macong0420 GitHub avatar

topic-material-collector

macong0420

An open-source Codex skill that researches, timestamps, downloads, clips, renames, and catalogs video-first materials from YouTube and other sources using subtitles, chapters, yt-dlp, and FFmpeg.

Stars

19

7-day growth

No data

Forks

6

Open issues

0

License

MIT

Last updated

2026-07-14

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It combines automated YouTube research with subtitle-based timestamping and confidence scoring, producing a traceable, license-aware material package ready for editing workflows.

Who it is for

  • Video editors and content creators needing rapid B-roll gathering
  • Scriptwriters and narrators looking for relevant footage clips
  • AI-assisted media production teams using Codex or similar agent environments
  • Media researchers cataloging assets with provenance and rights metadata

Use cases

  • Collecting video clips for a documentary or explainer based on a script or shot list
  • Automatically locating and clipping relevant segments from YouTube using subtitles and chapters
  • Building a searchable, multi-format manifest of candidate videos with confidence levels and reuse-risk labels
  • Fetching reviewed cross-platform candidates after manual curation

Strengths

  • Automated YouTube search with subtitle and chapter analysis for precise timestamping
  • Outputs Markdown, CSV, and JSON manifests that include source URLs, timestamps, rights notes, and reuse-risk levels
  • Supports both Codex skill invocation and standalone CLI scripts
  • Handles cookie and proxy configuration for YouTube access without bypassing DRM or paywalls

Considerations

  • Requires external dependencies (Python 3.10+, yt-dlp, FFmpeg) and a compatible agent environment for full skill functionality
  • Primarily focused on YouTube; cross-platform support is limited to a curated candidate list
  • Does not grant copyright clearance; users must independently verify rights before publication

README quick start

安装 Skill

Description

Open-source Codex skill for researching, timestamping, downloading, clipping, and cataloging video-first materials.

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482