Text To Video Long Duration

generate text prompts into long-form videos with this skill. Works with TXT, DOCX, PDF, SRT files up to 50MB. educators, marketers, content creators use it f...

Security Scan

The skill mostly matches a cloud video-generation purpose, but several inconsistencies and a few unclear instructions mean you should review how it obtains tokens, what it reads from disk, and what it will upload before installing.

Purpose & Capability

The skill claims to produce long-form videos and documents a cloud API and upload workflow that match that purpose. However there are mismatches: the registry metadata lists NEMO_TOKEN as a required env var, yet the SKILL.md provides an anonymous-token fallback flow (it will POST to an external endpoint to obtain a token). The description initially states support for TXT/DOCX/PDF/SRT up to 50MB but later the API accepts many media types (mp4, jpg, mp3, etc.) and the documented render time is inconsistent (3–6 minutes vs 30–90 seconds). Also SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while the registry metadata reported no required config paths. These inconsistencies affect trust in what the skill actually requires.

Instruction Scope

Instructions are explicit about calling the mega-api-prod.nemovideo.ai endpoints, uploading user files, controlling sessions, and using SSE. Those actions are coherent for a cloud render service. Points to note: the skill instructs the agent to read the skill's YAML frontmatter at runtime and to attempt to detect install path (~/.clawhub/, ~/.cursor/skills/) which implies filesystem checks beyond pure API calls. It also instructs automatic anonymous token acquisition if NEMO_TOKEN is missing — meaning network calls will be initiated automatically. None of these are clearly malicious, but they expand what the agent will do automatically.

Install Mechanism

Instruction-only skill with no install spec or bundled code — lowest installation risk. No downloads or extracts are requested.

Credentials

The skill declares a single primary credential (NEMO_TOKEN), which is proportionate for a cloud API. However the SKILL.md both treats NEMO_TOKEN as required and also documents an anonymous-token flow that will create/consume a token automatically. The frontmatter also references a config path (~/.config/nemovideo/) not reflected in the registry metadata. This mismatch (declared required env var vs automatic token generation, and the unexpected config path) reduces clarity about what secrets or files the skill legitimately needs.

Persistence & Privilege

always is false and the skill is user-invocable; it does not request persistent/privileged installation or modify other skills. It does expect to maintain a session_id in-memory for the session, which is normal for a remote API client.

What to consider before installing

This skill appears to be a client for a third‑party video rendering service and will upload files and call mega-api-prod.nemovideo.ai. Before installing or invoking: (1) Decide whether you want the agent to auto‑obtain an anonymous token (the skill will call an auth endpoint if NEMO_TOKEN is not present) — if not, provide your NEMO_TOKEN yourself. (2) Confirm you are comfortable uploading the files you will send (scripts, media) to that external domain and review the service’s privacy/terms. (3) Ask the publisher to clarify the inconsistencies (supported file types, expected render time, and whether ~/.config/nemovideo/ will be accessed). (4) If you prefer tighter control, require that the skill not auto-fetch tokens and require explicit user confirmation before any file upload or token exchange.

Getting Started

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

Try saying:

• "generate my text prompts"
• "export 1080p MP4"
• "generate a 3-minute video from this"

Quick Start Setup

This skill connects to a cloud processing backend. On first use, set up the connection automatically and let the user know ("Connecting...").

Token check: Look for NEMO_TOKEN in the environment. If found, skip to session creation. Otherwise:

• Generate a UUID as client identifier
• POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with X-Client-Id header
• Extract data.token from the response — this is your NEMO_TOKEN (100 free credits, 7-day expiry)

Session: POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Keep the returned session_id for all operations.

Let the user know with a brief "Ready!" when setup is complete. Don't expose tokens or raw API output.

Text to Video Long Duration — Generate Long Videos from Text

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

A quick example: upload a 300-word script about ocean conservation, type "generate a 3-minute video from this script with matching visuals and narration", and you'll get a 1080p MP4 back in roughly 3-6 minutes. All rendering happens server-side.

Worth noting: breaking your script into clearly labeled sections helps the AI match visuals more accurately per segment.

Matching Input to Actions

User prompts referencing text to video long duration, 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.

Skill attribution — read from this file's YAML frontmatter at runtime:

• X-Skill-Source: text-to-video-long-duration
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

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

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

SSE Event Handling

Event	Action
Text response	Apply GUI translation (§4), present to user
Tool call/result	Process internally, don't forward
heartbeat / empty data:	Keep waiting. Every 2 min: "⏳ Still working..."
Stream closes	Process final response

~30% of editing operations return no text in the SSE stream. When this happens: poll session state to verify the edit was applied, then summarize changes to the user.

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 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)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "generate a 3-minute video from this script with matching visuals and narration" — concrete instructions get better results.

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

Export as MP4 with H.264 codec for the best balance of file size and playback compatibility.

Common Workflows

Quick edit: Upload → "generate a 3-minute video from this script with matching visuals and narration" → Download MP4. Takes 3-6 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.