Video Editing Ai Gemini

Get AI-edited videos ready to post, without touching a single slider. Upload your raw video footage (MP4, MOV, AVI, WebM, up to 500MB), say something like "c...

Security Scan

The skill's requests and runtime instructions are consistent with a remote video-editing API: it needs one service token, uploads user video files, and makes API calls to the documented nemo video backend — nothing in the bundle suggests unrelated or excessive access.

Purpose & Capability

The skill's name and description (remote AI video editing) match the required credential (NEMO_TOKEN) and the API endpoints in SKILL.md. Minor inconsistency: the registry's top-level summary listed no required config paths, but the SKILL.md frontmatter metadata also lists a config path (~/.config/nemovideo/). That directory would be reasonable for storing a nemo client config/token, but the inconsistency between places should be noted.

Instruction Scope

Runtime instructions stay within the editing use case: create or use a NEMO_TOKEN, open a session, upload videos (multipart file or URL), stream edits via SSE, poll export status, and return download URLs. It asks the agent to detect an install path to set an X-Skill-Platform header and to persist session_id for job polling — both are coherent with the stated server-side rendering workflow. The instructions do not ask the agent to read unrelated system files or additional credentials.

Install Mechanism

No install spec or code files are included; the skill is instruction-only, which is the lowest-risk install profile. There are no downloads or package installs to evaluate.

Credentials

The skill only requires one credential (NEMO_TOKEN), which is proportional to a cloud service client. The frontmatter also references a config path (~/.config/nemovideo/) and a primaryEnv of NEMO_TOKEN — reasonable for holding tokens, but the registry metadata and frontmatter are inconsistent about required config paths. The skill also documents a way to generate a short-lived anonymous token via the service API; that behavior is expected but means the agent may obtain and store service tokens on first use.

Persistence & Privilege

always is false and the skill does not request elevated or permanent platform privileges. It asks to save a session_id and to reuse or store a token (normal for session management) but does not instruct changing other skills or system-wide settings.

Assessment

This skill appears to do what it says: it uploads your video to a nemo-video backend, edits it server-side, and returns a download link. Before installing/using it, consider: (1) privacy — uploaded raw video will be sent to https://mega-api-prod.nemovideo.ai, so review their policies or avoid sensitive footage; (2) token handling — the skill may generate and store a short-lived anonymous NEMO_TOKEN on first use or use a provided NEMO_TOKEN; store such tokens only if you trust the service; (3) config path note — the SKILL.md references ~/.config/nemovideo/, so check whether your agent environment will allow reading/writing that directory if you are uncomfortable with that; (4) verify the service domain and owner if you need higher assurance (this package has no homepage or provenance). If any of these are unacceptable, do not enable the skill.

Getting Started

Send me your raw video footage and I'll handle the AI-powered video editing. Or just describe what you're after.

Try saying:

• "edit a 2-minute unedited screen recording into a 1080p MP4"
• "cut the pauses, add transitions, and generate a summary caption using Gemini AI"
• "using Gemini AI to automatically edit and enhance raw video footage for content creators and marketers"

Automatic Setup

On first interaction, connect to the processing API before doing anything else. Show a brief status like "Setting things up...".

Token: If NEMO_TOKEN environment variable is already set, use it and skip to Session below.

Free token: Generate a UUID as client identifier, then POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id: <uuid>. The response field data.token becomes your NEMO_TOKEN (100 credits, 7-day expiry).

Session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Save session_id from the response.

Confirm to the user you're connected and ready. Don't print tokens or raw JSON.

Video Editing AI Gemini — Edit Videos with Gemini AI

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, type "cut the pauses, add transitions, and generate a summary caption using Gemini AI", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: shorter clips under 60 seconds get the fastest Gemini processing results.

Matching Input to Actions

User prompts referencing video editing ai gemini, 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: video-editing-ai-gemini
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

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.

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 "cut the pauses, add transitions, and generate a summary caption using Gemini AI" — 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 across platforms and devices.

Common Workflows

Quick edit: Upload → "cut the pauses, add transitions, and generate a summary caption using Gemini AI" → 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.