Free Text Background Video

Turn a 30-second talking head clip with a cluttered background into 1080p background-free videos just by typing what you need. Whether it's removing video ba...

Security Scan

The skill's requests and runtime instructions are consistent with a cloud-based video background-removal service and do not ask for unrelated credentials or risky installs.

Purpose & Capability

The name/description, required env var (NEMO_TOKEN), and the API endpoints described all align with a remote video-rendering/background-removal service. Minor inconsistency: the SKILL.md frontmatter mentions a config path (~/.config/nemovideo/) for metadata, while the registry metadata said no required config paths — this is likely a bookkeeping mismatch rather than malicious.

Instruction Scope

Runtime instructions are narrowly focused on creating/using a session token, uploading media, streaming SSE messages, polling render status, and returning download URLs. It does read/detect local install paths to set an attribution header and references a config directory in the frontmatter metadata, but it does not instruct scanning arbitrary system files or reading unrelated environment variables.

Install Mechanism

There is no install spec and no code files — this is instruction-only, which minimizes disk persistence and install risks.

Credentials

Only one credential (NEMO_TOKEN) is declared as required and is appropriate for a cloud API. The SKILL.md also documents obtaining an anonymous token automatically if NEMO_TOKEN is absent, which is coherent. The only small concern is the frontmatter's mention of a config path (~/.config/nemovideo/) which suggests it may look under that directory for local config — this is plausible for attribution but not strictly necessary for core functionality.

Persistence & Privilege

The skill is not always-on and does not request elevated privileges or modify other skills. It will operate remotely and only persists session state on the service side; there's no local installation or daemon requested.

Assessment

This skill will upload your video (and any text you provide) to a remote rendering service at mega-api-prod.nemovideo.ai and requires a NEMO_TOKEN to authenticate. If you don't provide a token the skill will request an anonymous token from the service for temporary use. Before installing or using the skill, consider: (1) Do you trust the nemovideo endpoint to handle your media? Avoid uploading sensitive or private footage you wouldn't want sent to a third party. (2) The skill may read local install paths or a config directory for attribution headers; this is not the same as exfiltrating arbitrary files, but be cautious if you have sensitive files in those paths. (3) There is no local install, so disk persistence risk is low. If you need higher assurance, ask the publisher for a privacy/data-retention policy or use your own service credentials (NEMO_TOKEN) rather than anonymous tokens.

Getting Started

Share your text or video and I'll get started on background removal and text overlay. Or just tell me what you're thinking.

Try saying:

• "create my text or video"
• "export 1080p MP4"
• "remove the background and replace it"

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.

Free Text Background Video — Remove Backgrounds and Add Text

Send me your text or video and describe the result you want. The background removal and text overlay runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 30-second talking head clip with a cluttered background, type "remove the background and replace it with a clean white backdrop, then add my brand name as a text overlay", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.

Worth noting: solid or evenly lit backgrounds produce cleaner removal results.

Matching Input to Actions

User prompts referencing free text background video, 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.

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

• X-Skill-Source: free-text-background-video
• 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.

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.

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 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 "remove the background and replace it with a clean white backdrop, then add my brand name as a text overlay" — concrete instructions get better results.

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

Export as MP4 for widest compatibility.

Common Workflows

Quick edit: Upload → "remove the background and replace it with a clean white backdrop, then add my brand name as a text overlay" → Download MP4. Takes 30-60 seconds 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.