Video Prompt Generation

Skip the learning curve of professional editing software. Describe what you want — generate a detailed video prompt for a 30-second product showcase with cin...

Security Scan

The skill mostly matches its stated purpose (remote video prompt/rendering) but has a few inconsistencies and minor surprises — notably a config-path requirement present in the skill frontmatter but not in registry metadata, and it instructs the agent to call an external API and mint anonymous tokens — so review before installing or granting credentials.

Purpose & Capability

The name/description (generate video prompts, server-side rendering, uploads) aligns with the API endpoints and workflows described. However the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) as required while the registry-level 'Requirements' listed earlier said no config paths — this mismatch is unexplained and worth confirming. Otherwise the required NEMO_TOKEN credential is proportional to a remote-video service.

Instruction Scope

Runtime instructions are explicit about creating sessions, SSE chat, uploads, polling exports, and returning download URLs — all consistent with a remote render/prompt service. The skill also instructs how to obtain an anonymous token by POSTing to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token (generating a UUID for X-Client-Id). It requires adding attribution headers and detecting install path to set X-Skill-Platform, which implies the agent may read its own install path; this is reasonable but expands file-system access beyond purely network calls and should be acknowledged.

Install Mechanism

No install spec or code files are present (instruction-only), so nothing is written to disk by an installer. This is the lower-risk model for skills.

Credentials

The skill declares a single primary credential (NEMO_TOKEN) which is appropriate for the API it talks to. It also documents a fallback flow to mint an anonymous token if NEMO_TOKEN is absent — that requires contacting the external API and then using that token. The unexplained frontmatter configPaths entry (~/.config/nemovideo/) could grant broader local access if the agent actually reads it; confirm whether the skill/agent will read files there and why.

Persistence & Privilege

always:false and normal autonomous invocation are set (no forced always-on behavior). The skill does not request system-wide changes or permission to alter other skills; no elevated persistence is requested.

What to consider before installing

What to check before installing: - Confirm trust in the external domain (mega-api-prod.nemovideo.ai) and its privacy policy before uploading video or audio files. - The skill expects a NEMO_TOKEN; if you don't provide one it will obtain an anonymous token by calling the provider — that's allowed but means network calls and issuance of a short-lived token. If you're cautious, try the anonymous flow first rather than giving a permanent credential. - There's a mismatch: the SKILL.md frontmatter lists ~/.config/nemovideo/ as a required config path but the registry metadata showed none. Ask the author whether the skill will read files in that directory and why. If it will, avoid installing if those files contain sensitive data. - Attribution headers (X-Skill-Source, X-Skill-Version, X-Skill-Platform) are required on each API call; the agent determines platform from install path which requires reading its own filesystem path — make sure you are comfortable with that behavior. - Only upload non-sensitive media while you evaluate the service. If you must use real content, prefer the anonymous token flow and monitor what gets uploaded and stored on the provider. If the author can clarify the config-path requirement and confirm the exact data the backend stores/retains, the assessment could move toward 'benign'.

Getting Started

Share your text descriptions and I'll get started on AI prompt generation. Or just tell me what you're thinking.

Try saying:

• "generate my text descriptions"
• "export 1080p MP4"
• "generate a detailed video prompt for"

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 Prompt Generation — Generate Video Prompts from Text

Send me your text descriptions and describe the result you want. The AI prompt generation runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a brief scene idea or topic description, type "generate a detailed video prompt for a 30-second product showcase with cinematic lighting", and you'll get a 1080p MP4 back in roughly 10-20 seconds. All rendering happens server-side.

Worth noting: more specific your input description, the more precise and usable the generated prompt will be.

Matching Input to Actions

User prompts referencing video prompt generation, 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-prompt-generation
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

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

Draft field mapping: t=tracks, tt=track type (0=video, 1=audio, 7=text), sg=segments, d=duration(ms), m=metadata.

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 "generate a detailed video prompt for a 30-second product showcase with cinematic lighting" — 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.

Common Workflows

Quick edit: Upload → "generate a detailed video prompt for a 30-second product showcase with cinematic lighting" → Download MP4. Takes 10-20 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.