explainer-video
/explainer-video
Zamienia wizualne wyjaśnienie w długi film z narracją, w którym kursor klika strony, a lektor je opisuje.
- Autor
- Prahaladha-Reddy ↗
- Repozytorium
- skills ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 05.11.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 12
- Skrypty
- 8
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 05.11.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
- 8 skryptów w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.
Skrypty: scripts/asr_check.py, scripts/assemble.py, scripts/build_video.py, scripts/judge_check.py, scripts/num_gate_narr.py, scripts/record.js, scripts/tts.py, scripts/validate_v2.py
Co robi i kiedy
Zamienia wizualne wyjaśnienie w długi film z narracją, w którym kursor klika strony, a lektor je opisuje.
Wyzwalacze z opisu
Oryginalny opis (EN)
Turn a visual-explainer site (kit_v4 side-panel pages) into a long narrated walkthrough video for YouTube/LinkedIn - a TTS voice explains while a scripted cursor clicks through the real pages, points at what is new, circles chapters, plays the clips; then voice-checks every line, records in parallel, assembles, joins, and writes YouTube chapters. Use when someone wants "a video of the explainer", "narrate the site", "walkthrough video", or to re-record/fix part of such a video.
Jak działa
- Pipeline (scripts/ in this folder; copy them next to the site)
- Plan format (one file per part; see references/example.json)
- Writing the narration (the part that matters most)
- Voice
- Running it on a laptop without freezing the chat
- Delivery
Podgląd SKILL.md
---
name: explainer-video
description: Turn a visual-explainer site (kit_v4 side-panel pages) into a long narrated walkthrough video for YouTube/LinkedIn - a TTS voice explains while a scripted cursor clicks through the real pages, points at what is new, circles chapters, plays the clips; then voice-checks every line, records in parallel, assembles, joins, and writes YouTube chapters. Use when someone wants "a video of the explainer", "narrate the site", "walkthrough video", or to re-record/fix part of such a video.
---
# Explainer video: a person walking through the site
The site already has the drawings; the video adds a voice and a hand. What the first viewer liked: "it feels
like a human is explaining step by step... clicking next... not just reading what's on the screen".
What they hated, in order: AI-sounding wording, robotic one-fragment-per-call delivery, dead screens.
## Pipeline (scripts/ in this folder; copy them next to the site)
```
plans/*.json ──► build_video.py ──► TTS (tts.py, any HTTP TTS, resumable, re-renders only changed text)
├► voice check: asr_check.py (Deepgram nova-3 via OpenRouter)
│ → judge_check.py (Gemini 2.5 Pro hears clip + script) on flagged only
│ → re-render judge-confirmed bad lines, up to 2 rounds
├► record.js per part, 3 in parallel (Playwright CDP screencast, 30 fps,
│ 1440x810 @ DSF 4/3 = 1920x1080, drawn cursor, presenter marks)
├► assemble.py (frames + every clip placed at its recorded time, H.264 crf18)
└► concat → <name>_full.mp4 + chapters.txt (one line per page, part letter)
```
`python3 -u build_video.py [--segments A,T] [--skip-voice] [--concat-only] [--par 3]`.
Set `PW=<path to a global playwright install>` (bare `npm root -g` can hang for minutes), plus
`TTS_ENDPOINT`, `TTS_API_KEY`, `TTS_MODEL`, `TTS_VOICE` and `OPENROUTER_API_KEY` (voice check).
## Plan format (one file per part; see references/example_*.json)
| beat | what it does |
|---|---|
| `{"go":"pageId","step":1,"wait":0.9}` | jump to a page/step |
| `{"say":"ID","text":"...","point":"halo"}` | speak; cursor glides to the current step's halo, drifts while talking |
| `{"next":1}` | click the panel's Next button like a person |
| `{"play":{"sel":...,"file":"a/x.mp3","dur":7.4}}` | click a play button; the clip is mixed into the audio |
| `{"click":"sel"}` / `{"pause":0.6}` | click anything / wait |
| `{"say":...,"nowait":true}` + `{"sync":1}` | keep moving while a line plays; wait for it before the next |
| `{"hover":"sel","hold":1.4,"circle":true,"big":true,"noring":true}` | glide to an element and loop the cursor around it (`big` = around a whole group) |
| `{"sweep":"sel","hold":3}` | underline-sweep a title or a line of text |
Red hand-drawn presenter rings appear on `point`, only around SMALL targets (< 45 % of the screen).
Never ring a whole title or a big block. For a tour of cards, use the cursor `circle`, not rings.
## Writing the narration (the part that matters most)
Read `references/narration_rewrite_brief.md`. The short version:
- **Whole thoughts per call, 12-48 words, 1-3 sentences.** Splitting a sentence across calls gives
every fragment a falling end-of-sentence tone: that, not the voice, made it sound robotic. The old
28-word cap in the validator caused it.
- **Sound like an engineer at your shoulder:** contractions, name things by colour/position on screen,
mixed sentence lengths. Cut: self-answered questions ("So what is X? X is..."), "Here's the thing",
"Let's dive in", "X, not Y" slogans, tricolons, recap lines, hype words, dramatic fragments, many
lines starting with So/Now/Okay. `validate_v2.py <old> <new>` enforces structure, numbers and slop.
- **Every line must match what is on screen at that moment.** In the intro especially: the voice and
the cursor tell the same story (title sweep -> chapter cards circled -> Start).
- **Intro:** no "Hi". Get moving in the first second. A shape that worked: "we're going to learn how X
works from scratch -> we split it into N chapters (scroll the chapter cards, one big circle around
all of them) -> the explainer is a public website, link in the description -> let's start".
- Same secrecy rules as the site: no internal model names, no product/version names, no internal
numbers. Put them in `gate_names.txt` / `gate_numbers_spoken.txt` (never commit them);
`num_gate_narr.py plans/*.json` must print 0.
- A subagent rewrite brief must ban ONLY what the owner named (banning the word "billion" made agents
write "seventeen hundred and twenty million").
## Voice
Let the owner pick the voice by ear: render the same two short passages (one idea, one with numbers) with
every voice the provider offers, on one listening page, plus a before/after of old vs new wording in one
voice. Spoken numbers are written in words; spell letter names ("D i T"). Deepgram writes "nine sixty"
for "nine hundred and sixty": the checker drops "hundred"/"and" before matching, and only the audio judge
can fail a line. A whole provider voice family returning `502 model_unavailable` instantly is a server
that is down, not a cold start: report it and move on.
## Running it on a laptop without freezing the chat
- Run long renders in `screen -dmS name bash script.sh`, never as a Claude background task (a session
restart killed every recorder and left a half-written MP4). `screen -X quit` can orphan the script:
check `ps` and kill the old tree by PID before starting a replacement.
- Recorders write ~30 JPEG/s. Keep the build dir out of VS Code's watcher and git
(`.git/info/exclude` + `files.watcherExclude`) or VS Code pins 97 % CPU and the Claude panel freezes.
- One silent trigger (`until grep -q DONE log; do sleep 60; done` in the background), not a streaming
monitor. `renice` heavy workers.
- After any interruption, validate outputs with `ffprobe` (a killed writer leaves a file with no moov).
## Delivery
- Size: mostly-static 1080p30 at crf 18 is ~3.5 MB/min (1 h 47 min = 378 MB). YouTube needs a
verified account for > 15 min; LinkedIn caps a video at 15 min (split longer parts at a page change).
- `chapters.txt` goes straight into the YouTube description (first line must be 0:00).
- Thumbnail: build it from the site's REAL figures + bold type, rendered as HTML (1280x720, < 2 MB).
Generic AI glow-wave art was rejected as "complete AI slop".
- To fix one part: edit its plan, re-render changed lines, `--segments X --skip-voice`, then
`--concat-only`. Re-check chapter labels (a page with no data-nav shows its id).
Pliki w paczce (12)
- SKILL.md 7 KB
- references/example_intro_plan.json 2 KB
- references/example_page_plan.json 2 KB
- references/narration_rewrite_brief.md 6 KB
- scripts/asr_check.py 3 KB
- scripts/assemble.py 3 KB
- scripts/build_video.py 8 KB
- scripts/judge_check.py 3 KB
- scripts/num_gate_narr.py 1 KB
- scripts/record.js 12 KB
- scripts/tts.py 3 KB
- scripts/validate_v2.py 5 KB
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · Prahaladha-Reddy/skills | 100 | MIT |
| smykla-skalski/sai | 100 | MIT |
| fengchen122123-sudo/xingyao-y-code | 100 | MIT |
| menschenkreis/explainer-video | 100 | MIT |
| 0xsline/OpenChatCut | 100 | AGPL-3.0 |
| shocklab/co-scientist-toolkit | 100 | MIT |
| Andyyesiyu/explainer-video-skill | 100 | MIT |
| mys1erious/skills | 100 | MIT |
| baskb/explainer-video | 100 | MIT |
Migawka bazy z 13.11.2026 · wersja paczki fcaba5d7b73a (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100walkthrough-video
Tworzy nagrany film demo aplikacji webowej: Playwright klika, lokalny lektor czyta skrypt, FFmpeg dodaje napisy i MP4. - 100walkthrough-video
Tworzy narracyjne filmy instruktażowe o produkcie w MP4: skrypt, lektor AI, zrzuty ekranu, podkreślenia i napisy. - 93narrated-video
Tworzy animowane filmy objaśniające z lektorem: scenariusz, głos z lokalnego TTS, synchronizację scen i render MP4. - 95v1-explainer-video
Tworzy animowane wideo wyjaśniające z narracją, np. objaśniające pull request albo trudną koncepcję. - 100video-chapters-youtube
Zamienia rozdziały MP4 na linie rozdziałów do opisu filmu w YouTube, z zasadami minimalnej długości każdego fragmentu. - 100html-explainer-video
Zamienia produkt lub pomysł w minutowy film wyjaśniający: scenariusz, lektor, sceny w HTML, montaż z napisami i muzyką.