Get the FREE Ultimate OpenClaw Setup Guide →

mixcut

Scanned
npx machina-cli add skill garroshub/MixCut-Skill/MixCut-Skill --openclaw
Files (1)
SKILL.md
4.3 KB

MixCut Skill

CRITICAL INSTRUCTION: MANDATORY CONFIGURATION

You MUST NOT proceed to downloading or processing until the Project Configuration is fully defined.

Step 1: The Configuration Gate Check if the user has provided ALL of the following:

  • Video Title: Main title for intro and segment cards.
  • Caption Language: Target language for subtitles (e.g., English, etc.). Crucial: No bilingual output.
  • Aspect Ratio: 16:9 (Desktop), 9:16 (Shorts/TikTok), or 1:1.
  • Target Duration: 30s, 60s, 120s, or 180s.
  • Pace: Fast, Medium, or Slow.
  • Style: Highlight Montage or Beat-cut.
  • Transitions: none, fade, slide, flash, or glitch.

If ANY of these are missing, you MUST use the AskUserQuestion tool to obtain them. DO NOT assume defaults. DO NOT start downloading until configuration is complete.

Workflow

Phase 1: Sources & Workspace Setup

  1. Gather Sources: Ask for YouTube URLs from the user.
  2. Setup Workspace:
    • Ensure the directory ./work exists in the project root.
    • Prepare ./work/assets and ./work/outputs subdirectories.

Phase 2: Content Analysis

For each YouTube URL provided:

  1. Download:
    • Run python skills/Youtube-clipper-skill/scripts/download_video.py <url> "./work/assets/youtube"
  2. Analyze:
    • Run python skills/Youtube-clipper-skill/scripts/analyze_subtitles.py <subtitle_path>
  3. Selection:
    • Present analyzed chapters/highlights to the user.
    • Confirm which segments to include in the final cut.

Phase 3: Assembly & Processing

  1. Configuration: Create ./work/mixcut_config.json with global settings and source clip metadata (start, end, title).
  2. Processing:
    • Run python skills/mixcut/scripts/process_mixcut.py "./work/mixcut_config.json"
    • This script automates clipping, media normalization (ffmpeg), and generates the initial timeline.json and final.srt.

Phase 4: Professional Subtitle Cleaning (Agent-Driven)

This phase ensures high-quality, professional subtitles.

  1. Read Timeline: Access ./work/timeline.json.
  2. Subtitle Optimization: Iterate through all subtitle entries and apply the following cleaning logic:
    • Remove Noise: Strip speaker markers (e.g., >>, >>>) and sound cues (e.g., [Music], [Applause]).
    • Deduplication: Remove repeated words, stutters, and verbal fillers ("uh", "um", "you know").
    • Flow Improvement: Merge fragmented phrases into natural, readable sentences.
    • Professional Polish: Refine text into the target language using appropriate technical terminology.
  3. Update: Save the optimized content back to ./work/timeline.json.
  4. Synchronize: Run python skills/mixcut/scripts/process_mixcut.py "./work/mixcut_config.json" --action generate_srt to sync changes to final.srt.

Phase 5: Rendering

  1. Delegate to Remotion:
    • Use the remotion skill to render the project located in skills/mixcut/remotion.
    • Provide the absolute path to ./work/timeline.json as input props.
    • Set output to ./work/outputs/final_mixcut.mp4.

Phase 6: Delivery Guard & Verification

Mandatory verification before completion.

  1. Integrity Check:
    • Verify ./work/outputs/final_mixcut.mp4 exists and has a file size > 0.
    • Verify ./work/outputs/final.srt exists and has a file size > 0.
  2. Troubleshooting: If files are missing or empty, identify the failure point in previous phases and re-run the necessary steps.

Phase 7: Completion & Cleanup

  1. Report: Provide the paths to the final video and subtitle files.
  2. Retention Policy: Do NOT delete the ./work directory until the user explicitly confirms the results or you have verified the outputs physically.

Technical Guidelines

  • Path Management: Always use absolute paths when delegating tasks to external skills.
  • Cross-Platform: Avoid hardcoding drive letters; use system-agnostic path resolution.
  • Performance: Use parallel tool calls for independent download/analysis tasks where supported.

Source

git clone https://github.com/garroshub/MixCut-Skill/blob/main/SKILL.mdView on GitHub

Overview

MixCut is a guided, phase-driven workflow that ingests YouTube clips, analyzes highlights, clips segments, and produces a publish-ready 30–180s video with polished subtitles. You provide a project configuration and YouTube sources; the skill handles workspace setup, automated analysis, clipping, subtitle cleaning, rendering, and delivery verification.

How This Skill Works

MixCut operates in clearly defined phases. First, you must complete the Project Configuration Gate; if any required field is missing, the system uses AskUserQuestion to collect it. Once configured, it creates a work area at ./work, downloads sources via the Youtube-clipper-skill, analyzes subtitles, and presents highlight segments for selection. It then writes ./work/mixcut_config.json with global settings and per-source metadata, runs process_mixcut.py to generate timeline.json and final.srt, and applies a professional subtitle-cleaning pass. The project is rendered via Remotion from skills/mixcut/remotion using the absolute path to ./work/timeline.json as input props, producing ./work/outputs/final_mixcut.mp4. A mandatory integrity check validates both final_mixcut.mp4 and final.srt exist with non-zero sizes. The work directory is retained until you explicitly confirm results or verification passes. All file and path handling uses absolute paths to ensure cross-platform compatibility.

When to Use It

  • You are creating social-media shorts (e.g., 9:16) from long YouTube videos and want a quick, polished result with accurate captions.
  • You need a multi-source recap or highlights reel (30–180s) from several YouTube clips with consistent subtitle language and branding.
  • You require professional, cleaned subtitles in a single target language (no bilingual output) and a timeline-driven render output.
  • You are preparing educational micro-lectures or product demos that demand precise segment selection and reliable playback-ready timelines.

Quick Start

  1. Provide the mandatory project configuration fields (Video Title, Caption Language, Aspect Ratio, Target Duration, Pace, Style, Transitions) via AskUserQuestion if any are missing.
  2. Supply one or more YouTube URLs as sources; the workflow will create ./work and subfolders automatically.
  3. Review analyzed chapters/highlights, confirm which segments to include, and then allow the system to generate ./work/mixcut_config.json and run process_mixcut.py to create timeline.json and final.srt.
  4. Render the project via Remotion and verify the final outputs in ./work/outputs.

Best Practices

  • Fully specify all configuration fields before proceeding to avoid repeated prompts (Video Title, Caption Language, Aspect Ratio, Target Duration, Pace, Style, Transitions).
  • Choose Aspect Ratio that matches your target platform (16:9 for desktop, 9:16 for Shorts/TikTok, 1:1 for certain feeds) and pick a pace that suits your audience (Fast for promo, Slow for educational content).
  • Keep a single caption language to comply with non-bilingual output; use the target language terminology consistent with your field.
  • Predefine source segments with clear start and end times in the mixcut_config.json to streamline processing and reduce re-clip rendering.
  • Audit the generated timeline.json and final.srt for alignment and readability, then perform the subtitle cleaning step to remove noise, deduplicate, and improve flow.
  • Test renders with a small subset of sources first to verify transitions, pacing, and subtitle timing before full-scale rendering.

Example Use Cases

  • Educational recap: a 60s beat-cut montage (9:16) from three YouTube tech talks with English subtitles, aimed at quick learner briefings.
  • Product teaser: a 30s 16:9 highlight reel compiled from five review clips, using fade transitions and tightly synced captions to showcase features.
  • Speaker interview highlight: a 90s montage (16:9) from a long interview, with cleaned English subtitles and smooth sentence flow for social posting.
  • Panel highlights: a 180s montage (16:9) from a conference session, combining top moments with professional, concise subtitles in English.
  • Tech-brief: a 60s educational clip created from developer talks, with domain-specific terminology in the subtitles and a focus on clear, actionable takeaways.

Frequently Asked Questions

Add this skill to your agents
Sponsor this space

Reach thousands of developers ↗