sugatoray/aiskills

dynamic-promo-video

Build a short narrated promo/intro video (HTML scenes, zoom/tilt, voiceover, music) for a library, app or product.

ソースを見る

使い方

  1. インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
  2. 必要なツール、認証情報、対応環境を原文で確認します。
  3. 入力と成果物を指定し、出力を資料と照合します。
npx skills add https://github.com/sugatoray/aiskills --skill dynamic-promo-video

開始前の確認

  • 導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
  • スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。
リポジトリの原文

見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。

Dynamic promo video (HTML scenes + voiceover + music)

Produces a 1280x720, ~25-45s MP4: animated scenes in one HTML page, rendered frame by frame with Playwright, encoded with ffmpeg, narrated with a TTS voice (e.g. ElevenLabs), with ducked background music.

SKILL_DIR below means this skill's folder. Only the template is copied into the work folder; the scripts run from SKILL_DIR/scripts/ (each has --help). Needs Node + Playwright/Chromium (preinstalled in cloud sessions; do not reinstall), ffmpeg/ffprobe, Python 3 with numpy.

StepUse
Scenesassets/template/index.html · details: references/scene-engine.md
Real page screenshotsreferences/screenshots.md
Voiceoverreferences/voiceover.md · scripts/tts_elevenlabs.py, scripts/timing.py
Render + encodescripts/render.js
Music, mixscripts/music.py, scripts/mix.py · references/music-and-mix.md
Checkscripts/verify.py

Inputs

FlagMeaning
--demo, --demo=defaultBuild the default demo instead of a real project: a placeholder video, then how to make one with this skill; see Demo below.
--demo=selfBuild the self demo: the skill explaining itself (what it is, how it works, install, use).
--voiceNarrate with the default ElevenLabs voice TABZn6CDfjMNGrsnGzzD.
--voice-elevenlabs=<voice-id>Narrate with that ElevenLabs voice. A bare --voice-elevenlabs = --voice.
  • Narration uses ElevenLabs only if one route is available, checked in this order:
  1. the ElevenLabs MCP connector (its creative_generate_speech tool can be loaded with ToolSearch), or
  2. an API key: ELEVENLABS_API_KEY is set, or the session's network secrets hold one for api.elevenlabs.io (then run scripts/tts_elevenlabs.py).
  • Real project, no voice flag: narrate with the default voice if a route exists, else music only.
  • --demo (any variant) without a voice flag: music only. With --voice (or the default voice id), use the variant's bundled clips: no ElevenLabs route is needed and no credits are spent.
  • A voice flag was given but no route exists: say so, offer to connect the connector, add a key or attach clips; do not silently drop the voice. Never invent a voice id and never fake narration.
  • A voice the user names in words is looked up with the connector's voice list; otherwise use the id as given.

Demo (--demo[=default|self])

No research, storyboard or editing. Each variant lives in assets/demo/<variant>/: index.html, narration.txt (one line per scene, - = none) and clips.json, which maps each scene to its approved recording in the shared assets/demo/clips/ (default voice).

  • default (48s): scenes 1-6 are the generic template, a placeholder for the viewer's own video; scenes 7-9 show how to make one: a bridge ("that was a placeholder"), the three install routes from sugatoray/aiskills, get started (music only). The cover is tagged "Demo of Skill /dynamic-promo-video · sugatoray/aiskills".
  • self (32s): the skill explaining itself: cover, the problem, the scene engine's code, the three install routes, usage, get started.
RequestRun
--demo / --demo=defaultpython3 SKILL_DIR/scripts/demo.py (music only)
--demo=selfpython3 SKILL_DIR/scripts/demo.py --variant self
add --voice (or the default voice id)add --voice: the bundled clips, no ElevenLabs route needed, no credits
add --voice-elevenlabs=<other id>, API keyadd --voice-id <id> (generates the clips)
add --voice-elevenlabs=<other id>, MCP connectorgenerate one clip per non-- line of the variant's narration.txt (see references/voiceover.md), save as clips/vo<scene>.mp3, add --clips-dir clips/

With --voice the result is identical every run (same frames, same audio). Output: promo-demo/demo_final.mp4 and thumbnail.png, checked; deliver as in step 5. The skill icons are simplified drawings.

0. Before building

  • Research the subject first: README, package page, marketplace listing, install commands. Use real names, commands and versions. Do not invent features.
  • Use the project's real branding (banner, icon, colors, fonts) and real screenshots from its docs where possible. Check the repo for docs images before drawing anything.
  • Sandbox network is allowlisted: npm registry, marketplace and github.com web pages are usually blocked from the shell. Git clone of a public repo often works (use the add_repo tool, then clone). If the repo's own CLAUDE.md says to read docs first and the task is not editing the repo, say you are skipping them.
  • Make a task list. Last task: check frames and audio, then deliver.

1. Storyboard (write the narration first)

Typical 6 scenes: (1) cover/title, (2) the problem, (3) the product in action, (4) install commands, (5) editor/extension usage, (6) end card with commands and links. The template has exactly these. Write one narration line per scene (about 2.5-3 words per second). Scene length is set by the narration, not the other way round.

2. Build the scenes

Copy SKILL_DIR/assets/template/index.html into the work folder and edit it: brand CSS variables, scene text, real screenshots, camera keyframes. Rules that matter most:

  • Everything is a function of t through window.setT(t); no CSS animation, no timers.
  • Frame 0 is a finished cover (social platforms use it as the preview). Scene 1 only fades out.
  • Icons are simplified drawings, not official logos; say so unless official files are supplied.
  • Do not reuse a class name a script queries with querySelectorAll.

3. Preview, then voice, then retime

bash
node SKILL_DIR/scripts/render.js index.html --preview 0,6,12,17,23,29 --thumbnail thumbnail.png

Look at the preview frames before going on. Then produce the voice clips with the voice from Inputs (details in references/voiceover.md; one generation per scene, never re-run a paid generation). With an API key:

bash
python3 SKILL_DIR/scripts/tts_elevenlabs.py --script narration.txt --voice <voice-id> --dry-run   # check the plan first
python3 SKILL_DIR/scripts/tts_elevenlabs.py --script narration.txt --voice <voice-id>

With the MCP connector, call creative_generate_speech once per scene with that voice_id. A scene with no narration gets the line - (no clip; pass - to timing.py). If the voice says a name wrong, write it the way it sounds, test the name alone (about 15 credits) and splice the approved sample into the clip instead of regenerating the line (references/voiceover.md). Then retime:

bash
python3 SKILL_DIR/scripts/timing.py --authored 0,4,9,15,21,26,31 --clips vo0.mp3 vo1.mp3 vo2.mp3 vo3.mp3 vo4.mp3 vo5.mp3

Add --write-html index.html to write the new const NB = [...] into the page (or paste the printed line). Scenes stretch to fit; the voice is never sped up.

4. Render, music, mix

bash
node SKILL_DIR/scripts/render.js index.html --encode promo_silent.mp4
python3 SKILL_DIR/scripts/music.py --style energetic --duration <total> --out music.wav
python3 SKILL_DIR/scripts/mix.py --video promo_silent.mp4 --music music.wav --voice 0.3:vo0.mp3 ... --out promo_final.mp4

Use a licensed track instead of music.py when the user supplies one; if synthesized, say it is simple and synthesized. Copy the --voice arguments from timing.py's output. If only visuals change later, re-render and run mix.py --audio-from <previous final>.

5. Verify and deliver

bash
python3 SKILL_DIR/scripts/verify.py promo_final.mp4 --frames <one time per scene>
  • It must report both streams with near-equal durations; read the per-second dB line (voice present, music dipping under it).
  • Look at frame 0, one frame per scene and the last frame in check/. Confirm no overlaps or clipped text.
  • Say clearly which file has sound: keep the _silent / _final names.
  • Send with SendUserFile (display render), plus thumbnail.png. Summarize in a few lines: what each scene shows, what is real vs. drawn, and what you could not verify (you have not listened to the audio).
  • Offer a LinkedIn/social post note only if asked; keep claims to what the README documents (for example "early development").
同じリポジトリから

関連する Skills

すべての Skills
sugatoray
コミュニティ

create-lib-docs

Writes top-grade, verified user documentation for a library, CLI or framework as a folder of Markdown pages plus SVG diagrams, structured the way FastAPI, Pydantic, DuckDB and Effect structure theirs: a landing page with a 30-second example, Getting Started, a progressive Tutorial with runnable steps, task-oriented How-to Guides, Concepts (explanations with diagrams), an exhaustive Reference (CLI flags, API, config, output schemas, one anchor per error with cause and fix), FAQ/troubleshooting, a

1時間の導入数
2
GitHub Stars
4
更新日
11月18日
sugatoray
コミュニティ

meeting-agenda

Turn a meeting agenda into a self-contained HTML slide deck with a countdown timer per item: one slide per item (large 01, 02… number, title, optional sub-points), a ring timer that turns amber in the last 20% and red with a +M:SS count-up past zero, a footer with clickable progress dots and a per-item meeting progress bar, and a built-in editor (gear button) that saves to localStorage or downloads an updated copy. Use when the user invokes /meeting-agenda, or asks for agenda slides, a timed age

1時間の導入数
2
GitHub Stars
4
更新日
11月18日
sugatoray
コミュニティ

scrolls-compact

Compacts the history in a docs/.scrolls/ (or docs/scrolls/) project-memory system at a point in time, and saves a git checkpoint of everything it condenses. Condenses the parts of SPEC.md, PLAN.md, HANDOFF.md, GAPANALYSIS.md and GAPCONTEXT.md that git blame shows are older than a compaction base — by default the newer of 7 days ago and the 20th-latest first-parent commit on main/master — while open tickets, open gaps and HANDOFF's open threads always stay word for word. Records ONE commit whose

1時間の導入数
2
GitHub Stars
4
更新日
11月18日
sugatoray
コミュニティ

scrolls-explainer

Shows, copies or rebuilds scrolls-explainer.html: an interactive, offline page that explains how the scrolls skill family works (/scrolls-setup, /scrolls-update, /scrolls-hide, /scrolls-unhide, /scrolls-remove, /scrolls-restore, /scrolls-help) — one tab per command that animates, step by step, what the command does to docs/.scrolls/, SCROLLS.md, CLAUDE.md, AGENTS.md and git, with a callout explaining each step, a tab for how a new agent session reads the memory, and full keyboard navigation (arr

1時間の導入数
2
GitHub Stars
4
更新日
11月18日