Text To Video Creation

Skip the learning curve of professional editing software. Describe what you want — turn this blog intro into a 30-second video with visuals and background mu...

Security Scan

The skill mostly matches a text->video service but has small, unexplained requests (a local config path and instructions to probe install paths/frontmatter) that don't clearly match its stated purpose and raise privacy/footprint questions.

Purpose & Capability

Name/description, API endpoints, and required NEMO_TOKEN align with a cloud text-to-video service. However, the registry metadata declares a required config path (~/.config/nemovideo/) which is not justified by the SKILL.md instructions; that suggests the skill expects to read local configuration files without explanation and is disproportionate to the stated purpose.

Instruction Scope

Runtime instructions are detailed and stay within the expected domain (auth, session creation, SSE, upload, render). They do instruct the agent to read the skill's YAML frontmatter and detect install path to populate X-Skill-Platform, which implies filesystem probing. The SKILL.md also tells the agent to hide technical details from the chat. Reading frontmatter / detecting install path is outside the core text->video task and could access local state the user did not expect.

Install Mechanism

No install spec and no code files — instruction-only skill — so there is no download/execute risk from an install step. This is the lowest-risk install mechanism.

Credentials

Requiring a single credential, NEMO_TOKEN, is appropriate for a remote API. But metadata also lists a config path (~/.config/nemovideo/) and the skill will generate/obtain an anonymous token when NEMO_TOKEN is absent. The config path requirement and filesystem detection behavior increase the scope of access beyond a single API token.

Persistence & Privilege

always is false and there is no indication the skill requests permanent system presence or modifies other skills. The skill runs as-needed and uses remote API calls; no elevated persistence privileges are requested.

What to consider before installing

This skill mostly behaves like a normal cloud text→video integrator: it needs a NEMO_TOKEN (or it will obtain a short-lived anonymous token) and it will upload whatever files you provide to mega-api-prod.nemovideo.ai. Things to consider before installing or using it: - Privacy: any text/files you upload (TXT, DOCX, PDF, images, audio) will be sent to the external API. Avoid uploading sensitive or confidential content unless you trust the service and its privacy policy. - Tokens: the skill will send Authorization: Bearer <NEMO_TOKEN> to the external domain. If you set NEMO_TOKEN in your environment, that secret will be transmitted to that host. - Unexpected local access: metadata and instructions indicate the skill may read the SKILL.md frontmatter and attempt to detect install paths (~/.clawhub/, ~/.cursor/skills/) and it declares ~/.config/nemovideo/ as a required config path. Ask the publisher why filesystem access is needed and what files under that path will be read. If you prefer, run the skill in an isolated environment or without a local NEMO_TOKEN. - Trust the domain: the API host (mega-api-prod.nemovideo.ai) is not a well-known public vendor in the manifest — verify the service owner and privacy/security practices before sending real data. - If you only want to test functionality, use throwaway content and do not provide proprietary data or your own production tokens. If the publisher is unknown, prefer not to store your main credentials in NEMO_TOKEN. Given these unexplained filesystem/access bits (configPath + install-path probing) I recommend asking the skill author for clarification or using it in a sandboxed environment; the mismatch is concerning enough to mark it as suspicious rather than benign.

Getting Started

Send me your text prompt and I'll handle the AI video creation. Or just describe what you're after.

Try saying:

• "generate a 150-word product description into a 1080p MP4"
• "turn this blog intro into a 30-second video with visuals and background music"
• "generating videos from written content without filming anything for marketers, content creators, educators"

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 Creation — Convert Text Into Shareable Videos

Drop your text prompt 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 150-word product description, ask for turn this blog intro into a 30-second video with visuals and background music, and about 1-2 minutes later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter, clearer prompts produce more accurate scene matches than long paragraphs.

Matching Input to Actions

User prompts referencing text to video creation, 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-creation
• 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.

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.

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)

Common Workflows

Quick edit: Upload → "turn this blog intro into a 30-second video with visuals and background music" → Download MP4. Takes 1-2 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 "turn this blog intro into a 30-second video with visuals and background music" — concrete instructions get better results.

Max file size is 500MB. Stick to TXT, DOCX, PDF, plain text for the smoothest experience.

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