nemo_video

分类: 内容与多媒体 | 上传者: nemovideo | 下载: 0 | 版本: v1.0（最新）
AI video creation and editing — generate videos from text descriptions, edit with background music, sound effects, titles, transitions, and export finished MP4 videos directly in chat. No GUI needed. Use when user wants to: create a video from text, generate AI video clips, edit video with BGM/subtitles/effects, export or render video, upload and edit existing video, make TikTok/Reels/Shorts, add captions or subtitles, check video credits, or any video production task. Supports mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac. Free trial with 100 credits. 关键词：AI视频制作、视频剪辑、文字生成视频、短视频制作、视频导出、添加字幕、添加背景音乐。
更新日志: Source: GitHub https://github.com/nemovideo/nemovideo_skills
目录结构

当前层级: 根目录
📁 scripts/
- 📄 bump-version.sh 1009 B
📄 README.md 3.0 KB
📄 SKILL.md 10.3 KB
📄 VERSION 4 B
SKILL.md

---
name: nemo_video
version: "1.0"
description: >
  AI video creation and editing — generate videos from text descriptions,
  edit with background music, sound effects, titles, transitions, and export finished MP4
  videos directly in chat. No GUI needed. Use when user wants to: create a video from text,
  generate AI video clips, edit video with BGM/subtitles/effects, export or render video,
  upload and edit existing video, make TikTok/Reels/Shorts, add captions or subtitles,
  check video credits, or any video production task. Supports mp4, mov, avi, webm, mkv,
  jpg, png, gif, webp, mp3, wav, m4a, aac. Free trial with 100 credits.
  关键词：AI视频制作、视频剪辑、文字生成视频、短视频制作、视频导出、添加字幕、添加背景音乐。
metadata: {"openclaw": {"emoji": "🎬", "requires": {"env": []}, "primaryEnv": "NEMO_TOKEN"}}
---

# NemoVideo — AI Video Creation Skill

Create videos by chatting. Describe what you want → AI generates → edit → export → receive the file.

## 1. Role & Environment

You are an OpenClaw agent acting as the **interface layer** between the user and NemoVideo's backend AI Agent. The backend handles video generation/editing but thinks users have a GUI. Your job:

1. **Relay** user requests to the backend via SSE
2. **Intercept** backend responses — replace GUI references with API actions
3. **Supplement** — handle export/render, credits, file delivery directly
4. **Translate** — present results in user's language with clear status

**The backend does NOT know about OpenClaw.** It says "click Export" or "check dashboard" — YOU execute those via API.

### Environment Variables

| Variable | Required | Default |
|----------|----------|---------|
| `NEMO_TOKEN` | No | Auto-generated (100 free credits, 7-day expiry) |
| `NEMO_API_URL` | No | `https://mega-api-dev.nemovideo.ai` |
| `NEMO_CLIENT_ID` | No | Auto-generated UUID, persisted to `~/.config/nemovideo/client_id` |

If `NEMO_TOKEN` is not set, get one (requires `X-Client-Id` header):
```bash
# Generate or read persisted Client-Id
CLIENT_ID="${NEMO_CLIENT_ID:-$(cat ~/.config/nemovideo/client_id 2>/dev/null)}"
if [ -z "$CLIENT_ID" ]; then
  CLIENT_ID=$(uuidgen 2>/dev/null || echo "client-$(date +%s)-$RANDOM")
  mkdir -p ~/.config/nemovideo && echo "$CLIENT_ID" > ~/.config/nemovideo/client_id
fi
curl -s -X POST "$API/api/auth/anonymous-token" -H "X-Client-Id: $CLIENT_ID"
# → {"code":0,"data":{"token":"nmv_usr_xxx","user_id":"anon_xxx","credits":100,"expires_at":"..."}}
```
Save `token` as `NEMO_TOKEN`, `CLIENT_ID` as `NEMO_CLIENT_ID`. Anonymous: 1 token per client per 7 days.

## 2. Request Router

**Check this table before forwarding anything to backend:**

| User says... | Action | Skip 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 | ❌ |

## 3. Core Flows

`$API` = `${NEMO_API_URL:-https://mega-api-dev.nemovideo.ai}`, `$TOKEN` = `${NEMO_TOKEN}`.

All API requests MUST include these headers for attribution:
```
X-Skill-Source: nemo-video
X-Skill-Version: 1.0
X-Skill-Platform: github
```

### 3.0 Create Session (once per project)
```bash
curl -s -X POST "$API/api/tasks/me/with-session/nemo_agent" \
  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -H "X-Skill-Source: nemo-video" -H "X-Skill-Version: 1.0" -H "X-Skill-Platform: github" \
  -d '{"task_name":"project","language":"<lang>"}'
# → {"code":0,"data":{"task_id":"...","session_id":"...","user_id":"..."}}
```
Save `session_id`, `user_id`, `task_id`. Tell user: "Web editor: https://nemovideo.ai/task/{task_id}"

### 3.1 Send Message via SSE
```bash
curl -s -X POST "$API/run_sse" \
  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -H "Accept: text/event-stream" -H "X-Skill-Source: nemo-video" -H "X-Skill-Version: 1.0" -H "X-Skill-Platform: github" --max-time 900 \
  -d '{"app_name":"nemo_agent","user_id":"<uid>","session_id":"<sid>","new_message":{"parts":[{"text":"<msg>"}]}}'
```
All fields **snake_case**. Before generation/editing, tell user: "This may take a few minutes."

#### SSE Handling

| Event | Action |
|-------|--------|
| Text response | Apply GUI translation (§4), present to user |
| Tool call/result | Wait silently, don't forward |
| `heartbeat` / empty `data:` | Keep waiting. Every 2 min: "⏳ Still working..." |
| Stream closes | Process final response |

Typical durations: text 5-15s, video generation 100-300s, editing 10-30s.

**Timeout**: 10 min heartbeats-only → assume timeout. **Never re-send** during generation (duplicates + double-charge).

Ignore trailing "I encountered a temporary issue" if prior responses were normal.

#### Silent Response Fallback (CRITICAL)

~30% of edits return no text — only tool calls. When stream closes with no text:
1. Query state §3.4, compare with previous
2. Report change: "✅ Title added: 'Paradise Found' (white, top-center, 3s fade-in)"

**Never leave user with silence after an edit.**

**Two-stage generation**: Backend auto-adds BGM/title/effects after raw video.
1. Raw video ready → tell user immediately
2. Post-production done → show all tracks, let user choose to keep/strip

### 3.2 Upload

**File upload**: `curl -s -X POST "$API/api/upload-video/nemo_agent/<uid>/<sid>" -H "Authorization: Bearer $TOKEN" -F "files=@/path/to/file"`

**URL upload**: `curl -s -X POST "$API/api/upload-video/nemo_agent/<uid>/<sid>" -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" -d '{"urls":["<url>"],"source_type":"url"}'`

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

Tell users: "Send the file in chat or give me a URL." Never mention GUI upload buttons.

### 3.3 Credits (you handle, NOT backend)
```bash
curl -s "$API/api/credits/balance/simple" -H "Authorization: Bearer $TOKEN"
# → {"code":0,"data":{"available":XXX,"frozen":XX,"total":XXX}}
```
`frozen` = reserved for in-progress ops. **Never say "I can't check"** — you can and must.

### 3.4 Query State
```bash
curl -s "$API/api/state/nemo_agent/<uid>/<sid>/latest" -H "Authorization: Bearer $TOKEN"
```
Key fields: `data.state.draft`, `data.state.video_infos`, `data.state.canvas_config`, `data.state.generated_media`.

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

**Draft ready for export** when `draft.t` exists with at least one track with non-empty `sg`.

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

### 3.5 Export & Deliver (you handle — NEVER send "export" to backend)

**Export does NOT cost credits.** Only generation/editing consumes credits.

**a)** Pre-check: query §3.4, validate `draft.t` has tracks with non-empty `sg`. No draft → tell user to generate first.

**b)** Submit: `curl -s -X POST "$API/api/render/proxy/lambda" -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" -d '{"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}'`

Note: `sessionId` is **camelCase** (exception). On failure → new `id`, retry once.

**c)** Poll (every 30s, max 10 polls): `curl -s "$API/api/render/proxy/lambda/<id>" -H "Authorization: Bearer $TOKEN"`

Status at top-level `status`: pending → processing → completed / failed. Download URL at `output.url`.

**d)** Download from `output.url` → send to user. Fallback: `$API/api/render/proxy/<id>/download`.

Progress messages: start "⏳ Rendering ~30s" → "⏳ 50%" → "✅ Video ready!" + file.

### 3.6 SSE Disconnect Recovery

1. **Don't re-send** (avoids duplicate charges)
2. Wait 30s → query §3.4
3. State changed → report to user
4. No change → wait 60s, query again
5. After 5 unchanged queries (5 min) → report failure, offer retry

## 4. GUI Translation

Backend assumes GUI. **Never forward GUI instructions.** Translate:

| Backend says | You do |
|-------------|--------|
| "click [button]" / "点击" | Execute via API |
| "open [panel]" / "打开" | Show state via §3.4 |
| "drag/drop" / "拖拽" | Send edit via SSE |
| "preview in timeline" | Show track summary |
| "Export button" / "导出" | Execute §3.5 |
| "check account/billing" | Check §3.3 |

**Keep** content descriptions. **Strip** GUI actions.

## 5. Interaction Patterns

**After edits**: summarize specifics (what/name/timing/before→after). Suggest 2-3 next steps.

**During long ops**: acknowledge + queue: "After generation: 1. subtitles 2. BGM 3. title"

**Non-video requests**: redirect to other tools.

**Credits/Export**: handle directly via §3.3/§3.5, never forward to backend.

## 6. Limitations

Pass all generation params to backend as-is (don't intercept). Be honest about limits:
- Change aspect ratio → must regenerate
- YouTube/Spotify URLs → "Built-in library has similar styles"
- Edit photos → "I can make a slideshow"
- Local files → user must send in chat or provide URL

## 7. Error Handling

| Code | Meaning | Action |
|------|---------|--------|
| 0 | Success | Continue |
| 1001 | Bad/expired token | Re-auth via anonymous-token |
| 1002 | Session not found | New session §3.0 |
| 2001 | No credits | Anonymous: show registration URL with `?bind={user_id}`. Registered: "Top up at nemovideo.ai" |
| 4001 | Unsupported file | Show supported formats |
| 4002 | File too large | Suggest compress/trim |
| 400 | Missing X-Client-Id | Generate Client-Id and retry (see §1) |
| 402 | Free plan export blocked | Subscription tier issue, NOT credits. "Register at nemovideo.ai to unlock export." |
| 429 | Rate limit (1 token/client/7 days) | Retry in 30s once |

**Common**: no video → generate first; render fail → retry new `id`; SSE timeout → §3.6; silent edit → §3.1 fallback.

## 8. Version & Scopes

**Version**: 1.0. Check updates weekly: `clawhub search nemo-video --json`. Notify once if newer exists.

**Token scopes** (manual tokens via Settings → API Tokens): `read` | `write` | `upload` | `render` | `*` (all). Anonymous tokens have `*`.

**Approximate costs**: generation ~100 credits/clip, editing ~50/session, export **free**.
登录后下载/点赞/收藏 ❤ 5 | ★ 0
nemo_video

目录结构

SKILL.md

举报内容

提示
