← Back to Skills Marketplace
Shotcut
by
susan4731-wilfordf
· GitHub ↗
· v1.0.0
· MIT-0
72
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install shotcut
Description
Get edited video clips ready to post, without touching a single slider. Upload your raw video footage (MP4, MOV, AVI, MKV, up to 500MB), say something like "...
Usage Guidance
This skill appears to do what it says (upload your video to a NemoVideo backend, run cloud edits, return a download). Before installing or using it: (1) verify you trust the NemoVideo endpoint (no homepage or owner info is provided here), (2) understand that uploading media sends your footage to an external service — do not upload sensitive content you wouldn't want stored or processed by a third party, (3) confirm where NEMO_TOKEN comes from and whether using an anonymous token is acceptable, (4) ask the author or registry to clarify the config-path discrepancy (~/.config/nemovideo/ present in SKILL.md but not declared in registry metadata), and (5) test with non-sensitive sample videos first. If you need higher assurance, request a homepage/privacy policy or source repo before proceeding.
Capability Analysis
Type: OpenClaw Skill
Name: shotcut
Version: 1.0.0
The skill is a legitimate integration for a cloud-based AI video editing service hosted at mega-api-prod.nemovideo.ai. It provides instructions for the agent to manage sessions, upload media, and poll for render status using a NEMO_TOKEN. The logic is consistent with the stated purpose of video editing, and there are no indicators of data exfiltration, malicious execution, or harmful prompt injection.
Capability Assessment
Purpose & Capability
The name/description describe cloud AI video editing and the SKILL.md contains concrete API endpoints and upload/render workflows that align with that purpose. Requesting a single service token (NEMO_TOKEN) is appropriate. However, the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while the registry metadata reported none — an internal inconsistency about required config paths.
Instruction Scope
Runtime instructions stay focused on connecting to the NemoVideo backend, creating sessions, uploading user-provided media, polling render status, and returning download links. This is within the stated scope. Two items to note: (1) the skill will make network calls to obtain anonymous tokens and to upload user media (expected for a cloud editor), and (2) it instructs reading frontmatter/install path to populate X-Skill-Platform and X-Skill-Version headers — that may require inspecting agent install paths or the SKILL.md file and is a minor privacy/telemetry action.
Install Mechanism
Instruction-only skill with no install spec or code files presents low install risk — nothing is downloaded or written by an installer.
Credentials
Only one credential is declared (NEMO_TOKEN) and it's the primaryEnv, which is proportional for a cloud editing service. The SKILL.md also describes obtaining an anonymous token when NEMO_TOKEN is absent (network call). The earlier-mentioned discrepancy about a config path in the frontmatter (~/.config/nemovideo/) is unexplained and could imply the skill expects local config files or will look for them; that should have been declared explicitly.
Persistence & Privilege
The skill does not request always:true and no elevated or persistent platform privileges are requested. It uses ephemeral session tokens for cloud jobs; jobs may remain on the remote service if you close the client (not a local privilege escalation).
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install shotcut - After installation, invoke the skill by name or use
/shotcut - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Shotcut 1.0.0 — Initial Release
- Instantly edit and export videos up to 500MB via simple chat commands.
- Supports automatic silent trimming, scene cuts, and smooth transitions — just describe what you want.
- Handles a wide range of formats (MP4, MOV, AVI, MKV for video; plus common image and audio types).
- One-click export to 1080p MP4; finished jobs delivered in about 30–90 seconds.
- Automatic token and session management; prompts for user login only if needed.
- Credits, timeline, and state management all accessible via chat prompts.
Metadata
Frequently Asked Questions
What is Shotcut?
Get edited video clips ready to post, without touching a single slider. Upload your raw video footage (MP4, MOV, AVI, MKV, up to 500MB), say something like "... It is an AI Agent Skill for Claude Code / OpenClaw, with 72 downloads so far.
How do I install Shotcut?
Run "/install shotcut" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Shotcut free?
Yes, Shotcut is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Shotcut support?
Shotcut is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Shotcut?
It is built and maintained by susan4731-wilfordf (@susan4731-wilfordf); the current version is v1.0.0.
More Skills