Communitygithub.com

josueh04/product-video-skills

協調當前產品的一個或多個簽名影片的建置,由子代理(來源重構、產品事實、UI 規格、語音、每個影片一個建置者)完成,自行重新執行品質檢查,然後交付。一個輕量級的協調者,本身不執行建置。僅在使用者輸入 /video-build 時執行。

product-video-skills 是什麼?

此技能作為一個協調代理,負責管理產品影片的從頭到尾建置流程,但不直接參與實際建置工作。它首先檢查簽名閘門,確保所有必要的批准都已到位,然後按階段派遣專業子代理,包括來源重構(source-recon)、產品事實(product-truth)、UI 規格(ui-spec-from-code / ui-reference-capture)、語音(script-and-voice)和合成與渲染(ui-demo-composer + seek-safe-motion)。建置完成後,技能會使用 render-qa 腳本執行自己的品質檢查,以捕捉子代理可能遺漏的問題(例如閃爍或剪輯的模態視窗)。如果問題存在,它會將修復反饋給建置者,並在交付前重新確認。最終,交付腳本會將渲染結果存檔,並提供全面的批次報告,其中包含關於每個影片版本的版本、時長、章節、涵蓋範圍解釋、品質檢查結果和交付檔案等詳細資訊。此技能針對多影片建置進行了最佳化,可平行處理多個影片和階段,同時保持狀態僅存在於檔案中,而非代理的對話上下文中,從而實現可靠的中斷續傳。

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

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-build

您是協調者。您檢查關卡,按階段派遣子代理,通過其檔案驗證每個階段,自行重新執行 QA,交付並報告。您不撰寫組合程式碼、規格或旁白,也不負責渲染。

為什麼要拆分:在這些技能來源的生產中,當主要代理自行建置影片時,其上下文會填滿 8 次,其中一次發生在修正的中途。當它僅進行協調(整合、撰寫簡報、審查證據、交付)時,三個修正案在 70 分鐘內完成。品質關卡也位於協調中:子代理報告「乾淨」的渲染,但協調者自己的 QA 隨後發現了 0.3 秒的閃爍和裁剪的模態框。

0. 找到工作

PVS_HOME="$(cd "$(cd "${CLAUDE_SKILL_DIR}" && pwd -P)/../.." && pwd)"
PY="$PVS_HOME/bin/pvs-py"; S="$PVS_HOME/skills/video-build/scripts"   # 使用時請引用兩者
  • 若有 <video>:videos/<video>/ 位於目前產品中。
  • 若無:您所在的影片資料夾,或產品的所有影片中,其工作表已簽署且目前版本尚未交付。在派遣任何項目之前,先顯示該清單並以一個封閉式問題確認。

對每個影片執行 "$PY" "$S/stages.py" <video_dir> 並顯示表格。已完成的階段會被跳過,因此 /video-build 可以恢復中途停止的建置。

1. 關卡

"$PY" "$S/stages.py" <video_dir> --require signoff。如果 BRIEF.md 中的任一簽名為空,請停止並告知使用者缺少什麼以及如何簽署(審查者寫下他們的名字,或告訴您從 /video-new 執行 sign.py)。這項檢查可以防止最昂貴的重工類型(審查者想要解釋但沒有人寫下的功能)開始建置。

--draft 是唯一的例外,且僅在使用者輸入時:可以建置、渲染和 QA 檢查草稿,以便審查者在簽署前看到內容,但 deliver.py 會拒絕它。請在報告中說明。

同時自行閱讀 product.yaml、kit/RULES.md、BRIEF.md、COVERAGE.md 和 CLAIMS.md:您需要它們來撰寫子代理提示並判斷其結果。不要深入閱讀其他內容。

2. 派遣

使用具有背景子代理的 Agent 工具。每個階段的提示位於 references/stage-prompts.md,建置者提示位於 references/builder-prompt.md;在第一次派遣前閱讀它們並填寫所有佔位符。在每個子代理報告後,在開始任何依賴它的項目之前,執行 "$PY" "$S/stages.py" <video_dir> --require <stage>。

波次階段子代理需要寫入
1偵查每個影片 1 個,source-recon簽署sources.lock, SOURCES.md
2事實每個影片 1 個,product-truth偵查TRUTH.md
2規格每個畫面 1 個,ui-spec-from-code(或針對無程式碼的畫面使用 ui-reference-capture)偵查specs/<screen>.md
3語音每個影片 1 個,script-and-voice事實audio/lines.tsv, clips/, timings.json
4合成 + 渲染每個影片 1 個建置者,ui-demo-composer + seek-safe-motion規格, 語音video/, renders/<video>-v<N>.mp4
5QA您渲染qa/REPORT.json
6交付您QAdeliveries/

各波次在影片之間並行執行,並在波次內並行執行(事實和每個畫面的規格一起發出)。多個影片共用一台機器:在每個提示中說明,沒有代理會終止它未啟動的程序,並且渲染可能因為其他程式在執行而變慢。

在版本 1 的波次 3 之前,如果語音提供者是付費的,請在一則訊息中向使用者顯示旁白計畫:章節表格、標語、語音,最多三個帶有預設值的封閉式決策。錄製旁白會消耗共享配額,且審查者不喜歡的語氣或名稱在錄製前更改最便宜。如果使用者已表示直接進行,請跳過此步驟,並在最終報告中列出可供否決的選項。

當子代理執行時,不要用訊息輪詢它們。透過檔案(修改時間、$STAGES、渲染日誌的尾部)檢查進度,並在它們發送問題時回答它們。批准向上傳遞給使用者,決策向下傳遞:如果子代理要求只有使用者才能允許的事情(下載、新的資產來源),請向使用者提出一個封閉式問題並轉達答案。

如果子代理停止回應,請使用相同提示啟動一個新的代理,並加上「前一個代理在 停止;從檔案繼續」。狀態存在於檔案中,而不是代理中。

3. 您自己的 QA,無論建置者報告了什麼

"$PVS_HOME/bin/pvs-py" "$PVS_HOME/skills/render-qa/scripts/qa.py" <video_dir> <mp4> \
  --strip <name>:<t0>:<t1> ...

載入 render-qa 技能以了解如何讀取結果。添加一個圍繞每個章節標題、每個模態框和結束畫面的條帶,以鎖定交接(時間來自建置者的章節表格)。然後自行查看 qa/REPORT.md、每個連絡表單和每個條帶。根據 COVERAGE.md 檢查旁白:每個「是」的行必須在其章節中解釋。

如果任何項目失敗,請將確切的問題發送回建置者(在它還活著時使用 SendMessage,並使用 references/stage-prompts.md 中的精簡修復格式),或者,如果它已消失,請使用 $PVS_HOME/skills/video-review/references/fix-prompt.md 中的提示啟動修復者(閱讀檔案;不要調用該技能,它是使用者調用的)。在新渲染上重新執行此步驟。切勿交付未經您自己 QA 的渲染。

4. 交付

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

它會拒絕草稿、失敗的報告,或 sha256 與檔案不符的報告。不要繞過拒絕:修正原因。切勿覆蓋已交付的檔案;deliver.py 會改為遞增名稱並發出警告,您也必須這麼說。

5. 報告

一個用於整個批次表格,然後最多三個封閉式決策:

影片版本時長章節涵蓋範圍已解釋QA交付為

在其下方:哪些是真實的,哪些是假設的,任何未驗證的內容,可供否決的名稱、語音和標語,以及下一步(使用審查者筆記的 /video-review)。使用使用者的語言書寫,簡潔,表格優先。

何時閱讀參考資料

  • references/stage-prompts.md:在派遣波次 1 到 3 之前,以及針對任何修復請求。
  • references/builder-prompt.md:在派遣波次 4 之前。

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

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.

相關技能