Communitygithub.com

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.

product-video-skills 是什么？

product-video-skills is a Claude Code agent skill that 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.

兼容平台✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/josueh04/product-video-skills/tree/HEAD/skills/video-setup
查看原文→浏览所有技能

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

OpenAIChatGPTClaudeClaudeGeminiGeminiGrokGrokPerplexityPerplexityDeepSeekDeepSeek

文档

/video-setup

Get the workbench from a fresh clone to passed N, failed 0 in one step. setup.sh does the work; your job is to explain it, get a yes, run it, and turn every FAIL line into its fix.

Find the workbench first (this works from the workbench and from a product folder):

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

Talk to the user in their language. Keep it short: they want a working setup, not a tour.

With the argument check

Run bash "$PVS_HOME/setup.sh" --check and show the result. It installs nothing, downloads nothing and writes nothing. For each FAIL line, give its fix (the line ends with it). Stop there.

Otherwise

1. Report the machine

Run bash "$PVS_HOME/setup.sh" --check first. It prints one line per item: ok, warn or FAIL with the exact fix.

  • If a line under Machine fails (node 22+, python 3.9+, ffmpeg, git), setup cannot continue. Give the user the fix from the line (for example brew install ffmpeg) and ask them to run it in their terminal, then run the check again. Installing system packages is their call, so do not run brew or apt yourself unless they ask you to.
  • A warn on Claude Code is informational.
  • FAIL lines under Toolchain are what setup installs. That is expected on a first run.

2. Say what will be downloaded, and ask once

Tell the user, in one short list, only the pieces the check reported missing:

PieceSizeWhere
HyperFrames CLI at the pinned version, with its dependenciesabout 128 MBnode_modules/
The Chrome build HyperFrames renders withabout 195 MB (skipped if cached)the HyperFrames cache
HyperFrames agent skills from the same release taga few MBvendor/hyperframes/skills/
Python packages, mostly torch for speech to textabout 339 MB.venv/
The whisper small.en speech model the QA uses484 MB~/.cache/whisper/

Ask one closed question: "Install these now? (yes / no)". The setup should happen in one step from the first /video-setup, so do not split it into several confirmations.

3. Run it

On yes, run bash "$PVS_HOME/setup.sh" --yes (the --yes is the user's answer, already given). It takes a few minutes on a first run and seconds when everything is cached; use a timeout of at least 10 minutes. It is idempotent: running it again only redoes what is missing.

4. Handle each FAIL

Every FAIL line names its fix. The common ones:

FAILWhat to do
npm install failedNetwork or registry problem. Show the last lines of the log it names, then run setup again
hyperframes browser ensure failedRun npx hyperframes browser ensure --force from the workbench, then setup again
could not clone heygen-com/hyperframesNetwork or GitHub access. Check git ls-remote https://github.com/heygen-com/hyperframes, then setup again
python3 -m venv failedOn Debian or Ubuntu: sudo apt install python3-venv (the user runs it)
pip install -r requirements.txt failedShow the log tail. A Python newer than the pins can need a newer wheel; report it rather than editing the pins
hyperframes doctor: ...The line names the failing check and its fix. Version, Docker and the optional local voice and music checks are ignored on purpose
tests/run.sh: passed N, failed MRun bash "$PVS_HOME/tests/run.sh" and show the failing tests with their output

Never "fix" a FAIL by running hyperframes upgrade or hyperframes skills update. The workbench pins one HyperFrames release and takes its skills from the same tag, because a CLI and skills from different releases disagree about the composition contract. A version change is a pull request that passes tests/run.sh. The guard hook blocks both commands anyway.

5. The voice key

Setup creates .env from .env.example and tells you whether the ElevenLabs key is set, without printing it. If it is empty, tell the user:

  • Open .env (in the workbench folder) in their own editor and paste the key after ELEVENLABS_API_KEY=. Never in the chat: anything in the chat is stored in the transcript. If they paste it here anyway, tell them to rotate it.
  • Without a key, voice.provider: say in a product's product.yaml uses the free macOS voices, good enough for drafts and tests.

Never open, read or print .env yourself. The settings deny it and the guard hook blocks it, and the scripts load the key through lib/pvs.py on their own.

6. Close

Confirm the last lines of the output say passed N, failed 0 and Setup done. Then give the next step in one line: /product-new <slug> to bring their product, or /video-ask to see where things stand.

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.

相关技能

steipete/video-frames

Extract frames or short clips from videos using ffmpeg.

community

steipete/summarize

Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.

community

openclaw/openclaw

Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.

community

obra/superpowers

Obra superpowers agent skills.

community

finishing-a-development-branch

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

community

writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code

community