← Back to Skills Marketplace
Xiaoming Video
by
susan4731-wilfordf
· GitHub ↗
· v1.0.0
· MIT-0
69
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install xiaoming-video
Description
Get edited video clips ready to post, without touching a single slider. Upload your raw video footage (MP4, MOV, AVI, WebM, up to 500MB), say something like...
Usage Guidance
This skill appears to be what it claims: a cloud video-editing assistant that uploads your footage to nemovideo.ai and uses a NEMO_TOKEN for auth. Before installing/using it: (1) confirm you are comfortable having raw videos uploaded to https://mega-api-prod.nemovideo.ai (check their privacy/retention policy); (2) verify how the skill stores the anonymous or provided NEMO_TOKEN (ephemeral memory vs written to disk); (3) note the minor metadata mismatch (SKILL.md references ~/.config/nemovideo/ while registry said no config paths) — ask the publisher whether any local files will be written; (4) because source/homepage are unknown, prefer using an anonymous token rather than a long-lived account token, and avoid uploading sensitive or private footage until you verify the service and policies.
Capability Analysis
Type: OpenClaw Skill
Name: xiaoming-video
Version: 1.0.0
The 'xiaoming-video' skill is a legitimate integration for an AI video editing service (nemovideo.ai). It provides instructions for an AI agent to manage authentication tokens, upload video files, and interface with a cloud rendering API via SSE and REST endpoints. The skill includes transparent metadata regarding its environment variable requirements (NEMO_TOKEN) and configuration paths. There is no evidence of malicious intent, data exfiltration of sensitive local credentials, or unauthorized command execution; all network activity is directed toward the stated service domain (mega-api-prod.nemovideo.ai).
Capability Assessment
Purpose & Capability
The skill is a cloud video-editing frontend: it requires a NEMO_TOKEN and communicates with endpoints at mega-api-prod.nemovideo.ai for session, upload, and export. Requesting a single API token and uploading media to a remote rendering API is proportionate to the stated purpose.
Instruction Scope
Runtime instructions direct the agent to accept user video files and upload them to the nemovideo API, create or reuse an auth token (anonymous-token flow if none provided), create sessions, run SSE for edits, poll export status, and return download URLs. These behaviors are expected for the service, but they do mean the skill will transmit user video/audio to a third-party endpoint; users should expect that their raw footage will leave their device. The instructions do not appear to read unrelated system files or require unrelated credentials, though they do instruct the agent to detect its install path to populate attribution headers.
Install Mechanism
No install spec and no code files (instruction-only). This is the lowest-risk install footprint — nothing is downloaded or written by an install step in the skill bundle itself.
Credentials
The only required environment credential is NEMO_TOKEN (declared as primary), which aligns with the API-based workflow. One minor inconsistency: the SKILL.md frontmatter lists a configPaths value (~/.config/nemovideo/) while the registry metadata reported 'Required config paths: none'. Also, the anonymous-token flow instructs the agent to treat the returned token as NEMO_TOKEN (storage location unspecified) — clarify whether the token is kept in ephemeral memory or persisted to disk/environment.
Persistence & Privilege
The skill is not always-enabled and uses normal model invocation. There is no install behavior that requests elevated or persistent platform privileges. The skill will maintain an in-session session_id/token for job orchestration, which is appropriate for its runtime behavior.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install xiaoming-video - After installation, invoke the skill by name or use
/xiaoming-video - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of Xiaoming Video skill for fast personal video editing and export.
- Upload raw video clips (MP4, MOV, AVI, WebM, up to 500MB) and request edits by describing your needs.
- Automated connection to the cloud video processing API—handles token setup, session creation, and status feedback.
- Supports actions like trimming, adding subtitles, viewing credits, exporting as 1080p MP4, and more via simple prompts.
- Designed for quick, easy edits for casual creators; no editing experience required.
- Backend handles error cases (file types, credit usage, export restrictions) and guides users accordingly.
Metadata
Frequently Asked Questions
What is Xiaoming Video?
Get edited video clips ready to post, without touching a single slider. Upload your raw video footage (MP4, MOV, AVI, WebM, up to 500MB), say something like... It is an AI Agent Skill for Claude Code / OpenClaw, with 69 downloads so far.
How do I install Xiaoming Video?
Run "/install xiaoming-video" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Xiaoming Video free?
Yes, Xiaoming Video is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Xiaoming Video support?
Xiaoming Video is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Xiaoming Video?
It is built and maintained by susan4731-wilfordf (@susan4731-wilfordf); the current version is v1.0.0.
More Skills