Video Cutter Online

trim video clips into trimmed video clips with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. content creators use it for cutting unwanted sec...

Security Scan

The skill's requirements and runtime instructions are generally consistent with an online video-trimming service, but there are small metadata/instruction mismatches and you should be aware it will upload your video files to an external API endpoint.

Purpose & Capability

The skill claims to trim videos using a cloud backend and only requests a single service token (NEMO_TOKEN) which is coherent for a hosted video-processing API. Minor inconsistency: the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while the registry metadata earlier reported no required config paths.

Instruction Scope

The instructions describe creating or using a NEMO_TOKEN, uploading video files, opening SSE streams, polling render status, and mapping GUI actions to API calls — all expected for this use case. They also instruct the agent to read the skill file's YAML frontmatter for attribution and to detect install paths (e.g., ~/.clawhub/, ~/.cursor/skills/) which requires reading some local paths; this is plausible but broader filesystem probing than strictly necessary for processing uploads.

Install Mechanism

No install spec or bundled code is present (instruction-only skill), so nothing is written to disk by an installer. This is the lowest install risk.

Credentials

Only NEMO_TOKEN is declared as the primary credential, which is proportional for a cloud video service. One mismatch: the registry lists NEMO_TOKEN as required, but the runtime instructions provide a clear anonymous-token fallback when NEMO_TOKEN is absent (so the token is not strictly required). No unrelated credentials are requested.

Persistence & Privilege

always:false and no install hooks are present. The skill does not request persistent system privileges or to modify other skills. It will, however, initiate remote jobs that may continue on the service if you close the client (server-side orphaning), which is normal for remote render services.

Assessment

This skill appears to do what it says: upload your videos to a cloud service and return trimmed exports. Before installing or using it, consider: (1) it will send your video files to https://mega-api-prod.nemovideo.ai for processing — verify you trust that domain/owner and do not upload sensitive content you would not want transmitted off your machine; (2) the registry metadata and SKILL.md disagree slightly (config path listed in the skill but not the registry; NEMO_TOKEN is marked required yet the skill can obtain an anonymous token), which suggests the publisher may have edited the skill text without updating registry fields — not necessarily malicious but worth noting; (3) there is no homepage or known source/owner reputation — prefer services with documented privacy and ownership if you process private or commercial footage; (4) because it is instruction-only and requires no local install, local risk is low, but the main risk is data exposure to the remote API. If you proceed, test with non-sensitive sample videos first and confirm how long uploaded files and render outputs are retained by the service.

Getting Started

Share your video clips and I'll get started on AI video trimming. Or just tell me what you're thinking.

Try saying:

• "trim my video clips"
• "export 1080p MP4"
• "cut out the first 2 minutes"

Getting Connected

Before handling any user request, establish a connection to the backend API. Show a brief status like "Connecting...".

If NEMO_TOKEN is in the environment, use it directly and create a session. Otherwise, acquire a free starter token:

• Generate a UUID as client identifier
• POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with the X-Client-Id header
• The response includes a token with 100 free credits valid for 7 days — use it as NEMO_TOKEN

Then create a session by POSTing to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer authorization and body {"task_name":"project","language":"en"}. The session_id in the response is needed for all following requests.

Tell the user you're ready. Keep the technical details out of the chat.

Video Cutter Online — Cut and Export Trimmed Videos

Drop your video clips in the chat and tell me what you need. I'll handle the AI video trimming on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a 10-minute interview recording, ask for cut out the first 2 minutes and trim the end after the sign-off, and about 20-40 seconds later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter source clips process faster — split a long file before uploading if possible.

Matching Input to Actions

User prompts referencing video cutter online, aspect ratio, text overlays, or audio tracks get routed to the corresponding action via keyword and intent classification.

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	❌

Cloud Render Pipeline Details

Each export job queues on a cloud GPU node that composites video layers, applies platform-spec compression (H.264, up to 1080x1920), and returns a download URL within 30-90 seconds. The session token carries render job IDs, so closing the tab before completion orphans the job.

All calls go to https://mega-api-prod.nemovideo.ai. The main endpoints:

1. Session — POST /api/tasks/me/with-session/nemo_agent with {"task_name":"project","language":"<lang>"}. Gives you a session_id.
2. Chat (SSE) — POST /run_sse with session_id and your message in new_message.parts[0].text. Set Accept: text/event-stream. Up to 15 min.
3. Upload — POST /api/upload-video/nemo_agent/me/<sid> — multipart file or JSON with URLs.
4. Credits — GET /api/credits/balance/simple — returns available, frozen, total.
5. State — GET /api/state/nemo_agent/me/<sid>/latest — current draft and media info.
6. Export — POST /api/render/proxy/lambda with render ID and draft JSON. Poll GET /api/render/proxy/lambda/<id> every 30s for completed status and download URL.

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

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

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

Include Authorization: Bearer <NEMO_TOKEN> and all attribution headers on every request — omitting them triggers a 402 on export.

Draft JSON uses short keys: t for tracks, tt for track type (0=video, 1=audio, 7=text), sg for segments, d for duration in ms, m for metadata.

Example timeline summary:

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

Translating GUI Instructions

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

• "click" or "点击" → execute the action via the relevant endpoint
• "open" or "打开" → query session state to get the data
• "drag/drop" or "拖拽" → send the edit command through SSE
• "preview in timeline" → show a text summary of current tracks
• "Export" or "导出" → run the export workflow

Reading the SSE Stream

Text events go straight to the user (after GUI translation). Tool calls stay internal. Heartbeats and empty data: lines mean the backend is still working — show "⏳ Still working..." every 2 minutes.

About 30% of edit operations close the stream without any text. When that happens, poll /api/state to confirm the timeline changed, then tell the user what was updated.

Error Codes

• 0 — success, continue normally
• 1001 — token expired or invalid; re-acquire via /api/auth/anonymous-token
• 1002 — session not found; create a new one
• 2001 — out of credits; anonymous users get a registration link with ?bind=<id>, registered users top up
• 4001 — unsupported file type; show accepted formats
• 4002 — file too large; suggest compressing or trimming
• 400 — missing X-Client-Id; generate one and retry
• 402 — free plan export blocked; not a credit issue, subscription tier
• 429 — rate limited; wait 30s and retry once

Common Workflows

Quick edit: Upload → "cut out the first 2 minutes and trim the end after the sign-off" → Download MP4. Takes 20-40 seconds for a 30-second clip.

Batch style: Upload multiple files in one session. Process them one by one with different instructions. Each gets its own render.

Iterative: Start with a rough cut, preview the result, then refine. The session keeps your timeline state so you can keep tweaking.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "cut out the first 2 minutes and trim the end after the sign-off" — concrete instructions get better results.

Max file size is 500MB. Stick to MP4, MOV, AVI, WebM for the smoothest experience.

Export as MP4 for widest compatibility across platforms and devices.