Communitygithub.com

josueh04/product-video-skills

將一批產品影片的審閱意見轉換為每部影片一份表格,平行修復所有有問題的影片(每部影片一個子代理),同時保留已核准的部分,重新執行品質檢查與一致性比對,提升版本並交付。僅在使用者輸入 /video-review 時執行。

product-video-skills 是什麼?

此技能專為批次處理產品影片審閱意見而設計,能顯著提升效率。傳統上,審閱意見以序列方式逐一處理,導致上下文填滿、修復時間冗長。此技能透過將所有意見合併成每部影片一份表格,然後平行啟動多個子代理,同時修復所有需要處理的影片。支援 Claude Code 等平台,透過 SKILL.md 中定義的腳本流程,自動執行取得批次意見、建立意見表格、版本號遞增、平行修復、自行檢查結果(包括一致性比對與品質檢查)、交付與報告等步驟。此方法能將原本需要 50-90 分鐘的序列修復流程,大幅縮短為平行處理,並確保在修復過程中不覆蓋已核准的片段或先前版本。此技能特別適合需要快速迭代、處理大量影片審閱意見的產品開發團隊。

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

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

/video-review

一次審閱循環:收集整批意見,按影片彙整,同時修復所有有問題的影片,自行檢查每個結果,交付下一個版本,並產出報告。

為何採用批次與平行處理:在這些技能所屬的生產環境中,曾經有三條意見間隔五分鐘到達,代理程式便在其自身上下文中開始修復第一條。上下文填滿後,審閱者不得不中止它,並表示逐一處理意見的方式沒有效率。合併成一個表格後交由三個平行子代理處理,同樣的三項修復在 70 分鐘後完成審閱與交付。修復從來不只是重新渲染:編輯、旁白、渲染、品質檢查和報告每部影片需要 50 到 90 分鐘,因此序列化修復會導致時間倍增。

0. 設定

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

找到產品(目前目錄上層最近的 product.yaml),並列出所有影片及其當前版本與交付狀態(對每部影片執行 skills/video-build/scripts/stages.py)。

1. 取得整批意見

如果引數是檔案,則讀取檔案;如果是文字,則使用該文字。然後確認一次:「這是此輪所有影片的全部意見回饋嗎?沒有意見的影片保持原樣。」在修復任何內容之前等待回答。如果在彙整時意見持續到達,請將其加入同一輪;不要為每條訊息啟動一次修復。

2. 將意見合併成每部影片一份表格

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

它會將每條意見逐字分類,放到它所命名的影片(依 id、標題或 heading)下方,將關於「所有影片」的意見放在共享區段,並列出無法歸類的意見。然後你需要在每一行填入:意義(你的解讀,包括不得變更的內容)、驗收條件(你將如何檢查:時間範圍、片段、某個畫面)以及是否為所有影片的規則?

在填寫之前請先閱讀 references/review-protocol.md:其中涵蓋聽寫錯誤、實際上是規則的意見,以及與產品衝突的意見。

對每條意見需要問的三個問題:

  1. 這真的是規則嗎?如果是,它適用於此輪的所有影片,而不僅是審閱者所指出的那一部。曾有審閱者在一部影片上給出覆蓋規則,數小時後又要求將其套用到所有影片。
  2. 產品真的有做到嗎?在承諾修復之前先檢查程式碼。如果沒有,提出一個封閉式問題並附上建議選項(「僅顯示已存在的內容」)。
  3. 這是 COVERAGE.md 中缺少的功能嗎?如果是,則修復時需加入該行。

向使用者展示合併後的表格,最多包含三個封閉式決策(附上預設值)。沉默表示接受預設值。沒有意見的影片被列為未更動。

3. 為每部有問題的影片開啟下一個版本

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

它會備份 lines.tsv、timings.json 和 video/src 為 v,將 BRIEF 版本提升至 N+1 並使用引號開啟一個變更日誌區段。如果 v 從未被渲染過(這會跳過一個版本),則會拒絕執行。v 的渲染結果保持不變:它是一致性比對的參考,且審閱者可能已分享的檔案絕不會被覆寫。

4. 每部影片一個修復子代理,全部同時啟動

為每部影片填寫 references/fix-prompt.md(審閱者的原話、你的意義與驗收條件、你已在程式碼中找到的內容及 file:line、共享規則),並在同一輪中使用 Agent 工具在背景啟動所有修復器。在啟動之前,請自行簡短執行「我已找到的內容」所需的程式碼查詢;這能為每個修復器省去相同的搜尋時間,並捕捉產品無法滿足的意見。

在修復器執行時,不要自行修復任何內容,也不要發送訊息輪詢它們。觀察檔案(stages.py、修改時間、渲染日誌)。如果修復器需要核准,向使用者提出一個封閉式問題並轉達答案。如果修復器停止,使用相同的提示詞加上其中止的位置啟動一個新的修復器:狀態都在檔案中。

5. 自行檢查每個結果

針對每部影片,無論修復器回報了什麼:

  1. 與先前版本的一致性比對,排除有意識變更的區段: "$PY" "$PVS_HOME/skills/render-qa/scripts/parity.py" <old mp4> <new mp4> --skip a:b ...。 已核准的區段發生變更即為回歸:退回修復。
  2. 品質檢查:"$PY" "$PVS_HOME/skills/render-qa/scripts/qa.py" <video_dir> <new mp4> --strip ... 並在每個變更的節拍處設定 strip。請載入 render-qa 以了解如何解讀;自行查看 sheets 與 strips。
  3. 從你的表格中檢查每條意見的驗收條件。渲染結果未滿足的意見會退回同一個修復器(SendMessage:問題、時間範圍,「不要更改其他任何內容」)。
  4. BRIEF.md 中的變更日誌區段需填寫完整。

6. 交付並關閉此輪

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

然後一起關閉此輪:成為規則的意見需寫入 kit/RULES.md(附上日期與審閱者的原話),以便下一個建置繼承它們;每個 BRIEF 變更日誌需完整。不再更新的規則檔案會變得錯誤,然後規則就必須在每個提示詞中手動重複。如果審閱者已將先前版本上傳到某處,請指出哪些檔案需要重新上傳。

7. 報告

影片從到已套用的意見查看位置一致性品質檢查交付版本

接著:未更動的影片、已加入 kit/RULES.md 的規則、任何未驗證的項目,最多三個封閉式決策。使用使用者的語言,以表格為先,保持簡短。

參考資料

  • references/review-protocol.md:在填寫合併表格之前閱讀。
  • references/fix-prompt.md:在啟動修復器之前閱讀。

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.

相關技能