Communitygithub.com

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.

Was ist product-video-skills?

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

Funktioniert mit✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/josueh04/product-video-skills/tree/HEAD/skills/product-new
Original anzeigen→Alle Skills durchsuchen

In Ihrer bevorzugten KI fragen

Öffnet einen neuen Chat, in dem dieser Agent-Skill bereits geladen ist.

OpenAIChatGPTClaudeClaudeGeminiGeminiGrokGrokPerplexityPerplexityDeepSeekDeepSeek

Dokumentation

/product-new

Create one product folder in the workbench: a short interview, one script that writes the folder, then the two model-invoked skills that fill it (source-recon fetches the code, product-kit extracts tokens, fonts, icons, logos, cast and names).

Why an interview before anything else: in the production these skills come from, the cast, the product names and the positioning arrived one review at a time, and each one forced a re-render. Every answer collected here is one review round that does not happen later.

Before you start

Resolve the workbench from this skill's real path (it works from the workbench and from a product folder):

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

Check the slug from the arguments: 2 to 40 lowercase letters, digits or dashes, starting with a letter. If $PVS_HOME/products/<slug> already exists, stop and say so: never overwrite a product, it has its own history and probably signed briefs. If the user passed --from examples/acme (or another folder), the interview only needs what differs from it.

Tell the user, once, before connecting any repo: Claude reads the product's code, which means it is sent to the model as context. They should make sure their company allows that.

1. Interview

Ask in small groups (two or three questions per message), in the user's language. Propose a default for anything you can infer, so the user mostly confirms. The full question list with the reason behind each one is in references/interview.md; read it before asking.

  1. The product: its name, what it is in one sentence (the positioning), who it is for.
  2. Never-say phrases: descriptions the team rejects, even if a company document uses them.
  3. Sources: for each one (frontend, backend, design, docs), a git URL or a local path, the branch that is in production, the app dir and the framework (angular-primeng, react, vue, svelte, html, other). Ask which branch is really deployed: a stale checkout cost real time in the original production.
  4. Docs: URLs, repo paths or mcp:<name> (read-only).
  5. Brand: only if it is not in the frontend (logo and font files). Otherwise product-kit finds it.
  6. Fictional cast: propose a company and two or three people with full names, a 555 phone and an email on an example/.test domain. Offer it for veto in one closed question with your proposal as the default. Reviewers react strongly to bland or real-sounding names, and a person whose surname changes between videos is a bug that ships.
  7. Names and pronunciations: the canonical names, the legacy strings the live UI may still show, and how brand words are spoken.
  8. Banned terms: competitors, vendors, real customers, anything that must never be seen or heard.
  9. Reviewer: who signs the coverage matrix and the claims sheet of each video.

Never ask for a token, a password or an SSH key, and never offer to store one. Sources are fetched with the git access the machine already has. If a URL contains credentials (https://user:token@...), ask the user to remove them; the script refuses them anyway.

2. Write the folder

Write the answers to a scratch file shaped like product.yaml (any subset; see references/answers.example.json), outside the repo, then run:

"$PVS_HOME/bin/pvs-py" "$PVS_HOME/skills/product-new/scripts/new_product.py" <slug> \
  --answers <scratch>/answers.json [--from examples/acme]

The script copies _template/product and then the --from folder over it (so an example that lacks a file, like kit/RULES.md, still gets the template's), merges the answers into product.yaml line by line (the template's comments are the user's documentation, so they are kept), writes CLAUDE.md and .gitignore when the template has none, runs scripts/link-skills.sh so cd products/<slug> && claude sees the same skills, and makes a first git commit. It refuses an existing slug, credentials in a URL, and cast emails or phones that are not obviously fictional. If it fails, fix the answer it names and run it again; do not create the folder by hand.

If it prints "still to fill in product.yaml", those are template placeholders the interview did not cover. Ask about them, or tell the user which ones remain.

3. Fill it

Call these model-invoked skills through the Skill tool, in this order:

  1. source-recon, to fetch every source into products/<slug>/sources/ and pin it in sources.lock. If a fetch fails for access, report the exact git error and stop: the user fixes access on their machine, never by giving you a credential.
  2. product-kit, to extract kit/tokens.css, fonts, icons, logos, and to write the cast, names and pronunciations into the kit and kit/RULES.md.

Both write only inside the product folder. Never edit anything in sources/.

4. Report

One short table, then the next command:

ItemValue
Folderproducts/<slug>/ (git: first commit or why not)
Sourcesrole, branch, commit from sources.lock
Kitwhat product-kit extracted, and what it could not find
Castthe frozen names, for a last veto
Openplaceholders still in product.yaml, anything unverified

Next: cd products/<slug> && claude, then /video-new <video>.

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

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.

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.

Verwandte Skills

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