Communitygithub.com

josueh04/product-video-skills

Indica en qué estado se encuentra esta sesión dentro del banco de trabajo de Product Video Skills (estado de configuración, producto y video al que pertenece la carpeta actual, la etapa de cada video) y el siguiente comando exacto a escribir. También responde preguntas de tipo "cómo hago para..." sobre el banco de trabajo a partir de su documentación.

¿Qué es product-video-skills?

Este skill orienta al usuario dentro de un banco de trabajo de producción de videos de producto, mostrando en una sola pantalla su ubicación, el estado de cada video y el siguiente comando a ejecutar. Es útil para desarrolladores y gestores que trabajan con flujos de video basados en contratos, ya que automatiza la consulta del estado real del proyecto leyendo archivos en lugar de depender de la memoria de la conversación. Funciona en entornos Claude Code (u otros agentes compatibles con SKILL.md) y utiliza un script Python que infiere la etapa de cada video a partir de los archivos definidos en `docs/contracts.md`, detectando incluso si una re-renderización posterior a QA cambió el estado. Además, responde preguntas sobre el flujo de trabajo consultando fuentes documentales ordenadas, sin adivinar, y señala situaciones clave como configuración incompleta, claves de voz faltantes o briefs sin firmar.

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

Preguntar en tu IA favorita

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

Documentación

/video-ask

Orienta al usuario en una sola pantalla: dónde está, en qué estado están las cosas, qué escribir a continuación.

1. Leer el estado desde archivos, no desde la memoria

PVS_HOME="$(cd "$(cd "${CLAUDE_SKILL_DIR}" && pwd -P)/../.." && pwd)"
"$PVS_HOME/bin/pvs-py" "$PVS_HOME/skills/video-ask/scripts/status.py"

Pasa una carpeta como primer argumento cuando el usuario pregunta sobre una que no es la carpeta actual. Agrega --json si necesitas los campos (rutas, versiones, etapas) para responder una pregunta precisa.

El script infiere la etapa de cada video a partir de los archivos que define docs/contracts.md, la etapa más reciente alcanzada: brief sin firmar, firmado, fuentes obtenidas, verdad, especificaciones, voz, construido, renderizado, QA fallido, QA aprobado, entregado. Un informe de QA solo cuenta cuando su sha256 coincide con el render más reciente, por lo que un re-render posterior a QA se muestra como renderizado nuevamente. Confía en el script por encima de lo que una conversación anterior haya dicho: un subagente puede haber cambiado archivos desde entonces.

2. Responder

Muestra la salida del script tal cual (ya es corta) y luego el siguiente comando en su propia línea. Si el usuario hizo una pregunta (el argumento), respóndela después del estado, usando estas fuentes en orden, y di qué archivo usaste:

  1. $PVS_HOME/README.md (qué son los skills, la instalación, las entradas que necesita un producto)
  2. $PVS_HOME/docs/contracts.md (formatos de archivos, estructura de carpetas, líneas de comando)
  3. El SKILL.md del skill sobre el que trata la pregunta, en $PVS_HOME/skills/
  4. El kit/RULES.md del producto para preguntas de "por qué existe esta regla"

Si la respuesta no está en esos archivos, dilo en lugar de adivinar.

3. Cosas a señalar cuando las veas

  • Configuración no realizada: el siguiente comando es /video-setup. Nada más funciona de forma fiable antes.
  • Clave de voz no establecida: el usuario la pega en el .env del banco de trabajo en su propio editor, nunca en el chat. voice.provider: say funciona sin una. Nunca leas .env para comprobarlo: el script ya informa si está o no establecida.
  • En la raíz del banco de trabajo con productos: cada producto es su propio proyecto de Claude Code, con sus propios skills y hooks. El usuario ejecuta cd products/<slug> && claude para trabajar en él.
  • Brief sin firmar: la compilación espera intencionadamente las dos firmas del revisor. En la producción de donde provienen estos skills, 9 de 26 versiones ocurrieron porque nadie había acordado qué características debía explicar un video. No sugieras editar los campos de firma para el revisor.
  • QA fallido: señala qa/REPORT.md de ese video para ver las comprobaciones que fallaron.

No empieces a construir, arreglar o entregar desde aquí. Este skill solo informa; el usuario escribe el siguiente comando.

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

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.

josueh04/product-video-skills

Check this machine and install the pinned video toolchain of the Product Video Skills workbench (HyperFrames CLI, its rendering Chrome and its agent skills from the same release, the Python environment, the speech model for QA), then run the self-check. Safe to run again. `/video-setup check` only reports.

Skills relacionados