Best YouTube Video Editor — AI-Powered Editing for Creators

The best-youtube-video-editor skill on ClawHub transforms how YouTube creators produce content by enabling conversational, AI-driven video editing without timelines or complex software. Trim dead air, add chapter markers, layer captions, adjust pacing, and optimize exports — all through plain-language instructions. On first use, the skill auto-configures credentials via NemoVideo API, so you're editing within seconds of activation. Built for YouTubers, educators, podcasters, and brand channels who need fast turnaround without sacrificing quality. Supports mp4, mov, avi, webm, and mkv formats.

## 0. First Contact

When the user opens this skill or sends their first message, **greet them immediately**:

> Hey! Ready to produce your best YouTube video yet? Whether you need to trim footage, punch up your pacing, add captions, or export a YouTube-optimized file — just tell me what you're working on and we'll get it done fast. What are we editing today?

**Try saying:**
- "Cut out all silences longer than 2 seconds from my talking-head interview and add a subtle zoom-in on each cut to keep energy high."
- "Add auto-generated captions styled for YouTube Shorts — bold white text, centered, with a black outline — and export as a vertical mp4."
- "Take my 30-minute podcast recording and create a YouTube chapter list with timestamps based on topic changes, then trim the intro to under 30 seconds."

**IMPORTANT**: Always greet the user proactively on first contact. Let them know you're setting up while connecting.

### Auto-Setup (on first use)

When the user first opens this skill, run through these setup steps and briefly let them know you're connecting (e.g. "⚡ Connecting to NemoVideo..."):

1. **Check token**: If `NEMO_TOKEN` env var is set, use it. Otherwise:
2. **Read or generate Client-ID**:
   - Read `~/.config/nemovideo/client_id` if it exists
   - Otherwise generate a UUID, save it to `~/.config/nemovideo/client_id`
   - This file stores only a UUID for rate-limit tracking — no secrets or credentials.
3. **Acquire anonymous token**:
   ```bash
   curl -s -X POST "https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token" -H "X-Client-Id: $CLIENT_ID"
   ```
   Store the returned `token` as `NEMO_TOKEN` for this session. You get 100 free credits.
4. **Create a session** (§3.0) so you're ready to work immediately.

**Transparency**: Keep setup communication brief — tell the user you're connecting to NemoVideo while you set up, but don't dump raw API responses or token strings into the chat. The user should know setup is happening but doesn't need every technical detail.

# Edit YouTube Videos by Just Describing What You Want

The best-youtube-video-editor skill was built specifically around the YouTube creator workflow — not generic video production. Whether you're cutting a 45-minute talking-head recording down to a punchy 8-minute video, adding animated lower-thirds for your channel branding, or syncing background music to scene transitions, this skill understands YouTube-native concepts like retention editing, hook optimization, and end-screen placement.

At its core, the skill uses a conversational editing model. Instead of dragging clips on a timeline, you describe your intent: 'Remove all pauses longer than 1.5 seconds,' or 'Add a zoom punch at every cut.' The OpenClaw agent interprets these instructions, constructs the appropriate editing pipeline, and executes changes through the NemoVideo API backend — returning a preview or final render depending on your request.

The OpenClaw agent also maintains context across your session, so you can iterate naturally: refine a cut, undo a color grade, or re-export at a different resolution without starting over. This makes the skill especially powerful for creators who revise frequently or work across multiple video formats for Shorts, standard uploads, and embedded web content.

### Environment Variables

| Variable | Required | Default | What it does |
|----------|----------|--------|--------|
| `NEMO_TOKEN` | No | Auto-acquired on first use via `/api/auth/anonymous-token` (100 free credits, expires in 7 days, revocable via Settings → API Tokens) | Authenticates API requests |
| `NEMO_API_URL` | No | `https://mega-api-prod.nemovideo.ai` | API base URL |
| `NEMO_WEB_URL` | No | `https://nemovideo.com` | Web base URL |
| `NEMO_CLIENT_ID` | No | Auto-generated UUID, persisted to `~/.config/nemovideo/client_id` (UUID only — no secrets stored) | Rate-limit tracking |
| `SKILL_SOURCE` | No | Auto-detected from install path, fallback `unknown` | Usage attribution |

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 "https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token" -H "X-Client-Id: $CLIENT_ID"
# → {"code":0,"data":{"token":"nmv_usr_xxx","credits":100,...}}
```
Save `token` as `NEMO_TOKEN`, `CLIENT_ID` as `NEMO_CLIENT_ID`. Anonymous: 1 token per client per 7 days; token expires in 7 days and can be revoked at any time via **Settings → API Tokens** on nemovideo.com. If your token expires, request a new one with the same `X-Client-Id`.

**Local persistence:** This skill writes `~/.config/nemovideo/client_id` to persist the Client-Id across sessions. This avoids generating a new ID on every request, which would hit the per-IP rate limit quickly (default 10 tokens per 7 days per IP). The file contains only a UUID — no credentials are stored locally.

## 2. Endpoint Dispatch Map — Where Each Request Gets Routed

Every action in the editor pipeline hits a distinct endpoint — the table below maps each operation to its correct destination.

| 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 Editing Workflows — From Raw Footage to Finished Cut

$API = `${NEMO_API_URL:-https://mega-api-prod.nemovideo.ai}`, $TOKEN = `${NEMO_TOKEN}`, $WEB = `${NEMO_WEB_URL:-https://nemovideo.com}`.

Skill attribution variables — do NOT hardcode:
- `$SKILL_NAME` = this file's YAML frontmatter `name`
- `$SKILL_VERSION` = this file's YAML frontmatter `version`
- `$SKILL_SOURCE` = detect at runtime using the first match:
  1. Env `SKILL_SOURCE` if set
  2. If this file's path contains a known platform directory (e.g. `~/.clawhub/` → `clawhub`, `~/.cursor/skills/` → `cursor`)
  3. Fallback: `unknown`

**CRITICAL**: ALL API requests (including render/export/upload/state/credits) MUST include these headers. Missing them will cause export to fail with 402.
```
X-Skill-Source: $SKILL_NAME
X-Skill-Version: $SKILL_VERSION
X-Skill-Platform: $SKILL_SOURCE
```

### 3.0 Initializing an Edit Session
```bash
curl -s -X POST "https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent" \
  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -H "X-Skill-Source: $SKILL_NAME" -H "X-Skill-Version: $SKILL_VERSION" -H "X-Skill-Platform: $SKILL_SOURCE" \
  -d '{"task_name":"project","language":"<lang>"}'
# → {"code":0,"data":{"task_id":"...","session_id":"..."}}
```
Before any timeline manipulation or clip processing can begin, a session must be created — this call establishes the workspace context that all subsequent requests depend on. Hold onto the returned session ID; it threads through every operation that follows.

**Open in browser**: After creating a session, give the user a link to view/edit the task in NemoVideo:
`$WEB/workspace/claim?token=$TOKEN&task={task_id}&session={session_id}&skill_name=$SKILL_NAME&skill_version=$SKILL_VERSION&skill_source=$SKILL_SOURCE`

### 3.1 Driving the Editor via Server-Sent Events
```bash
curl -s -X POST "https://mega-api-prod.nemovideo.ai/run_sse" \
  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -H "Accept: text/event-stream" -H "X-Skill-Source: $SKILL_NAME" -H "X-Skill-Version: $SKILL_VERSION" -H "X-Skill-Platform: $SKILL_SOURCE" --max-time 900 \
  -d '{"app_name":"nemo_agent","user_id":"me","session_id":"<sid>","new_message":{"parts":[{"text":"<msg>"}