Communitygithub.com

product-video-skills

Indique où en est la session dans l'atelier Product Video Skills (état de configuration, produit et vidéo du dossier courant, stade de chaque vidéo) et la commande exacte à taper ensuite. Répond aussi aux questions « comment faire... » sur l'atelier depuis sa documentation.

Qu'est-ce que product-video-skills ?

Ce skill d'agent IA fournit une orientation contextuelle dans l'atelier Product Video Skills (PVS). Il lit l'état depuis les fichiers – pas depuis la mémoire – en exécutant un script Python qui inspecte la structure du dossier et les fichiers de contrat pour déterminer le stade de chaque vidéo (brief non signé, signé, sources récupérées, etc.). Il affiche ensuite la sortie du script et la commande suivante à taper. Le skill peut répondre à des questions précises sur l'atelier en consultant la documentation officielle (README, contrats, SKILL.md des sous-skills, RULES.md du produit). Il ne lance aucune action de construction ou de correction ; il se contente de rapporter et de guider la prochaine étape. Les plateformes supportées incluent Claude Code (via les skills) et tout agent capable d'exécuter des scripts shell. Le skill est conçu pour éviter la désorientation de l'utilisateur et les erreurs de commande, en particulier lors du travail sur plusieurs vidéos et produits.

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

Demander à votre IA préférée

Ouvre une nouvelle conversation avec cette compétence d'agent déjà préchargée.

Documentation

/video-ask

Oriente l'utilisateur en un seul écran : où il se trouve, l'état des choses, quoi taper ensuite.

1. Lire l'état depuis les fichiers, pas depuis la mémoire

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

Passez un dossier comme premier argument quand l'utilisateur demande un dossier qui n'est pas le dossier courant. Ajoutez --json si vous avez besoin des champs (chemins, versions, stades) pour répondre à une question précise.

Le script déduit le stade de chaque vidéo à partir des fichiers définis dans docs/contracts.md, stade le plus récent atteint : brief non signé, signé, sources récupérées, vérité, specs, voix, construit, rendu, QA échouée, QA réussie, livré. Un rapport QA ne compte que lorsque son sha256 correspond au rendu le plus récent, donc un nouveau rendu après QA s'affiche à nouveau comme rendu. Fiez-vous au script plutôt qu'à ce qu'un tour de conversation précédent a dit : un sous-agent a peut-être modifié des fichiers depuis.

2. Répondre

Affichez la sortie du script telle quelle (elle est déjà courte), puis la commande suivante sur sa propre ligne. Si l'utilisateur a posé une question (l'argument), répondez-y après l'état, en utilisant ces sources dans l'ordre, et dites quel fichier vous avez utilisé :

  1. $PVS_HOME/README.md (ce que sont les skills, l'installation, les entrées nécessaires pour un produit)
  2. $PVS_HOME/docs/contracts.md (formats de fichiers, structure des dossiers, lignes de commande)
  3. Le SKILL.md du skill concerné par la question, sous $PVS_HOME/skills/
  4. Le kit/RULES.md du produit pour les questions « pourquoi cette règle est-elle là ? »

Si la réponse ne se trouve pas dans ces fichiers, dites-le plutôt que de deviner.

3. Éléments à signaler quand vous les voyez

  • Configuration non effectuée : la commande suivante est /video-setup. Rien d'autre ne fonctionne fiablement avant.
  • Clé vocale non définie : l'utilisateur la colle dans le fichier .env de l'atelier dans son propre éditeur, jamais dans le chat. voice.provider: say fonctionne sans clé. Ne lisez jamais .env pour vérifier : le script signale déjà défini ou non.
  • À la racine de l'atelier avec des produits : chaque produit est son propre projet Claude Code, avec ses propres skills et hooks. L'utilisateur exécute cd products/<slug> && claude pour y travailler.
  • Brief non signé : la construction attend délibérément les deux signatures du relecteur. Dans la production d'où viennent ces skills, 9 versions sur 26 ont eu lieu parce que personne n'avait convenu des fonctionnalités qu'une vidéo devait expliquer. Ne suggérez pas de modifier les champs de signature pour le relecteur.
  • QA échouée : pointez vers qa/REPORT.md de cette vidéo pour les vérifications échouées.

Ne commencez pas à construire, corriger ou livrer depuis ici. Ce skill ne fait que rapporter ; l'utilisateur tape la commande suivante.

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 associés