Maker Ai Best
PassAudited by ClawScan on Apr 30, 2026.
Overview
This is a cloud video-editing skill that is broadly consistent with its purpose, but users should notice that it uploads media to an external service, uses a Nemo token, and can create cloud render jobs.
Install this only if you are comfortable sending your uploaded media and editing instructions to the Nemo video cloud service. Use non-sensitive clips first, keep track of credits or subscription limits, and ask for backend details before uploading anything private.
Findings (8)
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.
The editing service may direct the agent through workflow steps rather than every step being visibly chosen by the user.
The skill makes backend-generated instructions operationally authoritative for subsequent API actions. This appears tied to the video-editing workflow, but users should know the remote service can guide agent actions within the workflow.
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
Use the skill for intended video-editing tasks and review visible outputs, exports, and account-credit effects before relying on the result.
Files you provide may be uploaded to the service and export jobs may be started when you ask for rendering or downloading.
The skill directs the agent to use external API operations that upload user files and start render/export jobs. These operations are core to the stated purpose, but they can affect cloud state and potentially account credits.
`/api/upload-video/nemo_agent/me/<sid>` | POST | Upload a file (multipart) or URL. ... `/api/render/proxy/lambda` | POST | Start export.
Only provide media you are comfortable uploading, and be explicit when you want an export to be started.
The skill can act against the Nemo video service using the provided or generated token, including checking credits, uploading media, and starting render jobs.
The skill uses a bearer token for the Nemo video backend. This is declared and purpose-aligned, but the token represents account or anonymous-session authority for the service.
Include `Authorization: Bearer <NEMO_TOKEN>` and all attribution headers on every request
Use a token intended for this service and avoid sharing tokens tied to accounts or credits you do not want the skill to use.
Users have limited external provenance information for who maintains the skill or where to verify it outside the registry.
The skill has no code or install dependencies, but its provenance information is limited while it depends on a remote video backend.
Source: unknown; Homepage: none
Prefer using this with non-sensitive media unless you trust the publisher and the referenced Nemo backend.
Your editing session state and generated media references may persist in the backend session and be used for later actions in the same project.
The skill retrieves and relies on cloud session state containing project draft and generated media context. This is expected for video editing but means project context is stored and reused across workflow steps.
`/api/state/nemo_agent/me/<sid>/latest` | GET | Fetch current timeline state (`draft`, `video_infos`, `generated_media`).
Avoid uploading private or regulated media unless you are comfortable with the backend storing project state for the session.
Raw video, audio, images, prompts, and project metadata may leave your local environment and be processed by the Nemo video backend.
The skill clearly relies on an external cloud service that receives user media and prompts. This is purpose-aligned, but it is a sensitive data boundary users should understand.
This tool takes your raw video clips and runs AI video creation through a cloud rendering pipeline. You upload, describe what you want, and download the result.
Do not use confidential, personal, or third-party-restricted media unless you trust the service and its handling of uploaded content.
An interrupted export may keep running or leave an unfinished cloud job, which could affect credits or project state.
Render jobs can continue or become orphaned in the cloud if the session is interrupted. This is disclosed and consistent with cloud rendering, but it can leave work running outside the immediate chat flow.
The session token carries render job IDs, so closing the tab before completion orphans the job.
Wait for exports to finish when possible, and check status or credits if a session is interrupted.
You may see a simple status message rather than full details about token creation, session setup, or backend calls.
The instruction favors a simplified user experience while the skill performs authentication and backend session setup. This is not inherently deceptive, but users should still understand that external service calls are occurring.
Tell the user you're ready. Keep the technical details out of the chat.
Ask the agent for details if you want to know what service is being contacted or what data is being sent before uploading files.