Cap Cut
ReviewAudited by ClawScan on May 8, 2026.
Overview
This is a coherent cloud video-editing skill, but it will connect to NemoVideo, use a bearer token, and upload the media you provide for remote rendering.
Install only if you are comfortable sending selected videos to the NemoVideo cloud backend for processing. Use a dedicated token where possible, avoid uploading sensitive footage unless the provider’s privacy terms are acceptable, and review exports before posting.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Private or unpublished clips you choose to process may leave your device and be handled by the NemoVideo cloud backend.
User-supplied video files are sent to a third-party cloud renderer. This is central to the stated function and is disclosed, but the media may be sensitive.
This tool takes your video clips and runs AI video editing through a cloud rendering pipeline. You upload, describe what you want, and download the result.
Only upload content you are comfortable processing in that cloud service, and check provider terms or privacy handling if the clips are sensitive.
The agent can use the token to create sessions, run renders, and check credits on the backend.
The skill uses a backend access token and can create an anonymous token if one is not present. This is expected for backend access but still grants service access and credits.
Look for `NEMO_TOKEN` in the environment. If found, skip to session creation. Otherwise: ... POST `https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token` ... Include `Authorization: Bearer <NEMO_TOKEN>`
Use a dedicated token if possible and avoid sharing logs that contain Authorization headers or token values.
When you ask it to edit or export, the agent will perform multiple remote API calls and may start cloud rendering jobs.
The instructions authorize external API actions for uploading, rendering, polling, and downloading. These are proportional to the video-editing purpose.
Upload: POST `/api/upload-video/nemo_agent/me/<sid>` ... Export ... POST `/api/render/proxy/lambda` ... Poll GET `/api/render/proxy/lambda/<id>` every 30s
Review the requested edit/export before providing media, and stop the session if you do not want cloud rendering to continue.
A backend response can cause the agent to continue with editing or export steps instead of simply displaying the message.
The skill tells the agent to translate backend messages into API actions, making service responses influential over subsequent behavior. The actions appear scoped to the current editing session.
Backend Response Translation ... `click [button]` ... Execute via API ... `Export button` / `导出` | Execute export workflow
Use it for intended video-editing tasks and verify final outputs; developers should keep backend-driven actions scoped to the active session and user request.