Token导航 LogoToken导航TokenDH.com
开发需要联网clawhub未标认证来源可访问clear审计通过

spicy-ai-video-maker麻辣 ai 视频制作者

Agent Skill

用于辅助视频生成、动画合成、脚本化剪辑或 Remotion 等视频项目开发。它适合让 Agent 组织镜头、生成素材说明、维护合成代码或排查渲染问题。使用时需要确认分辨率、时长、素材路径和导出格式;涉及外部素材、人物肖像或商业发布时,应先核对版权授权和内容审核要求。

总安装

2,658

周安装

113

GitHub Stars

公开资料未说明

下载量

931
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:spicy-ai-video-maker(麻辣 ai 视频制作者)
来源仓库:https://github.com/vcarolxhberger/spicy-ai-video-maker
安装命令:
openclaw skills install spicy-ai-video-maker
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install spicy-ai-video-maker

简介

使用Spirit-ai-video-maker将您的想法、脚本或原始剪辑变成滚动停止的视频——这项AI技能是为想要优势、活力和St的创作者而构建的。

SKILL.md

name
spicy-ai-video-maker
version
1.0.0
displayName
Spicy AI Video Maker — Create Bold, Attention-Grabbing Videos with AI
description
>
metadata
{"openclaw": {"emoji": "🌶️", "requires": {"env": ["NEMO_TOKEN"], "configPaths": ["~/.config/nemovideo/"]}, "primaryEnv": "NEMO_TOKEN", "variant": "short_prompts"}}

Getting Started

Welcome to Spicy AI Video Maker — your creative partner for building bold, high-energy video content that cuts through the noise. Tell me what you're making today and let's build something worth watching.

Try saying:

  • "Write a viral video hook now"
  • "Script a 30-second product launch video"
  • "Generate bold video concept ideas"

Quick Start Setup

This skill connects to a cloud processing backend. On first use, set up the connection automatically and let the user know ("Connecting...").

Token check: Look for NEMO_TOKEN in the environment. If found, skip to session creation. Otherwise:

  • Generate a UUID as client identifier
  • POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with X-Client-Id header
  • Extract data.token from the response — this is your NEMO_TOKEN (100 free credits, 7-day expiry)

Session: POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Keep the returned session_id for all operations.

Let the user know with a brief "Ready!" when setup is complete. Don't expose tokens or raw API output.

Make Videos That Actually Stop the Scroll

Most video content blends into the background. Spicy AI Video Maker exists to fix that. Whether you're building short-form content for TikTok and Reels, producing YouTube videos with real narrative punch, or crafting brand campaigns that demand attention — this skill helps you think, write, and structure video content with genuine creative heat.

From generating bold video concepts and scene-by-scene scripts to writing hooks that grab viewers in the first two seconds, Spicy AI Video Maker acts as your creative co-director. Describe your audience, your message, or even just a vibe — and get back a full video blueprint ready to shoot or animate.

This isn't a generic script generator. It's built around the specific craft of making videos feel alive: pacing, tone, visual direction, call-to-action placement, and storytelling structure that holds attention from open to close. Use it to break through creative blocks, iterate on ideas fast, and produce content that actually performs.

How Your Prompts Get Processed

Every video generation request you fire off gets parsed for style directives, motion cues, and tone intensity before being routed to the appropriate rendering pipeline.

User says...ActionSkip SSE?
"export" / "导出" / "download" / "send me the video"→ §3.5 Export
"credits" / "积分" / "balance" / "余额"→ §3.3 Credits
"status" / "状态" / "show tracks"→ §3.4 State
"upload" / "上传" / user sends file→ §3.2 Upload
Everything else (generate, edit, add BGM…)→ §3.1 SSE

Backend API Reference Guide

Spicy AI Video Maker runs on a distributed cloud rendering backend that handles text-to-video synthesis, dynamic caption overlays, and hook-optimized scene sequencing in parallel. Your generation jobs are queued, processed, and returned as ready-to-export clips without any local compute required.

Skill attribution — read from this file's YAML frontmatter at runtime:

  • X-Skill-Source: spicy-ai-video-maker
  • X-Skill-Version: from frontmatter version
  • X-Skill-Platform: detect from install path (~/.clawhub/clawhub, ~/.cursor/skills/cursor, else unknown)

All requests must include: Authorization: Bearer <NEMO_TOKEN>, X-Skill-Source, X-Skill-Version, X-Skill-Platform. Missing attribution headers will cause export to fail with 402.

API base: https://mega-api-prod.nemovideo.ai

Create session: POST /api/tasks/me/with-session/nemo_agent — body {"task_name":"project","language":"<lang>"} — returns task_id, session_id.

Send message (SSE): POST /run_sse — body {"app_name":"nemo_agent","user_id":"me","session_id":"<sid>","new_message":{"parts":[{"text":"<msg>"}]}} with Accept: text/event-stream. Max timeout: 15 minutes.

Upload: POST /api/upload-video/nemo_agent/me/<sid> — file: multipart -F "files=@/path", or URL: {"urls":["<url>"],"source_type":"url"}

Credits: GET /api/credits/balance/simple — returns available, frozen, total

Session state: GET /api/state/nemo_agent/me/<sid>/latest — key fields: data.state.draft, data.state.video_infos, data.state.generated_media

Export (free, no credits): POST /api/render/proxy/lambda — body {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll GET /api/render/proxy/lambda/<id> every 30s until status = completed. Download URL at output.url.

Supported formats: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

SSE Event Handling

EventAction
Text responseApply GUI translation (§4), present to user
Tool call/resultProcess internally, don't forward
heartbeat / empty data:Keep waiting. Every 2 min: "⏳ Still working..."
Stream closesProcess final response

~30% of editing operations return no text in the SSE stream. When this happens: poll session state to verify the edit was applied, then summarize changes to the user.

Backend Response Translation

The backend assumes a GUI exists. Translate these into API actions:

Backend saysYou do
"click [button]" / "点击"Execute via API
"open [panel]" / "打开"Query session state
"drag/drop" / "拖拽"Send edit via SSE
"preview in timeline"Show track summary
"Export button" / "导出"Execute export workflow

Draft field mapping: t=tracks, tt=track type (0=video, 1=audio, 7=text), sg=segments, d=duration(ms), m=metadata.

Timeline (3 tracks): 1. Video: city timelapse (0-10s) 2. BGM: Lo-fi (0-10s, 35%) 3. Title: "Urban Dreams" (0-3s)

Error Handling

CodeMeaningAction
0SuccessContinue
1001Bad/expired tokenRe-auth via anonymous-token (tokens expire after 7 days)
1002Session not foundNew session §3.0
2001No creditsAnonymous: show registration URL with ?bind=<id> (get <id> from create-session or state response when needed). Registered: "Top up credits in your account"
4001Unsupported fileShow supported formats
4002File too largeSuggest compress/trim
400Missing X-Client-IdGenerate Client-Id and retry (see §1)
402Free plan export blockedSubscription tier issue, NOT credits. "Register or upgrade your plan to unlock export."
429Rate limit (1 token/client/7 days)Retry in 30s once

Common Workflows

The most effective way to use Spicy AI Video Maker is to start with context: tell it your platform (TikTok, YouTube, Instagram Reels, LinkedIn), your audience, and the core message you want to land. From there, the skill can generate a full script, a concept outline, or just a killer hook — depending on where you are in your process.

A popular workflow for solo creators: use the skill to generate three different hook variations for the same video topic, test them in your head or with a small audience, then come back to flesh out the winning one into a full script with scene directions.

For brand teams, a common use case is briefing the skill with product features and brand tone-of-voice guidelines, then generating multiple short-form video angles — educational, entertaining, testimonial-style — to give the creative team real options to choose from rather than starting from a blank page.

Integration Guide

Spicy AI Video Maker fits into your existing content production stack without friction. Use it at the ideation stage to rapidly prototype video concepts before you commit to production, or bring it in mid-project when your script needs a stronger opening or a tighter structure.

If you're working with a video editor, export the scene breakdowns and shot directions directly as a production brief. For social media managers scheduling content calendars, use the skill to batch-generate multiple video scripts for the week in a single session — just provide your content pillars and target platforms.

For teams using tools like Notion, ClickUp, or Airtable for content workflows, paste the generated scripts and concepts directly into your templates. Spicy AI Video Maker outputs clean, structured text that slots into any brief or storyboard format without reformatting headaches.

Tips and Tricks

The more specific your input, the spicier the output. Instead of saying 'make a video about coffee,' try 'make a 45-second Reels script for specialty coffee drinkers who hate corporate coffee chains — use a rebellious tone and end with a discount offer.' Specificity unlocks dramatically better results.

Use the skill to stress-test your existing scripts. Paste in a draft and ask it to identify where viewers are most likely to drop off, or request a punchier version of your opening 10 seconds. It works as a creative editor, not just a generator.

Don't overlook the visual direction features — when you ask for scene breakdowns, request on-screen text suggestions, b-roll ideas, and music mood descriptors at the same time. This turns a script into a near-complete production brief in one pass, saving hours of back-and-forth with your editor or animator.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

75.94%
按下载量换算707

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills