Communitygithub.com

josueh04/product-video-skills

Verifica esta máquina e instala el toolchain de video anclado del banco de trabajo de Product Video Skills (CLI de HyperFrames, su Chrome de renderizado y sus skills de agente de la misma versión, el entorno Python, el modelo de voz para QA), luego ejecuta la autoverificación. Es seguro ejecutarlo de nuevo. `/video-setup check` solo informa.

¿Qué es product-video-skills?

Esta skill automatiza la configuración del banco de trabajo de Product Video Skills, llevándolo desde un clon nuevo hasta el estado 'passed N, failed 0' en un solo paso. La skill ejecuta un script de verificación (`setup.sh --check`) que inspecciona la máquina y el toolchain, reportando estado por línea (ok, warn, FAIL) sin instalar nada. Si hay fallos en herramientas del sistema (Node 22+, Python 3.9+, ffmpeg, git), la skill pide al usuario que los instale manualmente. Luego, si el toolchain necesita componentes (HyperFrames CLI, Chrome, skills de agente, paquetes Python, modelo de voz Whisper), la skill los descarga e instala automáticamente tras confirmación del usuario, manejando cada posible fallo con instrucciones de reparación específicas.

Compatible con✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/josueh04/product-video-skills/tree/HEAD/skills/video-setup

Preguntar en tu IA favorita

Abre un nuevo chat con esta habilidad de agente ya precargada.

Documentación

/video-setup

Obtén el banco de trabajo desde un clon nuevo hasta passed N, failed 0 en un solo paso. setup.sh hace el trabajo; tu labor es explicarlo, obtener un sí, ejecutarlo y convertir cada línea FAIL en su solución.

Primero, encuentra el banco de trabajo (esto funciona desde el banco de trabajo y desde una carpeta de producto):

PVS_HOME="$(cd "$(cd "${CLAUDE_SKILL_DIR}" && pwd -P)/../.." && pwd)"

Habla con el usuario en su idioma. Sé breve: quieren una configuración funcional, no un recorrido.

Con el argumento check

Ejecuta bash "$PVS_HOME/setup.sh" --check y muestra el resultado. No instala nada, no descarga nada y no escribe nada. Para cada línea FAIL, da su solución (la línea termina con ella). Detente ahí.

De lo contrario

1. Reporta la máquina

Ejecuta primero bash "$PVS_HOME/setup.sh" --check. Imprime una línea por elemento: ok, warn o FAIL con la solución exacta.

  • Si una línea bajo Máquina falla (node 22+, python 3.9+, ffmpeg, git), la configuración no puede continuar. Dale al usuario la solución que aparece en la línea (por ejemplo brew install ffmpeg) y pídele que la ejecute en su terminal, luego ejecuta la verificación de nuevo. Instalar paquetes del sistema es decisión del usuario, así que no ejecutes brew ni apt a menos que te lo pidan.
  • Un warn en Claude Code es solo informativo.
  • Las líneas FAIL bajo Toolchain son lo que la configuración instalará. Eso es esperado en la primera ejecución.

2. Di qué se descargará, y pregunta una vez

Dile al usuario, en una lista corta, solo las piezas que la verificación reportó como faltantes:

PiezaTamañoDónde
CLI de HyperFrames en la versión anclada, con sus dependenciasunos 128 MBnode_modules/
La compilación de Chrome con la que renderiza HyperFramesunos 195 MB (omitido si está en caché)la caché de HyperFrames
Skills de agente de HyperFrames desde el mismo tag de versiónunos pocos MBvendor/hyperframes/skills/
Paquetes Python, principalmente torch para voz a textounos 339 MB.venv/
El modelo de voz small.en de whisper que usa el QA484 MB~/.cache/whisper/

Pregunta una pregunta cerrada: "¿Instalar esto ahora? (sí / no)". La configuración debe ocurrir en un solo paso desde el primer /video-setup, así que no la dividas en varias confirmaciones.

3. Ejecútalo

Ante un sí, ejecuta bash "$PVS_HOME/setup.sh" --yes (el --yes es la respuesta del usuario, ya dada). Tarda unos minutos en la primera ejecución y segundos cuando todo está en caché; usa un tiempo de espera de al menos 10 minutos. Es idempotente: ejecutarlo de nuevo solo rehace lo que falta.

4. Maneja cada FAIL

Cada línea FAIL nombra su solución. Las comunes:

FAILQué hacer
npm install failedProblema de red o registro. Muestra las últimas líneas del registro que nombra, luego ejecuta la configuración de nuevo
hyperframes browser ensure failedEjecuta npx hyperframes browser ensure --force desde el banco de trabajo, luego la configuración de nuevo
could not clone heygen-com/hyperframesProblema de red o acceso a GitHub. Verifica git ls-remote https://github.com/heygen-com/hyperframes, luego la configuración de nuevo
python3 -m venv failedEn Debian o Ubuntu: sudo apt install python3-venv (el usuario lo ejecuta)
pip install -r requirements.txt failedMuestra el final del registro. Un Python más nuevo que las versiones ancladas puede necesitar una rueda más reciente; infórmalo en lugar de editar los anclajes
hyperframes doctor: ...La línea nombra la verificación que falla y su solución. Las comprobaciones de versión, Docker y las opcionales de voz local y música se ignoran intencionadamente
tests/run.sh: passed N, failed MEjecuta bash "$PVS_HOME/tests/run.sh" y muestra las pruebas que fallan con su salida

Nunca "arregles" un FAIL ejecutando hyperframes upgrade o hyperframes skills update. El banco de trabajo ancla una versión de HyperFrames y toma sus skills del mismo tag, porque un CLI y skills de diferentes versiones no se ponen de acuerdo sobre el contrato de composición. Un cambio de versión es un pull request que pase tests/run.sh. El hook de guardia bloquea ambos comandos de todos modos.

5. La clave de voz

La configuración crea .env a partir de .env.example y te dice si la clave de ElevenLabs está establecida, sin imprimirla. Si está vacía, dile al usuario:

  • Abre .env (en la carpeta del banco de trabajo) en su propio editor y pega la clave después de ELEVENLABS_API_KEY=. Nunca en el chat: cualquier cosa en el chat se almacena en la transcripción. Si la pegan aquí de todos modos, diles que la roten.
  • Sin clave, voice.provider: say en el product.yaml de un producto usa las voces gratuitas de macOS, suficientemente buenas para borradores y pruebas.

Nunca abras, leas ni imprimas .env tú mismo. La configuración lo niega y el hook de guardia lo bloquea, y los scripts cargan la clave a través de lib/pvs.py por su cuenta.

6. Cierre

Confirma que las últimas líneas de la salida digan passed N, failed 0 y Setup done. Luego da el siguiente paso en una línea: /product-new <slug> para traer su producto, o /video-ask para ver cómo están las cosas.

Individual skills in this repo

This repo contains 14 individual skills — each has its own dedicated page.

josueh04/product-video-skills

Extract, once per product, everything every video of it reuses and write it to kit/ and product.yaml (design tokens, font subsets as woff2, icon subsets as SVG from the product's own icon packages, logos in light, dark and app-tile variants from the repo, a fictional cast proposed once for veto and then frozen, the canonical-names map, pronunciations, banned terms and the read-only tool list). Use it when a product is set up or its kit is missing or incomplete, when a video needs an icon, font or logo that is not in kit/ yet, when someone asks for demo names, fake customers, phone numbers or emails, when a brand word is mispronounced or an old product name shows up, and when checking that demo data is fictional.

josueh04/product-video-skills

Interview the user about a product, then create products/<slug>/ with its own git history, a filled product.yaml and linked skills, fetch its sources and build its kit. Run only when the user types /product-new.

josueh04/product-video-skills

Back every sentence of a video's narration (audio/lines.tsv) and every screen it shows with a citation into the pinned source code (role/path:line@sha) or a docs URL, mark what is visible in the UI versus backend-only, flag restricted or unreleased features, and cut or rewrite anything unbacked; writes the video's TRUTH.md and checks it with truth_check.py. Use it whenever a script or narration is drafted or edited, before voice is generated, before a build, when someone asks "can we say this?", "is this true?", "does the product really do X?", when a reviewer asks for a feature or a claim the product may not support, and when a source document (pitch deck, PRD, marketing page) makes claims the video wants to repeat.

josueh04/product-video-skills

Check a rendered product video before anyone else sees it: worker-pattern flicker, black frames, loudness and true peak, clipping, clicks at clip edges, overlapping narration, speech to text against the script, banned terms and legacy names, camera zoom, contact sheets, frame strips at transitions and parity against the approved version; then write qa/REPORT.json, the only thing deliver.py accepts. Use it after every HyperFrames render, whenever someone asks "is the render clean", "QA this", "check the video", "check the audio", "why does it flicker", "there is a click", "compare v3 with v2", "did the approved part change", or before showing, sending, uploading or delivering any MP4, even when the request does not say QA. Also use it to triage a defect a reviewer reported in a render.

josueh04/product-video-skills

Write a product video's narration and turn it into voice clips with word timings, pronunciation fixes, sound effects and even loudness. The script becomes a table of moments and then audio/lines.tsv (one clip per sentence, with role and speed columns); tts.py voices it with ElevenLabs or the free macOS say voice, maps brand respellings back to the on-screen spelling, normalizes every clip and writes audio/timings.json for the composer; make_sfx.py builds typing tracks from real keystrokes and places recorded click and pop sounds. Use it whenever a video needs a script, narration, voice-over, lines.tsv, timings.json, TTS, a new take, a voice or casting choice, a pronunciation fix ("it says the name wrong"), a changed sentence, a tone note ("too hype", "sounds cut off"), audio levels, a click at the end of a clip, typing or click sounds, or when the build stage asks for the voice. Also use it for silent loops, which still need a moment table and SFX.

josueh04/product-video-skills

The animation rules that keep HyperFrames' parallel render workers from dropping, flashing or flickering elements, plus a static lint (lint_motion.py) that finds the violations in a video's template before it costs a render. Use it whenever you write or edit GSAP tweens, timelines, cursors, camera moves, typing, scrolls or pop-ups in a HyperFrames composition or a video's src/template.tpl, whenever a render shows flicker, stutter, an element that vanishes on some frames, a title that flashes, or a "WORKER PATTERN" line from scan_render.py or qa.py, and whenever the preview looks right but the MP4 does not. Also use it to review someone else's timeline code before rendering.

josueh04/product-video-skills

Pin a product's source code (read-only exports in sources/ plus sources.lock), confirm that the pinned commit is what runs in production, and map every screen of a video brief to its route, components, i18n strings and state, written to the video's SOURCES.md. Use it whenever a video needs to know where a screen lives in the code, when sources/ is missing or stale, before ui-spec-from-code or product-truth start on a video, after the product's frontend changed ("what changed", "which videos are affected", "refresh the sources", "is this checkout current", "which commit is in prod"), and when there is no code and you need an inventory of the no-code references (recordings, recovered captures, docs) a screen can be rebuilt from.

josueh04/product-video-skills

Compose a narrated product demo in HyperFrames: the stage (the product UI rebuilt at its real viewport and scaled to 1080p, camera, rack focus with veil, chapter titles, cursor and clicks, typing, streaming text, pop-ups, toasts, scrolls, end screen and lockup) and the build.py that anchors every beat to a word of the narration. Use it whenever you write or edit a video's video/build.py, src/template.tpl or src/app.css, place a beat on a word, add a chapter, a click, a pop-up or a push-in, frame a screen, build the end screen or lockup, snapshot setup beats, or render a draft or delivery MP4 of a product video in this workbench. Also use it when someone says "the cursor is off", "too zoomed in", "too fast", "it feels chaotic", "the title flashes", "sync the UI to the voice", or asks for a walkthrough, demo or pitch video of a UI.

josueh04/product-video-skills

Gather pixel references for UI that the code cannot show, or to check a rebuild against the real thing, using frames and timed OCR text from screen recordings, captures recovered from past Claude Code session transcripts, a local instance of the app built like production, and web research for third-party apps, plus side-by-side parity images and contact sheets. Use it whenever someone hands over a screen recording (.mov or .mp4) of the product, when a screen has no usable source code (a stale checkout, another company's UI such as a sign-in page, calendar or CRM, runtime output from a backend not in the repos), when asked "what does it really look like", "match the recording", "how long does that animation take in the app", "compare our render to the real app", or when screenshots from an earlier session might already exist. Never uses the reviewer's personal browser.

josueh04/product-video-skills

Turn a product's real frontend code into 1:1 rebuild specs for a video, one read-only subagent per screen, each returning static HTML, CSS with every variable resolved to its literal value and cited (role/path:line@sha), every state, transitions with exact durations and easings, icons from the code's own icon sets, and the exact i18n strings; plus resolve_tokens.py to write the product's design tokens to kit/tokens.css. Use it whenever a screen of the product has to appear in a video, when writing or fixing video/src/app.css or the template markup, when someone asks for exact sizes, colors, fonts, paddings, animations or icons of a screen, when a rebuilt screen "looks off" next to the real app, and when the design tokens or theme of a product need extracting. Framework adapters cover Angular with PrimeNG (proven), React, Vue, Tailwind and plain HTML (unproven).

josueh04/product-video-skills

Say where this session stands in the Product Video Skills workbench (setup state, which product and video the current folder belongs to, the stage of every video) and the exact next command to type. Also answers "how do I..." questions about the workbench from its docs.

josueh04/product-video-skills

Coordinate the build of one or more signed videos of the current product with subagents (source recon, product truth, UI specs, voice, one builder per video), re-run QA itself, then deliver. A light coordinator that never builds itself. Run only when the user types /video-build.

josueh04/product-video-skills

Start a new video of the current product - create videos/<video>/, write BRIEF.md, the feature coverage matrix (COVERAGE.md) and the claims sheet (CLAIMS.md), propose chapters, then stop for the reviewer's sign-off. Never builds. Run only when the user types /video-new.

josueh04/product-video-skills

Turn a batch of reviewer feedback on the product's videos into one table per video, fix every video that got notes in parallel (one subagent each) while keeping approved parts, re-run QA and parity, bump versions and deliver. Run only when the user types /video-review.

Skills relacionados