Editor Background Changer

Skip the learning curve of professional editing software. Describe what you want — replace my office background with a clean studio backdrop — and get backgr...

Security Scan

The skill's stated purpose (remote AI background replacement) mostly matches its instructions, but there are inconsistencies and a few behaviors (automatic token generation/storage and directives to hide tokens, plus a metadata mismatch about config paths) that warrant caution before installing.

Purpose & Capability

Name and description match the runtime instructions (upload video → remote render). Requesting a service token (NEMO_TOKEN) is consistent with a cloud API-backed editor. However the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while the registry metadata earlier reported no required config paths — this mismatch is unexplained.

Instruction Scope

Runtime instructions tell the agent to obtain anonymous tokens, create sessions, upload user video files, poll render jobs, and store session IDs. They also explicitly instruct not to display raw API responses or token values to the user — a directive that could be used to hide credential values from end users. The skill also asks to 'auto-detect' a platform header from the install path (which implies reading agent install/environment paths). These behaviors expand scope beyond simple upload/transform: they include credential management and filesystem/context probing.

Install Mechanism

No install spec and no code files — instruction-only. That minimizes disk-write risk; nothing is downloaded or executed by an installer as part of the skill itself.

Credentials

Only one credential is required (NEMO_TOKEN), which is appropriate for a cloud API. But the skill instructs the agent to automatically obtain and store a token when none is present and to keep that token hidden from the user. It's unclear where and how the token/session_id will be persisted (in-memory, environment, or on-disk config). The unexplained frontmatter config path (~/.config/nemovideo/) suggests possible disk persistence which was not declared in the registry metadata — this inconsistency raises proportionality concerns.

Persistence & Privilege

always:false and no install script mean it does not demand permanent, elevated presence. The skill does ask to persist session state/tokens for reuse, but that is within its own scope and not obviously modifying other skills or global agent settings.

Scan Findings in Context

[no-findings] expected: No code files were present so the regex-based scanner had nothing to analyze. For instruction-only skills, the SKILL.md is the primary surface to evaluate.

What to consider before installing

This skill performs video uploads and creates/stores API tokens and session IDs to a remote service (mega-api-prod.nemovideo.ai). Before installing, consider: - Are you comfortable sending potentially sensitive video content to an external service? Confirm their privacy/storage policy and retention. - Ask the author where tokens and session_ids are stored (memory vs disk) and how to revoke or delete them; the frontmatter hints at ~/.config/nemovideo/ but registry metadata did not. - The skill explicitly says not to show raw API responses or token values to users — ask why and request transparency about stored credentials. - Verify the service domain (nemovideo.ai) is legitimate for your use and that uploads are sent over TLS. - If you handle sensitive footage, prefer a local/offline tool or a vetted provider; otherwise test with non-sensitive samples and monitor network activity. If the author can clarify storage location and token lifecycle (and remove the unexplained config-path mismatch), the risk would be reduced.

Getting Started

Share your video clips and I'll get started on AI background replacement. Or just tell me what you're thinking.

Try saying:

• "replace my video clips"
• "export 1080p MP4"
• "replace my office background with a"

First-Time Connection

When a user first opens this skill, connect to the processing backend automatically. Briefly let them know (e.g. "Setting up...").

Authentication: Check if NEMO_TOKEN is set in the environment. If it is, skip to step 2.

1. Obtain a free token: Generate a random UUID as client identifier. POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id set to that UUID. The response data.token is your NEMO_TOKEN — 100 free credits, valid 7 days.
2. Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer <token>, Content-Type: application/json, and body {"task_name":"project","language":"<detected>"}. Store the returned session_id for all subsequent requests.

Keep setup communication brief. Don't display raw API responses or token values to the user.

Editor Background Changer — Replace Video Backgrounds Instantly

Send me your video clips and describe the result you want. The AI background replacement runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 60-second talking-head video clip, type "replace my office background with a clean studio backdrop", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.

Worth noting: videos with good contrast between subject and background process more accurately.

Matching Input to Actions

User prompts referencing editor background changer, 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.

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

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

Header	Value
X-Skill-Source	editor-background-changer
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

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.

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

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

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.

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)

Common Workflows

Quick edit: Upload → "replace my office background with a clean studio backdrop" → 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "replace my office background with a clean studio backdrop" — 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.