Video Generation 4k

Get 4K AI videos ready to post, without touching a single slider. Upload your text prompts (MP4, MOV, WebM, AVI, up to 500MB), say something like "generate a...

Security Scan

The skill's declared need for a single NEMO_TOKEN and cloud endpoints is plausible for a video-generation tool, but there are internal inconsistencies (config path metadata vs registry report) and a few instructions that may require reading or persisting local state beyond what's declared—worth clarifying before installation.

Purpose & Capability

The skill's name, description, and API endpoints all align with a cloud video-rendering service and legitimately require a service token (NEMO_TOKEN) and upload capability. However, the SKILL.md frontmatter metadata lists a config path (~/.config/nemovideo/) even though the registry summary said 'Required config paths: none' — this mismatch is unexplained and could indicate the skill expects to read/write a local config directory.

Instruction Scope

Instructions explicitly direct the agent to call external APIs, upload user files (up to 500MB), create anonymous tokens, start sessions, stream SSE responses, and 'save session_id' from responses. Uploading user files to the third-party endpoint is expected for a renderer, but 'save session_id' and the requirement to auto-detect an install path for X-Skill-Platform implies reading/writing local state or filesystem paths not fully declared. The SKILL.md also requires specific attribution headers and instructs the agent to re-acquire tokens automatically — these are fine functionally but expand the agent's runtime actions beyond simple one-off calls.

Install Mechanism

This is an instruction-only skill with no install script or third-party package downloads. That minimizes installation risk — nothing is written to disk by an installer step. The runtime instructions themselves, however, may cause network I/O and optional local state changes.

Credentials

Only NEMO_TOKEN is declared as required, which is proportionate for a cloud video API. The SKILL.md provides a flow to generate an anonymous token if NEMO_TOKEN isn't set, which is reasonable. The concern is the apparent implicit use of a config path (~/.config/nemovideo/) in frontmatter and the instruction to 'save session_id' — these suggest additional local credential or session persistence that wasn't listed in the registry's required config paths, and should be clarified.

Persistence & Privilege

The skill is not forced-always and does not request elevated platform privileges. But the frontmatter's config path plus instructions that imply saving session state mean the skill may write/read from ~/.config/nemovideo/ or other local storage. Because the registry summary omitted this, it's a potential persistence concern (where tokens/sessions may be stored) and should be confirmed.

What to consider before installing

This skill appears to call a third-party video-rendering API and needs a NEMO_TOKEN (or it will request an anonymous token). Before installing or enabling it: 1) Confirm the mismatch about config paths — ask the developer whether ~/.config/nemovideo/ will be read or written and what is stored there (tokens, session IDs). 2) Understand privacy implications: any file you upload (video, images, audio) will be sent to mega-api-prod.nemovideo.ai — avoid uploading sensitive footage until you verify retention and access policies. 3) Ask where session_id and tokens are stored (in-memory only vs saved to disk) and whether they persist beyond the agent process. 4) Verify the service domain (HTTPS/TLS) and that the token scope/expiry is limited; prefer using anonymous token flow with test content first. 5) If you need stronger guarantees, request the developer remove or justify the configPath requirement, document exactly what local IO the skill performs, and provide a privacy/retention statement for uploaded media.

Getting Started

Got text prompts to work with? Send it over and tell me what you need — I'll take care of the AI 4K video generation.

Try saying:

• "generate a short text description of a mountain sunset scene into a 4K MP4"
• "generate a 10-second 4K video of a futuristic city at night with neon lights"
• "generating high-resolution 4K video clips from text prompts for content creators, marketers, filmmakers"

Automatic Setup

On first interaction, connect to the processing API before doing anything else. Show a brief status like "Setting things up...".

Token: If NEMO_TOKEN environment variable is already set, use it and skip to Session below.

Free token: Generate a UUID as client identifier, then POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id: <uuid>. The response field data.token becomes your NEMO_TOKEN (100 credits, 7-day expiry).

Session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Save session_id from the response.

Confirm to the user you're connected and ready. Don't print tokens or raw JSON.

Video Generation 4K — Generate 4K Videos from Text

This tool takes your text prompts and runs AI 4K video generation through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a short text description of a mountain sunset scene and want to generate a 10-second 4K video of a futuristic city at night with neon lights — the backend processes it in about 2-4 minutes and hands you a 4K MP4.

Tip: shorter prompts with clear scene descriptions produce more consistent 4K results.

Matching Input to Actions

User prompts referencing video generation 4k, 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.

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

Header	Value
X-Skill-Source	video-generation-4k
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

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 Codes

• 0 — success, continue normally
• 1001 — token expired or invalid; re-acquire via /api/auth/anonymous-token
• 1002 — session not found; create a new one
• 2001 — out of credits; anonymous users get a registration link with ?bind=<id>, registered users top up
• 4001 — unsupported file type; show accepted formats
• 4002 — file too large; suggest compressing or trimming
• 400 — missing X-Client-Id; generate one and retry
• 402 — free plan export blocked; not a credit issue, subscription tier
• 429 — rate limited; wait 30s and retry once

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 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)

Common Workflows

Quick edit: Upload → "generate a 10-second 4K video of a futuristic city at night with neon lights" → Download MP4. Takes 2-4 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 "generate a 10-second 4K video of a futuristic city at night with neon lights" — concrete instructions get better results.

Max file size is 500MB. Stick to MP4, MOV, WebM, AVI for the smoothest experience.

Export as MP4 with H.264 codec for the best balance of 4K quality and file size.