Video Podcast Maker

REQUIRED: Load Remotion Best Practices First

This skill depends on remotion-best-practices. You MUST invoke it before proceeding:

Invoke the skill/tool named: remotion-best-practices

Video Podcast Maker

Automated pipeline for 4K Bilibili horizontal knowledge videos from a topic. Coding agent + TTS backend + Remotion + FFmpeg.

Contents

• Bootstrap — update check + prerequisites (run before Step 1)
• Execution Modes — Auto vs Interactive, default decisions
• Regenerating an Existing Video — reuse videos/{name}/ to iterate on a finished video
• Workflow — the 15 steps + phase-file pointers + mandatory stops
• Hard Rules — non-negotiable production constraints + output specs
• Per-Video Layout — directory structure, --public-dir, naming
• Additional Resources — when to load each references/ file
• User Preferences
• Troubleshooting

---

Bootstrap

Resolve SKILL_DIR to the directory containing this SKILL.md. If your agent exposes a built-in skill directory variable (e.g. ${CLAUDE_SKILL_DIR}), map it to SKILL_DIR.

SKILL_DIR="${SKILL_DIR:-${CLAUDE_SKILL_DIR}}"

# 1. Update check (notify-only, throttled to 24h)
"${SKILL_DIR}/scripts/check_update.sh"

# 2. Prerequisites (CLIs + backend env vars)
python3 "${SKILL_DIR}/scripts/check_prereqs.py"

check_update.sh output:

• UPDATE_AVAILABLE vX.Y.Z -> vA.B.C — tell the user the version delta and ask before running git -C "${SKILL_DIR}" pull --ff-only. Notify-only by design — never pull without consent (the skill directory belongs to the user).
• UP_TO_DATE / SKIPPED_RECENT_CHECK / MANUAL_INSTALL — continue silently.

Prereqs failures — see README.md for setup. The check is backend-aware (resolves TTS_BACKEND env → user_prefs.json global.tts.backend → edge default), so only env vars required by the active backend are validated.

Design Learning shortcut: If the user provides a reference video/image or asks to save/list/delete style profiles, see references/design-learning.md instead of running the workflow below.

---

Execution Modes

Detect at workflow start:

• "Make a video about..." / no special instructions → Auto Mode (default)
• "I want to control each step" / "interactive" → Interactive Mode

Auto Mode defaults

Full pipeline with sensible defaults. Mandatory stop at Step 9 (Studio review); Step 10 (4K render) only fires when the user says "render 4K" / "render final".

Override any default in the initial request:

• "make a video about AI, burn subtitles" → auto + subtitles on
• "use dark theme, AI thumbnails" → auto + dark + imagenCN
• "need screenshots" → auto + media collection enabled

Interactive Mode

Prompts at each decision point.

---

Regenerating an Existing Video

If videos/{name}/ already exists and the user is iterating on a finished or in-progress video — "regenerate", "re-render", "rebuild", "I edited the script/prompt", "update the video", "change the BGM" — reuse that directory. Do NOT start a new project or a new videos/{newname}/; that is the Single Project rule applied to iteration, and starting fresh is the most common mistake here.

Pick the smallest re-run for what actually changed. Every command targets the same videos/{name}/, and every Remotion command keeps --public-dir videos/{name}/:

Any re-run that changes what the viewer sees or hears re-enters the Step 9 gate: apply the change, let Studio hot-reload (or relaunch it), and wait for a fresh explicit "render 4K" — the confirmation that started the previous render does not carry over to the adjusted version. Only the audio-untouched post-render steps (BGM mix, subtitles) skip the gate.

A script change shifts every downstream timestamp, so always regenerate timing.json through TTS — never hand-edit it (see Audio-Master Clock). After any re-run, re-verify:

python3 ${SKILL_DIR}/scripts/verify_output.py videos/{name}/

Cleanup only removes TTS temp files, never output.mp4 / video_with_bgm.mp4 — so BGM/subtitle re-runs avoid a full ~8-min re-render.

---

Workflow

Iterating on a finished video? If videos/{name}/ already exists and the user wants to regenerate after a change, do NOT start at Step 1 — see Regenerating an Existing Video for the minimal re-run.

At Step 1 start, create one task per step in your agent's tracker (Claude Code TaskCreate / Codex todo list / equivalent). Mark in_progress on start, completed on finish. Files in videos/{name}/ are the durable record — if interrupted, inspect the directory to determine where to resume.

Mandatory stops (bold rows above):

• Step 9 — Studio review. MUST launch npx remotion studio and wait for user feedback before rendering. NEVER render 4K until the user explicitly confirms ("render 4K" / "render final"). A reply containing adjustment requests is not confirmation — even if it also says "otherwise looks good": apply the changes, let Studio hot-reload, and ask again. Every round of adjustments needs its own fresh confirmation before Step 10.
• Step 14 — verify_output.py. MUST pass before declaring the video done. Exit 0 = green; exit 2 = warnings still publishable. Auto-fixes common omissions (creates final_video.mp4 if missing). For machine-readable output add --format json (auto when piped).

Pre-render audit (recommended) — before Step 9:

python3 ${SKILL_DIR}/scripts/audit_beat_sync.py  

Flags beats that drift > 1.5s from narration. Especially important for kinetic-typography videos.

Validation Checkpoints

---

Hard Rules

Visual minimums (text sizes, content width, safe zones, animation safety) live in references/design-guide.md. MUST load before Step 9.

Audio-Master Clock & Sync

Golden rules

1. Audio is the master clock. Every slide start, subtitle, progress-bar chapter, and animation beat is derived from podcast_audio.wav and podcast_audio.srt.
2. Generate timing from TTS, not from text estimates. The canonical pipeline is:

   podcast.txt (final)
     → generate_tts.py
     → podcast_audio.wav + podcast_audio.srt + timing.json
     → Remotion composition
     → render
   

3. Never hand-write timing.json before audio exists. If you already have curated slides, run align_timing_from_srt.py to anchor them to the real SRT, or add a "section" field to each slide and then run it.
4. Compensate TransitionSeries overlap. TransitionSeries renders sum(section.duration_frames) - (N-1) * transitionFrames frames. To keep the rendered length equal to timing.total_frames, scale every section proportionally; do not stuff all overlap frames into the first section. The corrected pattern is in templates/Video.tsx.

Mandatory sync checkpoints

If any checkpoint fails, stop. Do not publish.

Output Specs

---

Per-Video Layout

project-root/                           # Remotion project root
├── src/remotion/                       # Remotion source (Root.tsx, compositions, index.ts)
├── videos/{video-name}/                # Per-video assets (the agent's working dir)
│   ├── topic_definition.md             # Step 1
│   ├── topic_research.md               # Step 2
│   ├── podcast.txt                     # Step 4: narration script
│   ├── phonemes.json                   # Step 4.5: zh-CN pronunciation overrides
│   ├── podcast_audio.wav               # Step 8: TTS audio
│   ├── podcast_audio.srt               # Step 8: subtitles
│   ├── timing.json                     # Step 8: timeline (drives animations)
│   ├── thumbnail_*.png                 # Step 7
│   ├── output.mp4                      # Step 10: 4K render (no BGM)
│   ├── video_with_bgm.mp4              # Step 11
│   ├── final_video.mp4                 # Step 12: final output
│   └── bgm.mp3                         # Background music
└── remotion.config.ts

--public-dir per video

Remotion commands MUST use --public-dir videos/{name}/ — each video's assets stay in its own directory, no copy to public/. Enables parallel renders.

npx remotion studio src/remotion/index.ts --public-dir videos/{name}/
npx remotion render src/remotion/index.ts CompositionId videos/{name}/output.mp4 --public-dir videos/{name}/ --video-bitrate 16M
npx remotion still src/remotion/index.ts Thumbnail16x9 videos/{name}/thumbnail.png --public-dir videos/{name}/

Naming

• Video name {video-name}: lowercase English, hyphen-separated (e.g. reference-manager-comparison)
• Section name {section}: lowercase English, underscore-separated, matches [SECTION:xxx]
• Thumbnail naming (16:9 AND 4:3 both required):

---

Additional Resources

Load on demand — do NOT load all at once:

Script suite dispatcher

All scripts under ${SKILL_DIR}/scripts/ are reachable through one hierarchical entry point:

python3 ${SKILL_DIR}/scripts/cli.py --help                  # list resources
python3 ${SKILL_DIR}/scripts/cli.py  --help       # list actions
python3 ${SKILL_DIR}/scripts/cli.py   --help    # forwards to underlying script
python3 ${SKILL_DIR}/scripts/cli.py schema []       # JSON parameter schema

Routes: tts run|validate, verify, align, audit beats, shorts gen, design list|show|delete|add, assets init|add|list|validate, prereqs, capabilities, prefs get|migrate|backend|bgm-path, schema []. Direct script invocation (python3 scripts/.py ...) keeps working — the dispatcher is additive.

---

User Preferences

Skill auto-learns and applies preferences. Full commands and learning details: references/troubleshooting.md.

• Storage: user_prefs.json (auto-created from user_prefs.template.json, schema in prefs_schema.json).
• Priority: Root.tsx defaults < global < topic_patterns[type] < current instructions.
• User commands: "show preferences" · "reset preferences" · "save as X default".

---

Troubleshooting

See references/troubleshooting.md on errors, BGM options, preference learning, design-learning issues.