Ai Video Editor Hot

Get polished edited clips ready to post, without touching a single slider. Upload your raw video footage (MP4, MOV, AVI, WebM, up to 500MB), say something li...

Security Scan

The skill's declared need for a single NEMO_TOKEN and the described API calls align with a cloud video-editing service, but there are a few inconsistencies and privacy/behavior concerns (automatic outbound connections, a metadata mismatch about config paths, and implicit filesystem probing) that you should understand before installing.

Purpose & Capability

The skill is an instruction-only integration with a remote video-editing API and requests a single credential NEMO_TOKEN — this is consistent with its stated purpose. However the SKILL.md frontmatter advertises a required config path (~/.config/nemovideo/) while the registry Requirements block lists no required config paths, creating an inconsistency about whether the skill will read/write config files on disk.

Instruction Scope

Runtime instructions direct the agent to: (a) automatically connect to an external service on first open and obtain an anonymous token if no NEMO_TOKEN is present; (b) create and store session IDs and upload user media to https://mega-api-prod.nemovideo.ai; and (c) autodetect an install path to set X-Skill-Platform. Automatic outbound network activity and implicit filesystem checks (install path/config dir) are broader in scope than a simple on-demand file upload flow and may happen without an explicit user consent step.

Install Mechanism

There is no install spec and no code files — the skill is instruction-only. That lowers the risk from arbitrary code installation.

Credentials

Only NEMO_TOKEN is declared as required and is appropriate for a hosted video-editing API. But SKILL.md metadata also lists a config path (~/.config/nemovideo/) which was not reflected in the registry Requirements; if the skill will read/write that directory, it should be declared explicitly. The instructions also tell the agent not to display token values to the user, which is reasonable for secret handling but worth knowing (tokens will be stored/used by the agent).

Persistence & Privilege

always is false (normal). The skill instructs storing session_id for subsequent requests; storage location is unspecified (could be memory or ~/.config/nemovideo/). The agent may retain session state across uses — ask how/where session tokens are persisted and how to revoke them. Autonomous invocation is allowed by default, which increases the impact of the other concerns but is not itself a misconfiguration.

What to consider before installing

This skill generally matches a cloud video-editing integration: it needs a NEMO_TOKEN and talks to a nemovideo.ai API to upload and render clips. Before installing, ask the skill author or vendor: 1) Will the skill automatically contact the external API as soon as you open it (the SKILL.md says it will)? If so, are you comfortable that anonymous tokens will be minted without an explicit consent prompt? 2) Where are session tokens/session_id stored (in memory, or on disk under ~/.config/nemovideo/)? The SKILL.md mentions that config path but the registry metadata did not — confirm persistence and how to revoke/delete stored tokens. 3) Confirm exactly what files can be uploaded (it will send user media to the remote service) and ensure you’re okay with that data leaving your environment. 4) If you need stricter control, require that the skill ask for explicit confirmation before creating tokens or uploading files. If you cannot get clear answers to these questions, treat installation as higher risk.

Getting Started

Got raw video footage to work with? Send it over and tell me what you need — I'll take care of the AI-powered video editing.

Try saying:

• "edit a 2-minute unedited screen recording or phone clip into a 1080p MP4"
• "cut the boring parts, add background music, and export a tight 60-second version"
• "quickly editing raw footage into share-ready videos without manual timeline work for content creators and social media marketers"

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.

AI Video Editor — Edit and Export Polished Videos

Send me your raw video footage and describe the result you want. The AI-powered video editing runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 2-minute unedited screen recording or phone clip, type "cut the boring parts, add background music, and export a tight 60-second version", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: shorter clips under 90 seconds process significantly faster and give cleaner AI cut suggestions.

Matching Input to Actions

User prompts referencing ai video editor hot, 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.

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

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

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

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.

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)

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

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "cut the boring parts, add background music, and export a tight 60-second version" — concrete instructions get better results.

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

Export as MP4 with H.264 codec for the widest compatibility across platforms.

Common Workflows

Quick edit: Upload → "cut the boring parts, add background music, and export a tight 60-second version" → 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.