Index of every page on this site: llms.txt
All skills
dtsola avatar

/video-podcast-maker

@e86893e
by dtsoladtsola/xiaoyaosearch1k stars
54
Run it yourself

Use when the user gives a topic and wants an automated video podcast created, or asks to learn visual design patterns from a reference video/image. Produces 4K video via research → script → TTS → Remotion → MP4 + BGM.

Use this Skill: https://skilld.dev/gh/dtsola/xiaoyaosearch/video-podcast-maker

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencesworkflow-steps.md

≈636 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Video Podcast Maker — Workflow Steps Index

When to load: Whenever you need to locate a specific step. This file is only an index — load the phase file that contains the step you need.

The 15-step workflow (plus an optional Step 4.5 pronunciation pre-flight) is split across three phase files. Load just the phase you need — avoid pulling all three unless doing a full top-to-bottom pass.


Phase 1 — Scripting

Pre-workflow (design reference) → Startup (load preferences) → Steps 1-4 (topic, research, sections, narration script).

→ workflow-script.md

Step What it covers
Pre-workflow Optional design pattern extraction from reference video/image
Startup Load user_prefs.json + version migration
Step 1 Define topic direction (audience, style, tone, duration)
Step 2 Research topic (web search/fetch)
Step 3 Design 5-7 sections + content density tier
Step 4 Write narration script (podcast.txt) + duration dry-run

Phase 2 — Production

Steps 5-11 (media → publish draft → thumbnail → TTS → Remotion composition → 4K render → BGM).

→ workflow-production.md

Step What it covers
Step 5 Collect media assets (optional, text-only by default)
Step 6 Generate publish info (part 1 — title/tags/description)
Step 7 Generate video thumbnail (16:9 + 4:3, Remotion or AI)
Step 8 Generate TTS audio (generate_tts.py → wav/srt/timing.json)
Step 9 Create Remotion composition + Studio preview (mandatory stop)
Step 10 Render 4K video (output.mp4)
Step 11 Mix with background music (video_with_bgm.mp4)

Phase 3 — Publish

Steps 12-15 (subtitles → publish info part 2 → verify + cleanup → optional shorts).

→ workflow-publish.md

Step What it covers
Step 12 Add subtitles (usually skipped — Remotion renders natively)
Step 13 Complete publish info (part 2 — chapters, platform-specific format)
Step 14 Verify output + cleanup (final_video.mp4)
Step 15 Generate vertical shorts (optional, generate_shorts.py)

Related references

  • design-guide.md — Visual design rules, component selection, typography, icons. Required reading before Step 9.
  • troubleshooting.md — Errors, BGM options, preference commands, design-learning issues.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

2 warnings4mo3 checks · Risk SAFE
  • Gen Agent Trust Hub4mo

    The skill is an automated video podcast creation pipeline that handles research, scriptwriting, audio synthesis, and video rendering. It uses industry-standard tools like FFmpeg and Remotion, and integrates with well-known cloud services (Azure, OpenAI, Google, etc.) for Text-to-Speech synthesis. Its operations, including media processing and update checks, are consistent with its functional purpose as a developer-oriented automation tool.

  • Socket4mo

    1 alert: gptAnomaly

  • Snyk4mo

    Risk: MEDIUM · 2 issues

Signed by skilld at e86893e. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 7 months ago
argument-hint
[topic]
effort
high
author
Agents365-ai
Other metadata
category
Content Creation
version
2.0.0
created
2025-01-27
updated
2026-04-03
bilibili
https://space.bilibili.com/441831884
github
https://github.com/Agents365-ai/video-podcast-maker
dependencies
[
  "remotion-best-practices"
]
metadata
{
  "openclaw": {
    "requires": {
      "bins": [
        "python3",
        "ffmpeg",
        "node",
        "npx"
      ]
    },
    "primaryEnv": "AZURE_SPEECH_KEY",
    "emoji": "🎬",
    "homepage": "https://github.com/Agents365-ai/video-podcast-maker",
    "os": [
      "macos",
      "linux"
    ],
    "install": [
      {
        "kind": "brew",
        "formula": "ffmpeg",
        "bins": [
          "ffmpeg"
        ]
      },
      {
        "kind": "uv",
        "package": "edge-tts",
        "bins": [
          "edge-tts"
        ]
      }
    ]
  }
}

README badge

README badge for dtsola/xiaoyaosearch/video-podcast-maker