Qwen Video Generation

generate text prompts into AI generated videos with this skill. Works with MP4, MOV, GIF, WebM files up to 500MB. content creators use it for generating shor...

Security Scan

The skill's requirements and runtime instructions are mostly consistent with a cloud-based video-generation integration, but there are a few small metadata/instruction mismatches and an unknown remote service to trust.

Purpose & Capability

The skill claims to call a cloud video rendering backend and only requests a single service token (NEMO_TOKEN), which is proportionate for an API-based video-generation service.

Instruction Scope

Runtime instructions describe API calls, uploads, SSE streaming, session handling, and anonymous-token acquisition — all expected for this service. Two things to note: (1) the SKILL.md tells the agent to auto-request an anonymous token if NEMO_TOKEN is not present (contradicting the registry's 'required env var' claim that NEMO_TOKEN must be provided), and (2) it instructs the agent to read the skill's YAML frontmatter and detect install paths to set X-Skill-Platform, which requires reading files/paths beyond pure API use. Neither is obviously malicious but they are scope-expanding behaviors the user should be aware of.

Install Mechanism

No install spec and no code files (instruction-only). That minimizes on-disk code installation risk.

Credentials

Requesting NEMO_TOKEN as the primary credential is appropriate for a cloud API. However, SKILL.md frontmatter also lists a config path (~/.config/nemovideo/) which the registry metadata did not; this mismatch could indicate the skill expects to access local config files (privacy/credential exposure risk) even though the registry reports none.

Persistence & Privilege

always is false, no install or persistent background presence is requested, and the skill does not instruct modifying other skills or system-wide settings.

Assessment

This skill appears to do what it says: talk to a Nemovideo cloud API to create videos. Before installing: (1) verify you trust the domain (mega-api-prod.nemovideo.ai) because the skill will POST media and may create anonymous tokens that grant API access; (2) decide whether you want to provide a permanent NEMO_TOKEN or allow the skill to create anonymous tokens (they expire in 7 days and are rate-limited); (3) be aware the skill may read its own SKILL.md frontmatter and check install paths (~/.clawhub, ~/.cursor) which could reveal where it is installed; and (4) confirm whether the skill needs access to ~/.config/nemovideo/ (the frontmatter lists it, but the registry metadata does not). If you have sensitive media or credentials on your system, avoid giving broad access or test in a sandbox first.

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"
• "generate a 10-second video of a"

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.

Qwen Video Generation — Generate Videos from Text Prompts

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

Say you have a short text description of a sunset over the ocean and want to generate a 10-second video of a futuristic city at night with cinematic lighting — the backend processes it in about 1-3 minutes and hands you a 1080p MP4.

Tip: shorter, more specific prompts tend to produce more accurate and consistent results.

Matching Input to Actions

User prompts referencing qwen video 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.

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: qwen-video-generation
• 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.

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 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)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "generate a 10-second video of a futuristic city at night with cinematic lighting" — concrete instructions get better results.

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

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

Common Workflows

Quick edit: Upload → "generate a 10-second video of a futuristic city at night with cinematic lighting" → 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.