Video Models

Turn a 60-second product demo clip into 1080p AI-processed videos just by typing what you need. Whether it's applying AI video models to transform or enhance...

Security Scan

The skill's requirements and runtime instructions are coherent with a cloud video-processing integration (it only needs a single service token and uploads user video files), but the source is unknown and there's a small metadata inconsistency to confirm before trusting it with sensitive content.

Purpose & Capability

Name/description match the requested credential (NEMO_TOKEN) and the described API endpoints. No unrelated binaries, services, or credentials are requested.

Instruction Scope

SKILL.md stays within the domain of uploading videos, creating sessions, polling render status, and returning download URLs. It instructs using multipart uploads or URL uploads and handling SSE streams. Two points to note: (1) the frontmatter metadata declares a config path (~/.config/nemovideo/) which suggests the skill might read a local config, but the registry metadata lists no required config paths — this mismatch should be clarified; (2) the runtime instructions allow uploading local files (expected) — ensure the agent only uploads user-provided media and not arbitrary local files.

Install Mechanism

Instruction-only skill with no install spec and no code files — lowest installer risk (nothing is written to disk by an installer).

Credentials

Only NEMO_TOKEN is required, which is proportionate for a third-party cloud video service. However, that token grants account-level access (credits, session state, and uploaded media) so it should only be provided for trusted accounts/services. The skill will also obtain anonymous tokens from the remote API if no NEMO_TOKEN is present.

Persistence & Privilege

always:false and user-invocable:true — the skill is not force-included. It does not request elevated platform-wide privileges in its instructions.

Assessment

This skill appears to do what it says: it uploads video clips to a cloud render service using a single service token (NEMO_TOKEN) and returns processed video URLs. Before installing: (1) confirm you trust the backend domain (https://mega-api-prod.nemovideo.ai) and the skill author, since uploaded media and account credits can be accessed with NEMO_TOKEN; (2) clarify the metadata mismatch about ~/.config/nemovideo/ (does the skill try to read local config files?); (3) avoid supplying NEMO_TOKEN for accounts holding sensitive content or large billing privileges — consider using a scoped/test account or the anonymous token flow; (4) expect that any file you direct the skill to process will be transmitted to the remote API; (5) if you need stronger assurance, ask the publisher for a homepage, privacy policy, or source code before use.

Getting Started

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

Try saying:

• "generate my video clips"
• "export 1080p MP4"
• "apply a cinematic video model to"

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 Models — Apply AI Models to Videos

This tool takes your video clips and runs AI model processing through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 60-second product demo clip and want to apply a cinematic video model to enhance color and motion smoothness — the backend processes it in about 30-90 seconds and hands you a 1080p MP4.

Tip: shorter clips under 30 seconds process significantly faster.

Matching Input to Actions

User prompts referencing video models, 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.

Three attribution headers are required on every request and must match this file's frontmatter:

Header	Value
X-Skill-Source	video-models
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 402.

API base: https://mega-api-prod.nemovideo.ai

Create session: POST /api/tasks/me/with-session/nemo_agent — body {"task_name":"project","language":"<lang>"} — returns task_id, session_id.

Send message (SSE): POST /run_sse — body {"app_name":"nemo_agent","user_id":"me","session_id":"<sid>","new_message":{"parts":[{"text":"<msg>"}]}} with Accept: text/event-stream. Max timeout: 15 minutes.

Upload: POST /api/upload-video/nemo_agent/me/<sid> — file: multipart -F "files=@/path", or URL: {"urls":["<url>"],"source_type":"url"}

Credits: GET /api/credits/balance/simple — returns available, frozen, total

Session state: GET /api/state/nemo_agent/me/<sid>/latest — key fields: data.state.draft, data.state.video_infos, data.state.generated_media

Export (free, no credits): POST /api/render/proxy/lambda — body {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll GET /api/render/proxy/lambda/<id> every 30s until status = completed. Download URL at output.url.

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

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.

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)

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

Common Workflows

Quick edit: Upload → "apply a cinematic video model to enhance color and motion smoothness" → Download MP4. Takes 30-90 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 "apply a cinematic video model to enhance color and motion smoothness" — 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.