Text To Video Gen

Skip the learning curve of professional editing software. Describe what you want — create a 30-second video from this product description: 'Wireless earbuds...

Security Scan

The skill's behavior (sending uploads and requests to mega-api-prod.nemovideo.ai and requiring a NEMO_TOKEN) is consistent with a text-to-video service, but registry metadata (no homepage/source) and an unexplained configPaths entry create unexplained mismatches you should verify before trusting credentials or uploading sensitive files.

Purpose & Capability

The skill name/description match the runtime instructions: it talks to an external Nemo video API and requires a NEMO_TOKEN, which is proportional for a cloud video generator. However the frontmatter metadata also lists a config path (~/.config/nemovideo/) that the SKILL.md never actually explains reading; the registry also shows the skill Source is unknown and there is no homepage to validate the provider. Those metadata inconsistencies reduce confidence.

Instruction Scope

SKILL.md gives explicit, bounded API calls (session creation, SSE message posting, upload endpoints, render polling). It instructs uploading user files to the remote API and using the NEMO_TOKEN or acquiring a short-lived anonymous token — both expected for this service. Two points to watch: (1) the text asks to auto-detect X-Skill-Platform from an install path (implies reading agent/install path), and (2) frontmatter mentions a config path even though the runtime steps don't describe reading it. Those are scope mismatches to clarify.

Install Mechanism

No install spec and no code files — instruction-only skill. This is the lowest install risk (nothing will be written to disk by the skill itself).

Credentials

The only declared credential is NEMO_TOKEN (primaryEnv), which aligns with calling the nemo API. The SKILL.md also supports obtaining an anonymous ephemeral token if no NEMO_TOKEN is present, which is a reasonable fallback. The oddity: frontmatter lists a required configPaths entry (~/.config/nemovideo/), but the instructions never justify reading local config files; clarify whether the skill will access local config or only environment variables.

Persistence & Privilege

The skill does not request always:true and does not declare any persistent installs or system modifications. Autonomous invocation is enabled (default) but not combined with other high privileges in this package.

What to consider before installing

This skill behaves like a normal cloud text→video integration, but there are a few things to check before installing or providing credentials: - Verify the service: the registry lists no homepage or source; confirm that mega-api-prod.nemovideo.ai is a legitimate provider and that you trust it. Without a homepage you cannot easily confirm the vendor or privacy practices. - Prefer ephemeral tokens: if you don't fully trust the skill, don't supply a long-lived NEMO_TOKEN. Let the skill use the anonymous-token flow (the skill documents a short-lived token you can use) or create a token with minimal scope and the ability to revoke it. - Avoid uploading sensitive data: the skill will upload user files to an external API — do not send PII, secrets, or proprietary assets unless you're sure of retention and privacy policies. - Ask the author to clarify metadata mismatches: specifically why frontmatter claims a config path (~/.config/nemovideo/) and why the skill would need to auto-detect an install path for X-Skill-Platform. Those could be benign (leftover metadata) or indicate the skill expects to read local paths. - If you decide to proceed, monitor network requests and revoke any token you provided if you see unexpected behavior. If the publisher provides no verifiable contact or homepage, consider the risk of sharing credentials or private files as higher than usual.

Getting Started

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

Try saying:

• "generate my text prompts"
• "export 1080p MP4"
• "create a 30-second video from this"

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.

Text to Video Generator — Turn Text Into Video Clips

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

Here's a typical use: you send a a two-sentence product description, ask for create a 30-second video from this product description: 'Wireless earbuds with 24-hour battery life. Perfect for commuters and gym-goers.', and about 1-3 minutes later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter and more specific prompts produce more accurate and consistent video output.

Matching Input to Actions

User prompts referencing text to video gen, 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	text-to-video-gen
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

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

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.

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

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

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "create a 30-second video from this product description: 'Wireless earbuds with 24-hour battery life. Perfect for commuters and gym-goers.'" — concrete instructions get better results.

Max file size is 50MB. Stick to TXT, DOCX, PDF, plain text for the smoothest experience.

Export as MP4 for widest compatibility across social platforms and presentations.

Common Workflows

Quick edit: Upload → "create a 30-second video from this product description: 'Wireless earbuds with 24-hour battery life. Perfect for commuters and gym-goers.'" → 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.