Google Ai Studio

Skip the learning curve of professional editing software. Describe what you want — use Gemini AI to summarize this video and generate a short highlight reel...

Security Scan

The skill's name and description invoke Google/Gemini, but the runtime instructions use a third‑party nemo API (nemovideo.ai) and request a NEMO_TOKEN; that branding mismatch and remote upload behavior make the package potentially deceptive and worth caution.

Purpose & Capability

The skill markets itself as "Google AI Studio" and repeatedly mentions Gemini AI, but its runtime API endpoints, token name (NEMO_TOKEN), and config paths all point to a third‑party service (nemovideo.ai / nemovideo config). There is no use of Google APIs or Google credentials in the instructions. This is either a wrapper that proxies Gemini via a third party or a misleading name/branding; either way it's inconsistent with expectations for a Google product.

Instruction Scope

The SKILL.md tells the agent to look for NEMO_TOKEN, and if absent generate an anonymous token by POSTing to the nemo anonymous-token endpoint, then create sessions, upload user video files, stream SSE messages, and poll render jobs. All of these actions are consistent with a remote video processing service. The instructions do not ask the agent to read unrelated system secrets, but they do describe deriving X-Skill-Platform from install paths and reference a local config directory (~/.config/nemovideo/) — which implies some filesystem probing of install/config paths.

Install Mechanism

This is an instruction-only skill with no install spec and no code files, so nothing is written to disk by an installer. That lowers install-time risk.

Credentials

The only declared credential is NEMO_TOKEN, which matches the API the skill uses. However, the skill's public-facing description invokes Google Gemini while not requesting any Google credentials — a mismatch that could indicate misleading branding. The metadata also lists a nemovideo config path (~/.config/nemovideo/), which would give the skill access to local configuration if used; the SKILL.md implies it may read install paths to set headers.

Persistence & Privilege

The skill is not force‑enabled (always: false) and requests no special platform privileges or persistent system modifications. Autonomous invocation is allowed (default) but not combined here with other high‑risk privileges.

What to consider before installing

Be cautious before installing: the skill is named and marketed like an official Google/Gemini tool but actually uses a third‑party backend (nemovideo.ai). Videos you upload will be sent to that remote service and an anonymous or provided NEMO_TOKEN will be used for authorization. Before using it: verify the publisher/owner and the service domain; review nemovideo.ai's privacy and terms (who retains uploaded videos, how long, and whether content is reused); prefer skills that clearly document which vendor runs the backend; avoid uploading sensitive videos until you're confident in the service; and if you expect an official Google integration, ask the author for clarification or proof of use of Google's APIs.

Getting Started

Send me your video or text prompts and I'll handle the AI content generation. Or just describe what you're after.

Try saying:

• "generate a 2-minute raw interview clip into a 1080p MP4"
• "use Gemini AI to summarize this video and generate a short highlight reel"
• "generating and editing video content using Google Gemini AI models for developers and content creators"

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.

Google AI Studio — Generate and Edit AI Videos

Send me your video or text prompts and describe the result you want. The AI content generation runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 2-minute raw interview clip, type "use Gemini AI to summarize this video and generate a short highlight reel", and you'll get a 1080p MP4 back in roughly 30-90 seconds. All rendering happens server-side.

Worth noting: shorter clips under 60 seconds yield faster and more accurate AI-generated outputs.

Matching Input to Actions

User prompts referencing google ai studio, 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is google-ai-studio, 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

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 → "use Gemini AI to summarize this video and generate a short highlight reel" → Download MP4. Takes 30-90 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 "use Gemini AI to summarize this video and generate a short highlight reel" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across platforms and devices.