Communitygithub.com

josueh04/product-video-skills

確保產品影片中的每一句旁白與每個畫面都有可追溯的原始碼或文件引用,提供 TRUTH.md 並使用 truth_check.py 進行驗證,避免產品展示不實的風險。

product-video-skills 是什麼?

此技能專為產品影片製作流程設計,旨在透過結構化的方式驗證影片中所有宣稱(claims)的真實性。它會將影片的旁白逐句拆分、對應每個螢幕畫面,並強制為每一項宣稱提供可追溯的來源(如程式碼行號、文件 URL)。技能支援多種平台(如 Claude Code),並可與現有專案結構(如 videos/、sources/)整合。它將每個宣稱分類為 UI、後端、文件或模擬畫面,並賦予 backed、approved、needs-approval、rewrite、cut 或 unbacked 等 verdict。當宣稱無法被支援時,技能會要求改寫或刪除,而非模糊帶過。最終產出 TRUTH.md 檔案,並透過 truth_check.py 腳本自動檢查完整性,確保每行旁白、每個畫面都有對應的引用與正確的 verdict。這避免了過去成本高昂的「真相失敗」案例,例如顯示了產品不存在的功能或使用了錯誤的術語。

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

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

產品真相

=== ===

一個展示了產品做不到的事情的產品影片,比沒有影片更糟。在這些技能所來自的製作過程中,代價最高的時刻都是真相失敗:一個手工製作的徽章帶有錯誤的尺寸和錯誤的產品名稱;一個工作流程被旁白為「等待通話結果」,但產品僅透過單獨的觸發器返回結果;一個被重新標記為已確認預訂的測試通話,但沒有人進行端到端驗證;一份公司文件的標題與團隊已同意的定位相矛盾。每一個都是在審查時才被發現,並且耗費了一個版本來修正。

此技能將檢查變得明確且機械化:每一行和每個畫面在 TRUTH.md 中都有一個帶有來源的資料列,而 truth_check.py 會拒絕任何資料列缺失、過時或無來源的影片。

輸入

  • videos/<video>/audio/lines.tsv(旁白,每行 ID 對應一個句子)
  • videos/<video>/SOURCES.md(來自 source-recon:畫面及其程式碼)
  • videos/<video>/BRIEF.md、COVERAGE.md、CLAIMS.md(影片必須說明的內容、定位、應避免的用語、需要核准的主張)
  • product.yaml:positioning、never_say、names(正式名稱到舊版字串)、banned_terms
  • sources/<role>/ 和 sources.lock(由 source-recon 鎖定;如果遺失,請先執行 source-recon,因為引用必須指向鎖定的提交)

1. 列出主張

將 lines.tsv 的每一行拆分成它所做出的主張。"Acme Tasks 會讀取您的行事曆,並將逾期任務移至明天" 包含兩個主張:它讀取行事曆,以及它移動逾期任務。每個畫面以及 SOURCES.md 和章節中描述的每個螢幕操作(例如「點擊「規劃我的一天」會開啟規劃器,並顯示三個建議」)都需添加一個主張。

撰寫這些主張所引發的問題,並以程式碼可回答的方式表述:這是什麼觸發的?儲存了什麼?有哪些選項?使用者會看到什麼、在哪裡看到?哪些事情僅在伺服器端發生?

2. 從程式碼和文件中解答

並行啟動唯讀的子代理,每個產品領域一個(前端行為、各後端、文件),使用 references/product-facts-prompt.md 中的提示。將它們指向 sources/<role>/,切勿指向使用者的工作目錄,這樣它們的行號才能與鎖定相符。它們僅從程式碼或文件中回答,引用每個事實,如果找不到則說「未找到」。

3. 分類每個主張

可見性含義影片可以
ui由前端渲染;引用模板或 i18n 行顯示它並為其旁白
backend在伺服器上為真,螢幕上沒有任何顯示為其旁白,永不繪製 UI
docs只有文件這麼說使用文件 URL 為其旁白;在可能的情況下檢查程式碼是否同意
mock一個設計好的元件,不是產品 UI(電話畫面、結束卡、生成的文字)顯示它,在 BRIEF 中標記為設計
評判含義
backed來源確切地這麼說
approved需要簽署(受限、未發布、CLAIMS.md 中列出的主張),並且審查者在 CLAIMS.md 中已給予核准
needs-approval屬實,但受到限制、有門檻、未發布或在 CLAIMS.md 中列出;等待審查者
rewrite部分屬實;你在註解中提出有來源支援的措辭
cut不真實,或沒有找到來源
unbacked尚未檢查
mock僅適用於可見性 mock

對於旁白的行,只有 backed 和 approved 才能通過。一個受限的功能(僅對某些角色、方案或內部團隊可見)、一個在功能開關後的功能,或一個在未合併分支上的功能,在審查者在 CLAIMS.md 中同意之前,是 needs-approval,並且 BRIEF 會備註其受限。這在原始製作中發生過:一個只有內部員工才能看到的功能,應審查者要求被展示,並已標記。

4. 修正不符之處

  • 改寫部分屬實的句子,使其成為來源支援的最強版本。保留作者想要的意思;將機制改為真實的機制。
  • 刪除沒有來源的內容。不要將其軟化為模糊的內容;模糊的主張仍然是主張。
  • 切勿讓標籤偏離。 一個標記為「示意圖」的設計元件,不得為了後續美觀而丟棄該標籤,除非重新檢查未標籤版本所做的主張。
  • 定位優於文件。 如果一個簡報或 PRD 說了一些 never_say 或 CLAIMS.md 禁止的內容,則該規則獲勝,句子需要更改。
  • 僅使用目前的名稱。 使用 product.yaml names 中的正式名稱,即使即時 UI 或程式碼仍然顯示舊版字串。搜尋 lines.tsv、規格和模板中每個舊版字串和每個 banned_terms 項目(競爭對手、團隊不希望出現在螢幕上的第三方供應商、真實客戶),並修復每個命中。

5. 當請求與產品衝突時

當簡報或審查者要求某些程式碼不支援的內容時,不要偽造,也不要默默地放棄它。提出一個帶有選項和建議預設值的封閉式問題,並且每輪最多保留三個這樣的問題,因為無止盡的否決清單會無人回應,而沉默就變成了沒有人做出的決定。「只做真實的」模式:

簡報顯示 Acme Tasks 自己預訂會議室。程式碼只建立任務並連結會議室的行事曆(frontend/src/rooms/LinkRoom.tsx:22@1a2b3c4);預訂在行事曆應用程式中發生。選擇哪一個?

  1. 只做真實的(建議): 顯示連結步驟,並說「連結會議室的行事曆」。
  2. 將行事曆應用程式的預訂畫面顯示為一個設計元件,並加上標籤,且旁白為行事曆的步驟。
  3. 放棄這個節拍(Drop the beat)。

將答案記錄在 CLAIMS.md 中,並據此設定評判。

6. 撰寫 TRUTH.md

# 真相:<video>

已鎖定:前端 main@1a2b3c4,後端 main@5d6e7f8。檢查日期:2026-01-12。

| ID | 句子 | 來源 | 可見性 | 評判 | 備註 |
|---|---|---|---|---|---|
| N1 | Acme Tasks 從您的行事曆規劃您的一天。 | frontend/src/planner/plan.ts:31@1a2b3c4; https://docs.example.com/planner | ui | backed | |
| N2 | 逾期任務在午夜移至明天。 | backend/jobs/rollover.py:12-30@5d6e7f8 | backend | backed | 未在螢幕上顯示 |
| screen:board | 包含三個任務的看板,其中一個逾期 | frontend/src/pages/board/BoardPage.tsx:14@1a2b3c4 | ui | backed | |
| screen:call | 與客戶通話 | (設計) | mock | mock | 在 BRIEF 中標記 |

## 未解決問題
1. <帶有建議答案的封閉式問題>

每個 lines.tsv 的行 ID 對應一個資料列,句子需完全複製(檢查時會進行比對,因此在真相驗證後編輯該行會導致失敗,直到您重新驗證)。每個畫面一個資料列,ID 為 screen:<name>,與 SOURCES.md 相符。多個引用放入一個儲存格,以分號分隔。

7. 檢查它

PVS_HOME="$(cd "$(cd "${CLAUDE_SKILL_DIR}" && pwd -P)/../.." && pwd)"
"$PVS_HOME/bin/pvs-py" "$PVS_HOME/skills/product-truth/scripts/truth_check.py" <video_dir>

在以下情況下檢查會失敗:一行沒有對應的資料列、句子已更改、旁白行的評判不是 backed 或 approved、引用的角色未被鎖定、其 SHA 不是鎖定的 SHA(程式碼已移動;需重新驗證)、其檔案不在匯出範圍內、或其行號超過檔案尾端。修復每個失敗;不要編輯檢查腳本。

向使用者報告:有多少行和畫面是 backed、你改寫和刪除了什麼(附上原因)、什麼正在等待核准、以及未解決的問題。

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

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.

相關技能