Ai Video Editor Eye Contact

correct recorded video footage into eye contact corrected video with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. content creators, remote w...

Security Scan

The skill's requirements and runtime instructions are internally consistent with a cloud-based video eye-contact correction service, but it will send user videos and create/store a third-party session token on your behalf — review privacy and trust in the nemovideo.ai service before use.

Purpose & Capability

Name/description (AI eye-contact correction) match the declared requirement of a single API token (NEMO_TOKEN) and the SKILL.md describes uploading videos and requesting renders from the nemo backend; the requested env var is appropriate and expected.

Instruction Scope

Instructions direct the agent to create anonymous tokens, create sessions, upload local video files, use SSE for edits, and poll for render results — all expected for a cloud render pipeline. The skill also instructs detecting install path (~/.clawhub, ~/.cursor/skills/) to set an attribution header and to avoid showing raw API responses or token values to users; both are plausible but worth noting because they involve reading a small part of the home directory and programmatically hiding the token value.

Install Mechanism

Instruction-only skill with no install step or downloaded code; lowest install risk.

Credentials

Only a single credential (NEMO_TOKEN) is required and it is the primaryEnv; SKILL.md explains how to obtain an anonymous token if none is present. No unrelated credentials or broad environment/config paths are requested.

Persistence & Privilege

Skill is not forced-always, does not request persistent system-wide privileges, and only asks to store a session_id for ongoing requests (normal for a session-based API). Autonomous invocation is allowed but is the platform default.

Assessment

This skill will upload your video files to a third-party service (mega-api-prod.nemovideo.ai) for processing and will create or use a NEMO_TOKEN (anonymous token if you don't provide one). Before installing: confirm you trust nemovideo.ai and are comfortable sending the specific videos you plan to process (sensitive content should not be uploaded). You can provide your own NEMO_TOKEN from an account you control instead of letting the skill auto-generate one. Be aware the skill will read small paths under your home (to set an attribution header) and will store session IDs for ongoing API calls; if you need stronger guarantees, ask the skill author for details on token/session storage, data retention, and the service's privacy policy. If you do not trust the external service, do not use this skill or only test with non-sensitive sample footage.

Getting Started

Send me your recorded video footage and I'll handle the AI eye contact correction. Or just describe what you're after.

Try saying:

• "correct a 3-minute webcam interview recording into a 1080p MP4"
• "fix my eye contact so I look directly at the camera instead of the screen"
• "fixing eye contact in webcam recordings and video calls for content creators, remote workers, online educators"

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 Eye Contact — Fix Eye Contact in Videos

This tool takes your recorded video footage and runs AI eye contact correction through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 3-minute webcam interview recording and want to fix my eye contact so I look directly at the camera instead of the screen — the backend processes it in about 1-2 minutes and hands you a 1080p MP4.

Tip: works best when your face is well-lit and centered in the frame.

Matching Input to Actions

User prompts referencing ai video editor eye contact, 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.

All requests must include: Authorization: Bearer <NEMO_TOKEN>, X-Skill-Source, X-Skill-Version, X-Skill-Platform. Missing attribution headers will cause export to fail with 402.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is ai-video-editor-eye-contact, X-Skill-Version comes from the version field, and X-Skill-Platform is detected from the install path (~/.clawhub/ = clawhub, ~/.cursor/skills/ = cursor, otherwise unknown).

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

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

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.

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)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "fix my eye contact so I look directly at the camera instead of the screen" — 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 best balance of quality and file size.

Common Workflows

Quick edit: Upload → "fix my eye contact so I look directly at the camera instead of the screen" → 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.