Video Trimmer Google

trim video clips into trimmed video clips with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. casual users and content creators use it for cut...

Security Scan

The skill's declared purpose (cloud video trimming) matches the APIs, token requirement, and instructions; nothing in the SKILL.md is wildly out-of-scope, but there are a few small privacy/behavior ambiguities you should review before installing.

Purpose & Capability

The skill is a cloud video trimming front-end and requires a single service credential (NEMO_TOKEN) and talks to nemovideo.ai endpoints — this aligns with the stated functionality. Declared config path (~/.config/nemovideo/) and session handling are consistent with a remote service client.

Instruction Scope

Runtime instructions are focused on the nemovideo.ai API (session creation, upload, SSE, render polling). The skill tells the agent to upload user videos (multipart file uploads or URLs) and to read/store session_id and use the NEMO_TOKEN. It also instructs detecting install paths (~/.clawhub, ~/.cursor/skills/) to set an X-Skill-Platform header — this requires reading other directories in the user home and is a modest privacy concern but not obviously malicious. The SKILL.md does not instruct the agent to read arbitrary system files beyond these paths.

Install Mechanism

Instruction-only skill with no install spec and no code files; this is the lowest-risk install model (nothing is downloaded or written by an installer step).

Credentials

Only NEMO_TOKEN is required, which is appropriate for a third‑party video processing service. The instructions will generate an anonymous token if none is present; it's unclear whether that token or the session_id is persisted to disk (metadata references a config path). That ambiguity affects where credentials are stored and for how long (anonymous tokens are valid for 7 days per the text).

Persistence & Privilege

Skill is not always:true and does not request elevated system privileges. It may store session state or tokens for later requests (expected), but it does not instruct modifying other skills or system-wide configs. The instructions mention that render jobs can be orphaned if the client closes the tab — normal for remote async jobs.

Assessment

This skill appears to do what it says: it uploads videos to a nemovideo.ai backend for cloud trimming and returns download URLs. Before installing or using: (1) Confirm you trust the domain mega-api-prod.nemovideo.ai and review that service's privacy/retention policy — any uploaded video (potentially sensitive) will be sent to that backend. (2) Decide whether you want to supply your own NEMO_TOKEN (gives you control) or allow the skill to obtain an anonymous token; the SKILL.md is ambiguous about where/if tokens and session_ids are persisted (it references a config path). Ask the platform how/where the token/session is stored and whether it is saved to disk or environment, and whether logs include API responses. (3) Be aware the skill reads a couple of home directories to set an X-Skill-Platform header — this reveals installed-skill locations and is a minor privacy leak. (4) Avoid uploading videos you consider highly sensitive until you confirm the backend's handling of data. If you need higher assurance, request explicit documentation from the skill author about token persistence and data retention.

Getting Started

Got video clips to work with? Send it over and tell me what you need — I'll take care of the AI video trimming.

Try saying:

• "trim a 10-minute screen recording with dead air into a 1080p MP4"
• "trim the first 30 seconds and cut the silence in the middle"
• "cutting and trimming videos quickly in a browser for casual users and content creators"

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.

Video Trimmer Google — Trim and Export Video Clips

This tool takes your video clips and runs AI video trimming through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 10-minute screen recording with dead air and want to trim the first 30 seconds and cut the silence in the middle — the backend processes it in about 20-40 seconds and hands you a 1080p MP4.

Tip: shorter clips under 2 minutes process significantly faster.

Matching Input to Actions

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

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 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.

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 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

Common Workflows

Quick edit: Upload → "trim the first 30 seconds and cut the silence in the middle" → Download MP4. Takes 20-40 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 "trim the first 30 seconds and cut the silence in the middle" — 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 devices and platforms.