Token导航 LogoToken导航TokenDH.com
效率执行命令clawhub未标认证来源可访问clear审计提醒

roughcut-openclawroughcut OpenClaw 视频

Agent Skill

roughcut-openclaw 用于辅助视频、动画、脚本化剪辑和多媒体生成流程,适合在 OpenClaw 中需要整理视频素材、生成脚本或维护合成项目时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

21,050

周安装

895

GitHub Stars

公开资料未说明

下载量

7,375
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:roughcut-openclaw(roughcut OpenClaw 视频)
来源仓库:https://github.com/samergmtm22/roughcut-openclaw
安装命令:
openclaw skills install roughcut-openclaw
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install roughcut-openclaw

简介

在 macOS 上无头运行 RoughCut,从头部说话视频生成 Final Cut Pro (FCPXML) 粗剪时间线变体 — 本地优先,无媒体上传。

SKILL.md

name
roughcut
description
Run RoughCut headlessly on macOS to generate Final Cut Pro (FCPXML) rough-cut timeline variants from a talking-head video — local-first, no media upload.
metadata

RoughCut (macOS)

This skill lets an OpenClaw agent run RoughCut locally on a user's Mac to produce RoughCut.xml_variants.zip from a raw video file, without uploading media.

Preconditions

  1. Confirm the video is present on local disk and get an absolute file path (example: /Users/alice/Movies/raw.mp4).

If the file is on Google Drive/iCloud/Dropbox, ensure it is fully downloaded and accessible as a local file path. Tip: on macOS, you can drag the video file into Terminal to paste its absolute path. If the user is on a different machine than the OpenClaw Mac, agree on a delivery method: - Synced folder: a folder that syncs onto the OpenClaw Mac (iCloud Drive, Dropbox, Google Drive Desktop, etc.). - Direct download URL: ask the user for a direct HTTPS download link (for example an S3/R2/GCS pre-signed URL), then run RoughCut with --video-url (it downloads into output_root/RoughCut.inputs/ automatically).

  1. Confirm RoughCut repo is present on the same Mac.

- Repo: https://github.com/samerGMTM22/OpenClaw-RoughCut

  1. If the user enables fluff removal, ensure GEMINI_API_KEY is set in the environment that will run RoughCut.

If it is not set, ask the user to provide it and explain it is used only for fluff removal.

Questions To Ask The User

  1. Do you want to remove bad takes? (default: yes)
  2. Do you want to remove fluff/off-topic content? (default: no)
  3. If fluff removal is enabled: what is the video topic/goal? (required)

How To Run

Use repo_root and output_root from OpenClaw config:

bash "$REPO_ROOT/scripts/openclaw/roughcut.sh" \
  --video "$VIDEO_ABS_PATH" \
  --out "$OUTPUT_ROOT" \
  --remove-bad-takes true \
  --remove-fluff false

If the user provides a direct download URL, you can pass it directly (the runner downloads to $OUTPUT_ROOT/RoughCut.inputs/ first):

bash "$REPO_ROOT/scripts/openclaw/roughcut.sh" \
  --video-url "$VIDEO_URL" \
  --out "$OUTPUT_ROOT" \
  --remove-bad-takes true \
  --remove-fluff false

If the URL has no filename (common for pre-signed URLs), include --video-name, and optionally --video-sha256:

bash "$REPO_ROOT/scripts/openclaw/roughcut.sh" \
  --video-url "$VIDEO_URL" \
  --video-name "my_video.mov" \
  --video-sha256 "0123456789abcdef..." \
  --out "$OUTPUT_ROOT" \
  --remove-bad-takes true \
  --remove-fluff false

If fluff removal is enabled:

bash "$REPO_ROOT/scripts/openclaw/roughcut.sh" \
  --video "$VIDEO_ABS_PATH" \
  --out "$OUTPUT_ROOT" \
  --remove-bad-takes true \
  --remove-fluff true \
  --topic "$TOPIC"

The runner prints a single-line JSON result to stdout. On success it includes:

  • xml_variants_zip: absolute path to RoughCut.xml_variants.zip
  • video_path: absolute path to the input video used for processing
  • downloaded_video_path: present only when --video-url was used (where the video was saved)

On failure it will include:

  • error
  • optionally debug_zip (a bundle of intermediate outputs)

What To Return To The User

  1. The output zip path(s) from the JSON.
  2. How to import into Final Cut Pro:

- Unzip RoughCut.xml_variants.zip. - In Final Cut Pro: File -> Import -> XML... - Choose the desired .fcpxml variant.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

80.25%
按下载量换算5,918

安全审计

VirusTotal

可疑

ClawScan

通过

Static analysis

未展示

权限和风险

执行命令

安装流程涉及命令执行,可能通过 openclaw skills install roughcut-openclaw 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills