Ai Video Marketing Company

Turn a 2-minute product demo recording into 1080p polished marketing videos just by typing what you need. Whether it's creating branded marketing videos from...

Security Scan

The skill's runtime instructions generally match a cloud video-rendering service, but there are small inconsistencies in its declared requirements (config path vs registry metadata) and a few scope details (detecting install path) that merit caution before installation.

Purpose & Capability

The skill claims to convert raw footage into marketing videos and all network calls, upload, SSE and export workflows described map to that purpose. However the SKILL.md frontmatter lists a required config path (~/.config/nemovideo/) while the registry metadata provided earlier reported no required config paths — this mismatch is an incoherence that should be clarified. Needing an API token (NEMO_TOKEN) is appropriate for a cloud render service.

Instruction Scope

The SKILL.md instructs only interaction with the remote nemovideo API (session creation, uploads, SSE, polling export status) and handling user-provided footage. It does not instruct reading arbitrary user files or secrets beyond the token and an optional config path. It does instruct the agent to detect install path to set an attribution header, which expands scope slightly (see environment_proportionality).

Install Mechanism

There is no install spec and no code files — instruction-only skill — so nothing will be downloaded or written to disk by an installer. This is the lowest-risk install mechanism.

Credentials

The declared primary credential is NEMO_TOKEN, which is reasonable for authorizing render jobs. The SKILL.md also provides a fallback anonymous-token flow if NEMO_TOKEN is absent (so the token requirement is effectively optional), which conflicts with the declared 'required env var' assertion. The frontmatter also lists a config path (~/.config/nemovideo/) suggesting the skill might read or write that directory; this was not reflected in the registry summary and should be clarified. The skill will include an Authorization bearer token in API calls — that token grants access to account credits and job history, so users should only supply tokens they consent to share.

Persistence & Privilege

always:false (not force-included) and normal autonomous invocation are set. The skill does not request persistent system-wide privileges or to modify other skills. The only minor privilege is the implied ability to read an install path or the listed config path if implemented.

Scan Findings in Context

[no_findings] expected: Scanner found no regex matches; this is expected for an instruction-only skill with no code files. Absence of findings is not evidence of safety — review SKILL.md carefully (done above).

What to consider before installing

This skill appears to be a straightforward cloud video-rendering integration and needs an API token (NEMO_TOKEN) to operate. Before installing: (1) confirm the domain (mega-api-prod.nemovideo.ai) and vendor are trustworthy and that you accept uploading footage there (uploaded videos are sent to that backend); (2) understand that any NEMO_TOKEN you provide gives the skill access to your account/credits and job history — only provide a token you control and are willing to share; (3) ask the author to clarify the apparent metadata mismatch: SKILL.md mentions a config path (~/.config/nemovideo/) but the registry listing did not — confirm whether the skill will read or write that directory and why; (4) note the skill may derive an X-Skill-Platform header by inspecting local install paths — if you are uncomfortable with any filesystem probing, ask for that behavior to be removed or explained. If you need strong privacy guarantees for video content, do not install until the vendor's privacy/retention policy is verified.

Getting Started

Got raw video footage to work with? Send it over and tell me what you need — I'll take care of the AI marketing video creation.

Try saying:

• "create a 2-minute product demo recording into a 1080p MP4"
• "turn this product footage into a 60-second marketing video with branded text overlays and a call to action"
• "creating branded marketing videos from raw product or service footage for 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.

AI Video Marketing Company — Create and Export Marketing Videos

Send me your raw video footage and describe the result you want. The AI marketing video creation runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 2-minute product demo recording, type "turn this product footage into a 60-second marketing video with branded text overlays and a call to action", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: keep source clips under 3 minutes for faster AI processing and tighter output.

Matching Input to Actions

User prompts referencing ai video marketing company, 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is ai-video-marketing-company, X-Skill-Version comes from the version field, and X-Skill-Platform is detected from the install path (~/.clawhub/ = clawhub, ~/.cursor/skills/ = cursor, otherwise unknown).

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

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 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

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "turn this product footage into a 60-second marketing video with branded text overlays and a call to action" — 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 ad platforms like Meta and Google.

Common Workflows

Quick edit: Upload → "turn this product footage into a 60-second marketing video with branded text overlays and a call to action" → Download MP4. Takes 1-2 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.