Communitygithub.com

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.

product-video-skills 是什么？

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

兼容平台✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/josueh04/product-video-skills/tree/HEAD/skills/video-review
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-review

One review round: collect the whole batch, consolidate it per video, fix every video that got notes at the same time, check each result yourself, deliver the next versions, report.

Why batch and parallel: in the production these skills come from, three notes arrived five minutes apart and the agent started fixing the first one in its own context. The context filled, the reviewer had to stop it, and said that feedback handled one note at a time was not efficient. Consolidated into one table and handed to three parallel subagents, the same three fixes were reviewed and delivered 70 minutes later. A fix is never just a render: editing, narration, render, QA and the report took 50 to 90 minutes per video, so serial fixes multiply.

0. Setup

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

Find the product (nearest product.yaml above the current directory) and list its videos with their current version and delivery status (skills/video-build/scripts/stages.py on each).

1. Get the whole batch

If the argument is a file, read it; if it is text, use it. Then ask once: "Is this all the feedback for this round, for every video? Videos with no notes stay as they are." Wait for the answer before fixing anything. If notes keep arriving while you consolidate, add them to the same round; do not start a fix per message.

2. Consolidate into one table per video

"$PY" "$PVS_HOME/skills/video-review/scripts/feedback_table.py" <product_dir> <notes file or -> \
  --out <product_dir>/reviews/round-<date>.md

It sorts each note, verbatim, under the video it names (by id, title or heading), puts notes about "all videos" in a shared section, and lists notes it cannot place. Then you fill, per row: Meaning (your reading, including what must not change), Acceptance (how you will check it: a time range, a strip, a frame), and Rule for all videos?

Read references/review-protocol.md before filling it: it covers dictation errors, notes that are really rules, and notes that conflict with the product.

Three questions to ask of every note:

  1. Is it really a rule? Then it applies to every video in this round, not only the one the reviewer pointed at. A reviewer once gave a coverage rule on one video and had to ask again, hours later, for it to be applied to all of them.
  2. Does the product actually do it? Check the code before promising a fix. If not, a closed question with a recommended option ("show only what exists").
  3. Is it a feature that was missing from COVERAGE.md? Then the fix adds the row.

Show the consolidated tables to the user with at most three closed decisions (defaults stated). Silence means the defaults. Videos without notes are listed as untouched.

3. Open the next version of each video with notes

"$PY" "$PVS_HOME/skills/video-review/scripts/bump_version.py" <video_dir> --note "<quote>" ...

It backs up lines.tsv, timings.json and video/src as v, bumps the BRIEF version to N+1 and opens a changelog section with the quotes. It refuses when v was never rendered (that would skip a version). The v render stays untouched: it is the parity reference, and a file the reviewer may have shared is never overwritten.

4. One fix subagent per video, all at once

Fill references/fix-prompt.md for each video (the reviewer's words verbatim, your meaning and acceptance, what you already found in the code with file:line, the shared rules) and launch every fixer in the same turn with the Agent tool, in the background. Do the code lookups that feed "what I already found" yourself before launching, briefly; they save each fixer the same search and catch notes the product cannot satisfy.

While they run, do not fix anything yourself and do not poll them with messages. Watch files (stages.py, modification times, render logs). If a fixer needs an approval, ask the user one closed question and relay the answer. If a fixer stops, start a new one with the same prompt plus where it stopped: the state is in the files.

5. Check every result yourself

For each video, whatever the fixer reported:

  1. Parity against the previous version, outside the stretches that changed on purpose: "$PY" "$PVS_HOME/skills/render-qa/scripts/parity.py" <old mp4> <new mp4> --skip a:b .... An approved stretch that changed is a regression: send it back.
  2. QA: "$PY" "$PVS_HOME/skills/render-qa/scripts/qa.py" <video_dir> <new mp4> --strip ... with strips at every changed beat. Load render-qa for how to read it; look at the sheets and strips yourself.
  3. Each note's acceptance check from your table. A note the render does not satisfy goes back to the same fixer (SendMessage: the problem, the time range, "change nothing else").
  4. The changelog section in BRIEF.md is filled.

6. Deliver and close the round

"$PY" "$PVS_HOME/skills/render-qa/scripts/deliver.py" <video_dir> <new mp4> --archive-previous

Then close the round, together: notes that became rules go into kit/RULES.md (with the date and the reviewer's words) so the next build inherits them; each BRIEF changelog is complete. A rules file that stops being updated becomes wrong, and rules then get repeated by hand in every prompt. If the reviewer already uploaded previous versions somewhere, say which files need uploading again.

7. Report

VideoFromToNotes appliedWhere to see itParityQADelivered as

Then: untouched videos, rules added to kit/RULES.md, anything unverified, at most three closed decisions. In the user's language, short, tables first.

References

  • references/review-protocol.md: before filling the consolidated tables.
  • references/fix-prompt.md: before launching the fixers.

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

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.

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