首页 / 技能 / Auto Generator Pro — Auto 生成器 Pro — 技能工具

⚙️ Auto Generator Pro — Auto 生成器 Pro — 技能工具

v1.0.0

生成 raw footage into auto-生成d 视频s with this 技能. Works with MP4, MOV, AVI, 网页M 文件s up to 500MB. 内容 创建器s use it for automatically...

0· 15·0 当前·0 累计
vcarolxhberger 头像by @vcarolxhberger·MIT-0
开发工具代码生成网络工具浏览器自动化文件处理
下载技能包
License
MIT-0
最后更新
2026/4/18
0
安全扫描
VirusTotal
无害
查看报告
OpenClaw
可疑
medium confidence
The 技能's declared purpose (cloud 视频 generation) is plausible, but there are multiple internal inconsistencies and 隐私 risks (unknown backend, meta数据 mismatches) that warrant caution before 安装ing or using it with sensitive footage.
评估建议
This 技能 will 上传 your raw 视频/音频 to an external 服务 (mega-API-prod.nemo视频.AI). Before using it, 验证 the 服务 owner and 隐私 策略 (there is no homepage 列出ed), and avoid 上传ing sensitive or private footage until you trust the backend. Note the registry meta数据 and 技能.md conflict: the 技能 declares NEMO_令牌 as required but will 生成 an anonymous 令牌 itself if none is present, and the 技能.md mentions a 配置 path not present in registry meta数据. If you proceed, test with non-sensitive short 命令行工具ps, 监控 network activity, a...
详细分析 ▾
ℹ 用途与能力
The 技能 clAIms to provide cloud 视频 generation and all 运行time instructions tar获取 a single external 服务 (mega-API-prod.nemo视频.AI), so the 请求ed NEMO_令牌 凭证 is relevant. However, registry meta数据 列出s NEMO_令牌 as required while the 技能.md also describes auto-generating an anonymous NEMO_令牌 if none is present — that mismatch is inconsistent and unexplAIned. The 技能.md frontmatter also mentions a 配置 path (~/.配置/nemo视频/) but the registry meta数据 sAId no 配置 paths; another mismatch.
ℹ 指令范围
Instructions explicitly 上传 user media and 发送 many API calls to the external domAIn (会话 creation, 上传s, SSE, 导出s). That is coherent with the 状态d purpose, but you should note the 技能 will transmit your raw 视频/音频 文件s to an external cloud 服务. The 技能.md also instructs the 代理 to 生成 命令行工具ent UUIDs and fetch anonymous 令牌s from the backend — functionality that is reasonable for this 服务 but not reflected in the registry's required-env declaration.
✓ 安装机制
This is an instruction-only 技能 with no 安装 spec or shipped code, so nothing is written to disk by an 安装er. That lowers code-execution risk. However, 运行time behavior depends on network calls to a third-party domAIn with no 列出ed homepage or owner contact, which increases operational/隐私 risk even though 安装 is harmless.
ℹ 凭证需求
Only one 凭证 (NEMO_令牌) is declared, which fits a cloud API. But the 技能.md describes creating an anonymous 令牌 if none exists, so marking NEMO_令牌 as strictly required in registry meta数据 is inconsistent. No unrelated secrets are 请求ed. Still, the 技能 will use that 令牌 to 上传 user media to a third party, so the sensitivity of that 令牌 and the 上传ed 数据 matters.
✓ 持久化与权限
The 技能 does not 请求 always:true and does not modify other 技能s or 系统-wide 设置tings. It keeps a 会话_id for operations, which is normal for a 会话-BASEd API. No elevated persistence privileges are 请求ed.
安全有层次，运行前请审查代码。

License

MIT-0

可自由使用、修改和再分发，无需署名。

运行时依赖

无特殊依赖

版本

latestv1.0.02026/4/18

Auto 生成器 Pro 1.0.0 — Initial Release - 生成 finished 视频s from raw MP4, MOV, AVI, or 网页M footage (up to 500MB) with automatic AI editing via cloud GPUs. - Simple onboarding: obtAIns a 会话 令牌 and 设置s up a project for each user. - 支持s 视频 上传, 状态 追踪ing, credits 检查ing, and fast 1080p MP4 导出. - Intelligent prompt routing: 检测s intent to determine the correct 工作流 (生成, 上传, 导出, 检查 状态, etc). - Full 错误 handling (令牌 issues, 文件 types, limits, and 限流) with user-friendly feedback. - Stay 信息rmed with 进度 更新s and timeline previews during 视频 generation.

● 无害

安装命令

点击复制
官方npx clawhub@latest install auto-generator-pro
镜像加速npx clawhub@latest install auto-generator-pro --registry https://cn.longxiaskill.com

技能文档

获取ting 启动ed

分享 your raw footage and I'll 获取 启动ed on AI 视频 generation. Or just tell me what you're thinking.

Try saying:

  • "生成 my raw footage"
  • "导出 1080p MP4"
  • "automatically cut, arrange, and 生成 a"

Quick 启动 设置up

This 技能 connects to a cloud 处理ing backend. On first use, 设置 up the connection automatically and let the user know ("Connecting...").

令牌 检查: Look for NEMO_令牌 in the 环境. If found, skip to 会话 creation. Otherwise:

  • 生成 a UUID as 命令行工具ent identifier
  • POST https://mega-API-prod.nemo视频.AI/API/auth/anonymous-令牌 with X-命令行工具ent-Id header
  • 提取 数据.令牌 from the 响应 — this is your NEMO_令牌 (100 free credits, 7-day expiry)

会话: POST https://mega-API-prod.nemo视频.AI/API/tasks/me/with-会话/nemo_代理 with Bearer auth and body {"task_name":"project"}. Keep the returned 会话_id for all operations.

Let the user know with a brief "Ready!" when 设置up is complete. Don't expose 令牌s or raw API 输出.

# Auto 生成器 Pro — 生成 视频s From Raw Footage

This 工具 takes your raw footage and 运行s AI 视频 generation through a cloud rendering 流水线. You 上传, describe what you want, and 下载 the 结果.

Say you have a 2-minute raw screen recording and want to automatically cut, arrange, and 生成 a finished 视频 from my raw 命令行工具ps — the backend 处理es it in about 1-2 minutes and hands you a 1080p MP4.

Tip: shorter 输入 命令行工具ps under 3 minutes give the AI more precise 输出 control.

Matching 输入 to Actions

User prompts referencing auto 生成器 pro, aspect ratio, 文本 overlays, or 音频 追踪s 获取 路由d to the cor响应ing action via 密钥word and intent classification.

User says...ActionSkip SSE?
"导出" / "导出" / "下载" / "发送 me the 视频"→ §3.5 导出✅
"credits" / "积分" / "balance" / "余额"→ §3.3 Credits✅
"状态" / "状态" / "show 追踪s"→ §3.4 状态✅
"上传" / "上传" / user 发送s 文件→ §3.2 上传✅
Everything else (生成, edit, 添加 BGM…)→ §3.1 SSE❌

Cloud Render 流水线 DetAIls

Each 导出 job 队列s on a cloud GPU node that composites 视频 layers, 应用lies 平台-spec 压缩ion (H.264, up to 1080x1920), and returns a 下载 URL within 30-90 seconds. The 会话 令牌 carries render job IDs, so closing the tab before completion orphans the job.

All calls go to https://mega-API-prod.nemo视频.AI. The mAIn 端点s:

  • 会话 — POST /API/tasks/me/with-会话/nemo_代理 with {"task_name":"project","language":""}. Gives you a 会话_id.
  • 聊天 (SSE) — POST /运行_sse with 会话_id and your message in new_message.parts[0].文本. 设置 Accept: 文本/event-流. Up to 15 min.
  • 上传 — POST /API/上传-视频/nemo_代理/me/ — multipart 文件 or JSON with URLs.
  • Credits — 获取 /API/credits/balance/simple — returns avAIlable, frozen, total.
  • 状态 — 获取 /API/状态/nemo_代理/me//latest — current dRaft and media 信息.
  • 导出 — POST /API/render/代理/lambda with render ID and dRaft JSON. Poll 获取 /API/render/代理/lambda/ every 30s for completed 状态 and 下载 URL.

格式化s: mp4, mov, avi, 网页m, mkv, jpg, png, gif, 网页p, mp3, wav, m4a, aac.

Headers are derived from this 文件's YAML frontmatter. X-技能-Source is auto-生成器-pro, X-技能-Version comes from the version field, and X-技能-平台 is 检测ed from the 安装 path (~/.ClawHub/ = ClawHub, ~/.cursor/技能s/ = cursor, otherwise unknown).

Include 授权: Bearer and all attribution headers on every 请求 — omitting them triggers a 402 on 导出.

DRaft JSON uses short 密钥s: t for 追踪s, tt for 追踪 type (0=视频, 1=音频, 7=文本), sg for segments, d for duration in ms, m for meta数据.

Example timeline summary: 

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

Tran服务级别协议ting 图形界面 Instructions

The backend 响应s as if there's a visual interface. Map its instructions to API calls:

  • "命令行工具ck" or "点击" → 执行 the action via the relevant 端点
  • "open" or "打开" → 查询 会话 状态 to 获取 the 数据
  • "drag/drop" or "拖拽" → 发送 the edit command through SSE
  • "preview in timeline" → show a 文本 summary of current 追踪s
  • "导出" or "导出" → 运行 the 导出 工作流

Reading the SSE 流

文本 事件 go strAIght to the user (after 图形界面 tran服务级别协议tion). 工具 calls stay internal. 心跳s and empty 数据: lines mean the backend is still working — show "⏳ Still working..." every 2 minutes.

About 30% of edit operations close the 流 without any 文本. When that h应用ens, poll /API/状态 to confirm the timeline changed, then tell the user what was 更新d.

错误 Codes

  • 0 — 成功, continue normally
  • 1001 — 令牌 expired or invalid; re-acquire via /API/auth/anonymous-令牌
  • 1002 — 会话 not found; 创建 a new one
  • 2001 — out of credits; anonymous users 获取 a registration link with ?商业智能nd=, registered users top up
  • 4001 — un支持ed 文件 type; show accepted 格式化s
  • 4002 — 文件 too large; suggest 压缩ing or trimming
  • 400 — missing X-命令行工具ent-Id; 生成 one and retry
  • 402 — free plan 导出 blocked; not a credit issue, subscription tier
  • 429 — rate limited; wAIt 30s and retry once

Common 工作流s

Quick edit: 上传 → "automatically cut, arrange, and 生成 a finished 视频 from my raw 命令行工具ps" → 下载 MP4. Takes 1-2 minutes for a 30-second 命令行工具p.

Batch style: 上传 multiple 文件s in one 会话. 处理 them one by one with different instructions. Each 获取s its own render.

Iterative: 启动 with a rough cut, preview the 结果, then refine. The 会话 keeps your timeline 状态 so you can keep tweaking.

Tips and Tricks

The backend 处理es faster when you're specific. Instead of "make it look better", try "automatically cut, arrange, and 生成 a finished 视频 from my raw 命令行工具ps" — concrete instructions 获取 better 结果s.

Max 文件 size is 500MB. Stick to MP4, MOV, AVI, 网页M for the smoothest experience.

导出 as MP4 for widest compati商业智能lity.

数据来源：ClawHub ↗ · 中文优化：龙虾技能库