Opus Clip

Get short viral clips ready to post, without touching a single slider. Upload your long-form video (MP4, MOV, AVI, WebM, up to 500MB), say something like "cl...

Security Scan

The skill's requirements and runtime instructions are consistent with a cloud video-clipping service: it asks for a single service token and makes API calls only to nemovideo.ai endpoints, with no installer or unrelated credentials — but there are a few small inconsistencies and privacy-relevant behaviors to be aware of.

Purpose & Capability

Name/description (cloud video clipper) matches the declared primary credential (NEMO_TOKEN) and the SKILL.md instructs only calls to nemovideo.ai endpoints for uploads, SSE, rendering and exports. Nothing else (no AWS keys, no unrelated service tokens) is requested. Note: the SKILL.md frontmatter lists a configPaths entry (~/.config/nemovideo/) even though the registry summary above reported no required config paths — a discrepancy in metadata but not itself a functional mismatch.

Instruction Scope

The instructions keep scope focused on uploading videos, starting sessions, streaming SSE, polling render status, and exporting results from mega-api-prod.nemovideo.ai. They instruct the agent to use NEMO_TOKEN (or obtain a short-lived anonymous token via the anonymous-token endpoint) and to include attribution headers. One privacy-relevant instruction: detect the agent's install path to set X-Skill-Platform (e.g., check for ~/.clawhub/ or ~/.cursor/skills/), which implies filesystem inspection to derive a header value. Otherwise the runtime steps do not ask for unrelated files or other environment variables.

Install Mechanism

Instruction-only skill with no install spec and no code files; nothing is downloaded or written to disk by an installer. This is low risk from an installation perspective.

Credentials

Only one credential is required (NEMO_TOKEN), which is appropriate for calling the vendor API. The skill also describes a local config path in its frontmatter (~/.config/nemovideo/), but the registry's requirement list did not include config paths — this mismatch is a metadata inconsistency. The SKILL.md will attempt to mint an anonymous token if NEMO_TOKEN is absent, which is expected behavior but means the agent will perform a network POST to obtain a token.

Persistence & Privilege

The skill does not request always: true or other elevated platform privileges and does not instruct modifying other skills or system-wide settings. It uses session tokens for transient jobs; no persistent system presence is requested.

Assessment

This skill appears to be what it says: a cloud-based video clipper that requires a single service token. Before installing or using it, consider: (1) The service host (mega-api-prod.nemovideo.ai) will receive any uploaded video — do not upload sensitive content unless you trust the service and reviewed its privacy policy/retention rules. (2) If NEMO_TOKEN is not provided, the skill will POST to an anonymous-token endpoint to obtain a short-lived token automatically (this is normal but is a network call you should expect). (3) The SKILL.md asks the agent to detect its install path to set an X-Skill-Platform header — that can reveal which client/runtime path is in use; if you prefer not to expose that, provide a token and/or review how the agent builds headers. (4) There is a small metadata inconsistency (frontmatter mentions a config path while the registry metadata did not); not necessarily malicious but worth verifying. Lastly, the skill source/homepage is unknown — if you need stronger assurance, ask the publisher for a homepage or privacy/security documentation before uploading production or sensitive videos.

Getting Started

Ready when you are. Drop your long-form video here or describe what you want to make.

Try saying:

• "convert a 60-minute podcast recording or webinar into a 1080p MP4"
• "clip the best 60-second moments and add captions for TikTok"
• "generating short shareable clips from long videos for content creators and marketers"

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.

Opus Clip — Turn Long Videos Into Short Clips

This tool takes your long-form video and runs AI clip generation through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 60-minute podcast recording or webinar and want to clip the best 60-second moments and add captions for TikTok — the backend processes it in about 1-3 minutes and hands you a 1080p MP4.

Tip: videos under 30 minutes process significantly faster and yield more focused clips.

Matching Input to Actions

User prompts referencing opus clip, 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.

Base URL: https://mega-api-prod.nemovideo.ai

Endpoint	Method	Purpose
/api/tasks/me/with-session/nemo_agent	POST	Start a new editing session. Body: {"task_name":"project","language":"<lang>"}. Returns session_id.
/run_sse	POST	Send a user message. Body includes app_name, session_id, new_message. Stream response with Accept: text/event-stream. Timeout: 15 min.
/api/upload-video/nemo_agent/me/<sid>	POST	Upload a file (multipart) or URL.
/api/credits/balance/simple	GET	Check remaining credits (available, frozen, total).
/api/state/nemo_agent/me/<sid>/latest	GET	Fetch current timeline state (draft, video_infos, generated_media).
/api/render/proxy/lambda	POST	Start export. Body: {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll status every 30s.

Accepted file types: 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: opus-clip
• 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.

Error Handling

Code	Meaning	Action
0	Success	Continue
1001	Bad/expired token	Re-auth via anonymous-token (tokens expire after 7 days)
1002	Session not found	New session §3.0
2001	No credits	Anonymous: show registration URL with ?bind=<id> (get <id> from create-session or state response when needed). Registered: "Top up credits in your account"
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 or upgrade your plan to unlock export."
429	Rate limit (1 token/client/7 days)	Retry in 30s once

SSE Event Handling

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

Common Workflows

Quick edit: Upload → "clip the best 60-second moments and add captions for TikTok" → Download MP4. Takes 1-3 minutes 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 "clip the best 60-second moments and add captions for TikTok" — 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 TikTok, Reels, and YouTube Shorts.