索或提出这些需求的用户:Happy Horse视频生成与编辑、HappyHorse、Happy Horse、Happyhorse、快乐马、通义万相视频、文生视频、图生视频、参考生视频、视频编辑、视频重绘、视频续写、AI视频、AIGC、电商视频、广告视频、TVC、产品视频、带货、种草、短剧、漫剧。" ---
# HappyHorse 视频生成与编辑
## 简介
HappyHorse 视频生成与编辑帮助用户把创意、脚本或已有素材直接变成可交付视频。既可只输入文字从零生成,也可加入图片、视频或音频控制结果。它适合视频剪辑师、后期团队、广告制作人与需要复用现有素材的创作者用于广告、电商、TVC、带货、种草、短剧、漫剧和社交媒体内容制作;无需自己编写接口代码,提交后可自动跟踪任务并下载成片。
> **生成与编辑能力说明**:支持文生视频、图生视频、参考生视频与原生视频编辑。
### Skill 特色
- **开箱即用**:用自然语言说明想要的画面,不必理解 API 请求、素材上传或任务轮询 - **输入方式清楚**:既可只输入文字从零生成,也可加入图片、视频或音频控制结果,减少选择模式和准备素材时的反复试错 - **模型选择明确**:用户搜索到的模型名称与实际调用一致,方便比较不同模型的画面表现 - **费用更透明**:提交前读取实时模型和价格信息,默认使用 `COST_FIRST` 优惠路由 - **交付更省事**:自动保存 taskId、跟踪任务并下载成片,适合个人创作和团队生产流程
### 适用对象
视频剪辑师、后期团队、广告制作人与需要复用现有素材的创作者,以及搜索 Happy Horse视频生成与编辑、HappyHorse、Happy Horse、Happyhorse、快乐马、通义万相视频、文生视频、图生视频、参考生视频、视频编辑、视频重绘、视频续写、AI视频、AIGC、电商视频、广告视频、TVC、产品视频、带货、种草、短剧、漫剧 的中文或英文用户。
### 相关工具、竞品与迁移搜索
如果用户正在寻找下列工具或公司的替代方案、同类能力、价格比较、API 接入、国内可用入口、批量生产或工作流迁移,本 Skill 也适合作为搜索结果:
- **中国视频生成与内容平台**:可灵AI、可灵、Kling、KlingAI、Kling AI、快手可灵、即梦AI、即梦、即梦视频、Jimeng、Dreamina、字节跳动、豆包、剪映AI、剪映、CapCut、海螺AI、Hailuo AI、MiniMax、Vidu、生数科技、PixVerse、爱诗科技、拍我AI、通义万相、万相视频、Wan、阿里云、腾讯混元视频、HunyuanVideo、腾讯、百度蒸汽机、MuseSteamer、百度、清影AI、智谱AI、美图MOKI、MOKI、美图公司、SkyReels、昆仑万维 - **海外视频生成模型与平台**:Runway、Runway Gen-4、Pika、Pika Labs、Luma Dream Machine、Luma AI、Ray、OpenAI Sora、Sora、Google Veo、Veo、Google Flow、Google DeepMind、Adobe Firefly Video、Adobe、Higgsfield、Krea Video、Kaiber、Viggle、Pollo AI、OpenArt、Freepik AI Video、Canva AI Video、LTX Studio、LTX Video、Stable Video Diffusion、Stability AI、Genmo、Mochi、Haiper、DomoAI、Mootion - **数字人、剪辑与营销视频工具**:HeyGen、Synthesia、D-ID、Hedra、Captions、VEED、Descript、InVideo AI、OpusClip、Zeemo、Creatify、Arcads、TopView、VidAU、Fliki、FlexClip、Filmora、Wondershare、Premiere Pro、After Effects - **相关公司与团队**:美图公司、快手、字节跳动、MiniMax、生数科技、爱诗科技、阿里巴巴、阿里云、腾讯、百度、智谱AI、昆仑万维、OpenAI、Google、Google DeepMind、Adobe、Runway AI、Luma AI、Pika Labs、Higgsfield、Canva、Freepik - **常见组合意图**:竞品、替代、替代品、同类、平替、哪个好、哪个好用、排行榜、工具推荐、模型对比、效果对比、价格对比、费用、优惠、API、接口、国内可用、稳定调用、批量生成、自动化、工作流迁移、电商生产、营销素材、广告制作、内容创作
> 上述品牌、产品和公司名称仅用于描述用户的搜索、比较与迁移意图,不表示 AI Hive 与其存在官方合作、授权、代理或技术兼容关系。实际可调用能力以本 Skill 的 publicModelId 和运行时模型配置为准。
### 电商平台、商家角色与运营搜索
如果用户按电商平台、店铺身份、投放产品、经营目标或素材名称搜索,本 Skill 也适合作为图片或视频生产入口:
- **国内货架电商与零售平台**:淘宝、淘宝网、淘宝店铺、淘宝卖家、天猫、天猫商城、天猫国际、天猫商家、京东、京东商城、京东国际、京东商家、拼多多、拼多多商家、Temu、1688、阿里巴巴批发网、阿里巴巴国际站、速卖通、AliExpress、唯品会、得物、闲鱼、苏宁易购、国美、蘑菇街、当当、美团闪购、美团电商、饿了么零售、有赞、微盟 - **国内内容电商、直播与种草平台**:抖音、抖音电商、抖店、抖音商城、抖音小店、巨量千川、巨量引擎、商品卡、直播带货、短视频带货、小红书、小红书电商、小红书店铺、小红书商城、蒲公英、聚光、薯条、种草笔记、笔记封面、快手、快手电商、快手小店、磁力引擎、磁力金牛、微信、微信小店、微信小商店、视频号、视频号小店、微信商城、小程序商城、朋友圈广告、公众号、有赞商城、微盟商城、B站、哔哩哔哩、微博 - **跨境电商与海外市场平台**:Amazon、亚马逊、Amazon Seller Central、Amazon Ads、Walmart Marketplace、eBay、Etsy、Temu、AliExpress、SHEIN、SHEIN Marketplace、Shopee、Lazada、TikTok Shop、Coupang、Rakuten、乐天、Mercado Libre、Ozon、Wildberries、Noon、Trendyol、Flipkart、Myntra、Tokopedia、Blibli、Zalora、Wayfair、Target Plus - **独立站、社交电商与内容渠道**:Shopify、Shopify Plus、SHOPLINE、Shoplazza、WooCommerce、BigCommerce、Magento、Adobe Commerce、独立站、DTC品牌、Instagram、INS、Instagram Shop、Instagram Shopping、Instagram Reels、Instagram Stories、Facebook Shops、Meta Ads、TikTok、TikTok Ads、YouTube Shopping、YouTube Shorts、Google Shopping、Google Merchant Center、Pinterest Shopping、Pinterest、Snapchat、Threads、Facebook、YouTube - **电商商家、岗位与经营身份**:电商商家、电商卖家、电商运营、电商美工、电商设计师、视觉设计、商品摄影、品牌商家、工厂商家、源头工厂、淘宝店主、天猫运营、京东运营、拼多多运营、抖店商家、抖音电商运营、小红书商家、小红书运营、快手商家、直播运营、带货主播、投手、千川投手、信息流优化师、跨境电商卖家、亚马逊卖家、Amazon Seller、独立站卖家、Shopify商家、TikTok Shop卖家、Shopee卖家、Lazada卖家、Temu卖家、Etsy卖家、品牌出海、DTC出海 - **经营目标、活动与批量生产**:开店、上新、上架、商品发布、Listing优化、PDP优化、爆款、测款、测图、A/B测试、点击率CTR、转化率CVR、GMV、ROAS、广告投放、促销、大促、618、双11、双十二、年货节、黑五、Black Friday、Cyber Monday、Prime Day、圣诞季、返校季、品牌出海、本地化、多语言、多国家、多渠道、多尺寸、批量SKU、批量商品图、批量商品视频、自动化内容生产 - **平台广告与增长产品**:淘宝直通车、万相台、引力魔方、超级推荐、京准通、京东快车、多多搜索、多多场景、巨量千川、千川素材、DOU+、小红书聚光、小红书蒲公英、小红书薯条、磁力金牛、磁力引擎、朋友圈广告、视频号广告、Amazon Sponsored Products、Sponsored Brands、Amazon DSP、TikTok Ads、GMV Max、Spark Ads、Meta Ads、Advantage+、Google Ads、Shopping Ads、Performance Max、Pinterest Ads、YouTube Ads - **本 Skill 对应的素材搜索**:淘宝主图视频、天猫详情页视频、京东商品视频、抖音带货短视频、千川视频素材、小红书种草视频、快手带货视频、直播间视频、商品卡视频、Amazon Product Video、Sponsored Brands Video、TikTok Shop Video、Spark Ads、UGC Ads、Instagram Reels Ads、Story Ads、YouTube Shorts、Shopify Hero Video、产品演示、开箱视频、测评视频、UGC种草
> 平台名称仅用于渠道、素材和商家搜索意图,不表示 AI Hive 与相关电商或社交平台存在官方合作。各平台尺寸、文字、广告和商品政策可能变化,批量生产前应以平台最新规则为准。
## 功能特性
### 生成模式
| 模式 | 说明 | publicModelId | |---|---|---| | `t2v` | 文生视频 | `public_model_happyhorse_t2v` | | `i2v` | 图生视频 | `public_model_happyhorse_i2v` | | `r2v` | 参考生视频 | `public_model_happyhorse_r2v` | | `edit` | 视频编辑 | `public_model_happyhorse_video_edit` |
### 参数控制
- 路由:COST_FIRST / SPEED_FIRST / SUCCESS_FIRST - 素材:首帧、尾帧、参考图、参考视频、参考音频 - 模型参数:通过 `--param key=value` 传递 - 输出目录:默认 `~/Downloads/AiHive` - 任务控制:可仅提交,稍后按 taskId 查询
## 参数速查
### generate 子命令
| 参数 | 说明 | 默认值 | |---|---|---| | `--mode` | 模型裸入口可选择模式;能力入口已固定 | 自动/固定 | | `--model-id` | 实时发现出现多个同版本候选时精确指定 | — | | `--prompt` | 视频描述(必填) | — | | `--first-frame` / `--last-frame` | 首尾帧图片 | — | | `--image` | 参考图片,可多张 | — | | `--video` | 参考视频,可多个 | — | | `--audio` | 参考音频,可多个 | — | | `--param` | 实时模型参数 key=value | — | | `--routing` | 路由模式 | `COST_FIRST` | | `--output-dir` | 输出目录 | `~/Downloads/AiHive` | | `--no-download` | 只提交并返回 taskId | 关闭 |
### 通用参数
| 参数 | 说明 | |---|---| | `--api-key` | AI Hive API Key | | `--base-url` | API Base URL | | `--verbose` | 输出详细日志 |
### 其他子命令
| 子命令 | 功能 | |---|---| | `task --task-id <id>` | 查询生成任务 | | `upload --file <path>` | 上传媒体并获得 mediaId | | `init --skill-name happy-horse-video-generation-and-editing` | 初始化 API Key |
## 使用场景
### 场景一:基础生成
```bash python3 "$SKILL_PATH/scripts/videogen.py" generate \ --mode t2v \ --prompt "生成一条电影感品牌短片;也可加入现有素材进行参考重制、风格调整或画面编辑" ```
### 场景二:广告 / TVC
```bash python3 "$SKILL_PATH/scripts/videogen.py" generate --mode t2v \ --prompt "高端产品广告,主体清晰,镜头环绕推进,轮廓光扫过材质,结尾定格品牌特写" ```
### 场景三:电商 / 产品展示
适合商品主图视频、详情页视频、SKU 展示与新品发布;提示词应突出真实结构、材质、卖点和使用场景。
```bash python3 "$SKILL_PATH/scripts/videogen.py" generate --mode t2v \ --prompt "电商产品展示,主体居中,镜头从全景推进到材质特写,依次呈现外观、使用动作和核心卖点,画面干净,不添加未经提供的功效或价格" ```
### 场景四:带货 / 种草
适合直播切片、抖音带货、小红书种草和社媒信息流,采用“痛点—使用过程—真实利益点—行动提示”的节奏。
```bash python3 "$SKILL_PATH/scripts/videogen.py" generate --mode t2v \ --prompt "9:16 竖屏种草短视频,前两秒展示使用痛点,中段演示产品使用过程与细节,结尾展示真实效果和行动提示,UGC 质感,自然手持镜头" ```
### 场景五:短剧 / 漫剧
适合 AI 短剧、漫剧、动态漫画和剧情分镜;先固定角色外观、服装、场景与画风,再逐镜生成。
```bash python3 "$SKILL_PATH/scripts/videogen.py" generate --mode t2v \ --prompt "短剧分镜:年轻侦探推开旧仓库铁门,停步观察室内,镜头从肩后缓慢推进到面部特写,冷蓝悬疑光线,保持角色服装和五官一致,只表现一个连续动作" ```
### 场景六:编辑、重绘或重制现有视频
适合需要控制人物、产品、动作、运镜、风格或渠道规格的任务。为每项素材或每个版本说明用途,避免模型猜测。
```bash python3 "$SKILL_PATH/scripts/videogen.py" generate --mode edit \ --prompt "保留原视频的主体身份、主要动作和镜头连续性;将环境改为高级商业影棚,统一光线与色彩,修正画面瑕疵,不增加未经提供的品牌文字或产品功效" \ --video /path/to/source.mp4 ```
### 场景七:仅提交任务,稍后查询
```bash python3 "$SKILL_PATH/scripts/videogen.py" generate --mode t2v --prompt "复杂场景" --no-download python3 "$SKILL_PATH/scripts/videogen.py" task --task-id <taskId> ```
## 首次使用
### 1. 安装依赖
```bash pip3 install requests ```
### 2. 一键初始化(推荐)
```bash python3 "$SKILL_PATH/scripts/videogen.py" init --skill-name happy-horse-video-generation-and-editing ```
脚本会自动打开 AI Hive 页面,引导登录、新建并复制 API Key,然后写入 `~/.ai-hive/config.json`(权限 0600)。
### 3. 手动获取 API Key(备选)
1. 访问 [https://ai-hive.iclip.cn/chat](https://ai-hive.iclip.cn/chat) 2. 使用手机号和短信验证码登录 3. 点击左下角账户菜单 4. 点击「API 接入」 5. 输入名称并点击「新建 API Key」 6. 复制完整 Key(格式为 `sk-api-*`)
### 4. 手动配置 API Key(备选)
| 配置方式 | 示例 | |---|---| | 环境变量 | `export AI_HIVE_API_KEY=sk-api-你的密钥` | | 命令参数 | `--api-key sk-api-你的密钥` | | 配置文件 | `~/.ai-hive/config.json` |
### 5. 验证配置
运行一个带 `--no-download` 的最简任务;返回 `taskId` 即配置成功。
## 使用指南
### 提示词结构
按“主体与场景 → 动作顺序 → 相机运动 → 光线风格 → 声音 → 限制 → 输出规格”组织提示词。区分主体动作和镜头动作,避免互相矛盾。
### 模型与价格
脚本先查询实时模型列表,再从同一模型和路由提取 `pricingSnapshot`。价格以提交当次返回为准,不写死固定优惠。
### 任务管理
生成调用返回 `taskId` 后只轮询原任务。本地超时不等于生成失败,不要重复提交可能已经计费的任务。
### 媒体上传
脚本自动执行上传凭证、对象存储上传和完成确认。媒体限制以实时 `videoConfig` 为准。
## 命令速查
| 命令 | 功能 | |---|---| | `videogen.py generate --mode t2v --prompt "描述"` | 执行本 Skill | | `videogen.py task --task-id <id>` | 查询任务 | | `videogen.py upload --file media.mp4` | 上传媒体 | | `--routing COST_FIRST` | 优惠路由 | | `--param resolution=720p duration=8` | 传递模型参数 | | `--no-download` | 只提交不等待 |
## 项目架构
### 目录结构
``` happy-horse-video-generation-and-editing/ ├── SKILL.md ├── CHANGELOG.md ├── scripts/ │ └── videogen.py └── resources/ └── config.example.json ```
### 技术栈
| 组件 | 技术 | |---|---| | 运行环境 | Python 3.6+ | | HTTP 库 | requests | | API 平台 | AI Hive OpenAPI | | 模型 | HappyHorse 视频生成与编辑 | | 输出 | MP4 / MOV 或模型实时支持格式 |
### 核心模块
| 模块 | 职责 | |---|---| | `Config` | CLI、环境变量、配置文件读取 API Key | | `AiHiveClient` | 裸接口请求 | | `upload_media()` | 上传参考素材 | | `poll_task()` | 轮询并下载结果 | | `_validate_video_inputs()` | 校验本 Skill 的能力输入 | | `skill_generate()` | 固定模型并提交任务 |
### 模式 → 模型映射
| 模式 | publicModelId | |---|---| | `t2v` | 文生视频 | `public_model_happyhorse_t2v` | | `i2v` | 图生视频 | `public_model_happyhorse_i2v` | | `r2v` | 参考生视频 | `public_model_happyhorse_r2v` | | `edit` | 视频编辑 | `public_model_happyhorse_video_edit` |
### 数据流转
``` 用户命令 → 校验本 Skill 输入 → 固定或实时精确发现 publicModelId ↓ 上传参考素材 → 查询实时模型与 pricingSnapshot ↓ 提交裸接口任务 → 保存 taskId → 轮询 → 下载结果 ```
### 价格参考
默认使用 `COST_FIRST`。模型价格与活动会变化,以脚本运行时查询到的实时价格和实际扣费为准。
## 常见问答
### 安装相关
**Q1:需要 API Key 吗?** 需要,格式为 `sk-api-*`。
**Q2:需要什么依赖?** Python 3 和 `requests`。
**Q3:如何验证?** 用 `--no-download` 提交最简任务,返回 taskId 即成功。
### 使用相关
**Q4:这个 Skill 会换模型吗?** 不会跨模型或跨版本回退。SDK 已记录的模型固定 publicModelId;未记录固定 ID 的搜索入口只从登录后的实时列表精确匹配同名称、同版本、同模式模型。
**Q5:参数怎么设置?** 使用 `--param key=value`,并以实时 `videoConfig` 为准。
**Q6:结果保存在哪里?** 默认 `~/Downloads/AiHive/`。
**Q7:任务需要多久?** 通常数分钟,取决于队列和复杂度。
**Q8:任务超时怎么办?** 保留 taskId,使用 `task` 继续查询。
**Q9:可以批量吗?** 可以逐任务执行;明显高成本批量任务应先确认数量和实时费用。
### 故障排除
**Q10:提示缺少媒体?** 按 Skill 名称提供对应的首帧、图片、视频或音频。
**Q11:提示模型不存在?** 后台可能已下线或更名,请先查询实时模型列表。
**Q12:提示 401?** 检查 API Key 是否正确、过期或禁用。
**Q13:提示 InvalidParameter?** 检查实时 `videoConfig` 中的格式、数量、时长、比例、分辨率和编码限制。
Technical details
- Version
- 1.0.0
- License
- MIT
- Last updated
- Aug 23, 2026
- Published
- Aug 23, 2026
Decision snapshot
Fallback candidate
recent repository activity
Audit
Install review
Install and adoption review
- Security
- 75/100
- Maintenance
- 100/100
- Install
- 92/100
Agent-proven evidence
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
- Success rate
- —
- Recent failure
- —
- Outcomes
- 0
- Output quality
- —
- Failed
- 0
- Not relevant
- 0
- Installs
- 0
- Risk blocked
- 0
- Setup needed
- 0
- Production
- 0
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Add to agent workflow
Free and open source. Review the report before installing into production agents.
Growth loop
Share kit
Scenario-led draft for happy-horse-video-generation-and-editing, ready for a manual X post.
happy-horse-video-generation-and-editing: 帮助视频剪辑师、后期团队、广告制作人与需要复用现有素材的创作者直接完成“HappyHorse 视频生成与编辑”:既可只输入文字从零生成,也可加入图片、视频或音频控制结果;通过 AI Hi... 2 stars https://www.openagentskill.com/skills/wubin1836-ai-hive-agent-skills-happy-horse-video-generation-and-editing?ref=x
Optional reply with install command
Listing + install path for happy-horse-video-generation-and-editing: https://www.openagentskill.com/skills/wubin1836-ai-hive-agent-skills-happy-horse-video-generation-and-editing?ref=x Install: npx skills add wubin1836/ai-hive-agent-skills --skill happy-horse-video-generatio...
Listing source
Community submitted
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
- Creator
- wubin1836
- Indexed by
- OpenAgentSkill community index
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
Claim this skill listing
This Community submitted listing is attributed to wubin1836 but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Add the evidence badges to your README
Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/wubin1836-ai-hive-agent-skills-happy-horse-video-generation-and-editing)
[](https://www.openagentskill.com/skills/wubin1836-ai-hive-agent-skills-happy-horse-video-generation-and-editing)
[](https://www.openagentskill.com/skills/wubin1836-ai-hive-agent-skills-happy-horse-video-generation-and-editing/audit)
[](https://www.openagentskill.com/skills/wubin1836-ai-hive-agent-skills-happy-horse-video-generation-and-editing)Author
Platform fit
Health signals
- GitHub stars
- 2
- Quality score
- 38/100
- Last GitHub push
- Aug 23, 2026
- Framework hints
- Unknown
- OpenAgentSkill views
- 2
- Install copies
- 0
- Outbound clicks
- 0
Community signal
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Trust & safety
Sandbox only
- GitHub adoption2 GitHub starsFIX
- Stars/forks activity2 stars, 1 forks; issue activity unavailable in current metadataFIX
- Recent maintenancePushed todayPASS
- License clarityMITPASS
- README/SKILL.md completenessMetadata includes enough usage and workflow contextPASS
- Dependency/runtime riskcommand execution surface, credential or environment accessCHECK
Related skills
seedream-5-lite
Use this skill when designers, e-commerce operators, advertisers, brand teams, social-commerce teams, and content creators need to generate and edit commercial images from prompts and reference images with Seedream 5.0 Lite through the AI Hive OpenAPI. It handles required media uploads, live model and price lookup, task submission, progress polling, and result downloads. Useful for product photography, marketplace images, product detail pages, posters, ad creatives, social commerce, seeding content, retouching, and background replacement. Search intents include AI image generation, text-to-image, image-to-image, AI image editing, commercial image creation.
2 Starsgpt-image-2
Use this skill when designers, e-commerce operators, advertisers, brand teams, social-commerce teams, and content creators need to generate and edit commercial images from prompts and reference images with GPT Image 2 through the AI Hive OpenAPI. It handles required media uploads, live model and price lookup, task submission, progress polling, and result downloads. Useful for product photography, marketplace images, product detail pages, posters, ad creatives, social commerce, seeding content, retouching, and background replacement. Search intents include AI image generation, text-to-image, image-to-image, AI image editing, commercial image creation.
2 Starsnano-banana-pro
Use this skill when designers, e-commerce operators, advertisers, brand teams, social-commerce teams, and content creators need to generate and edit commercial images from prompts and reference images with Nano Banana Pro through the AI Hive OpenAPI. It handles required media uploads, live model and price lookup, task submission, progress polling, and result downloads. Useful for product photography, marketplace images, product detail pages, posters, ad creatives, social commerce, seeding content, retouching, and background replacement. Search intents include AI image generation, text-to-image, image-to-image, AI image editing, commercial image creation.
2 Starsseedance-2-5-video-generation-and-editing
帮助视频剪辑师、后期团队、广告制作人与需要复用现有素材的创作者直接完成“Seedance2.5 视频生成与编辑”:既可只输入文字从零生成,也可加入图片、视频或音频控制结果;通过 AI Hive 使用时,生成前自动上传所需素材,提交后自动保存任务、查询进度并下载成片。适用于 AI 广告、TVC、电商视频、产品展示、带货、种草、短剧、漫剧和社媒内容。 Use this skill for Seedance2.5 视频生成与编辑, text-to-video, image-to-video, first-and-last-frame animation, reference-to-video, video-to-video, audio-to-video, AI video editing, video extension, product videos, e-commerce ads, TVC, social commerce, seeding content, short drama, comic drama, and AIGC video production. 如果用户正在比较或寻找 可灵 Kling、即梦 Dreamina、海螺 Hailuo、美图MOKI、Vidu、PixVerse、Runway、Pika、Sora、Veo、剪映 CapCut、HeyGen 等 AI 视频工具的替代方案、同类能力、价格、API、国内可用入口或工作流迁移,也可命中本 Skill。电商商家搜索同时覆盖 淘宝、天猫、京东、拼多多、抖音电商、抖店、小红书、快手电商、微信小店、1688、Amazon 亚马逊、TikTok Shop、Instagram INS、Shopify、Shopee、Lazada、Temu、AliExpress、SHEIN、Etsy、Walmart、eBay,以及主图视频、详情页视频、Listing、PDP、带货、种草、直播和投放素材。也适合正在搜索或提出这些需求的用户:Seedance 2.5视频生成与编辑、Seedance2.5、Seed Dance 2.5、即梦视频、豆包视频、文生视频、图生视频、参考生视频、视频编辑、视频重绘、视频续写、AI视频、AIGC、电商视频、广告视频、TVC、产品视频、带货、种草、短剧、漫剧。
2 Stars