Communitygithub.com

josueh04/product-video-skills

将一批评审者对产品视频的反馈转化为每个视频的表格,并行修复每个有备注的视频(每个子Agent处理一个),同时保留已通过的部分,重新运行质量保证和一致性检查,升级版本并交付。仅在用户输入 /video-review 时运行。

product-video-skills 是什么?

该技能旨在高效处理产品视频的评审反馈流程。它通过将一批评审反馈按视频整理成表格,然后为每个有修改意见的视频并行启动独立的子Agent进行修复,从而显著缩短处理时间。这种并行机制避免了传统顺序处理中因上下文堆积和等待导致的低效问题,尤其是在每个修复步骤(编辑、配音、渲染、QA)本身耗时较长的情况下。技能支持通过CLI命令进行版本管理、质量保证和交付,并提供了详细的检查清单和参考文档,确保修复的准确性和一致性。它适用于需要频繁处理视频评审反馈的开发团队或内容制作团队,尤其是在Claude Code等支持Agent工具的环境中,能够自动化整个评审-修复-交付流程,减少人工干预。

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

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

/video-review

一轮评审:收集整批反馈,按每个视频合并,同时修复所有有备注的视频,自行检查每个结果,交付下一版本,并报告。

为什么采用批量和并行处理:在这些技能来源的生产环境中,三条反馈在五分钟内先后到达,代理开始在自己的上下文中修复第一条。上下文被填满,评审者不得不停止它,并指出一次只处理一条反馈效率不高。将反馈合并到一个表格中并交给三个并行的子代理后,同样的三个修复在70分钟后被评审并交付。修复绝非仅仅是渲染:编辑、配音、渲染、质量检查和报告每个视频需要50到90分钟,因此串行修复会成倍增加时间。

0. 设置

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

找到产品(当前目录上最近的 product.yaml)并列出其视频以及当前版本和交付状态(在每个视频上运行 skills/video-build/scripts/stages.py)。

1. 获取整批反馈

如果参数是一个文件,则读取它;如果是文本,则直接使用。然后询问一次:“这是本轮所有视频的所有反馈吗?没有备注的视频保持原样。” 在修复任何内容之前等待回答。如果在合并过程中反馈继续到达,将它们添加到同一轮中;不要每收到一条消息就启动一次修复。

2. 将反馈合并为每个视频的表格

"$PY" "$PVS_HOME/skills/video-review/scripts/feedback_table.py" <产品目录> <反馈文件或 -> \
  --out <产品目录>/reviews/round-<日期>.md

它将每条反馈按原样归类到它命名的视频(通过ID、标题或标题)下,将关于“所有视频”的反馈放在共享部分,并列出无法归类的反馈。然后,为每一行填写:含义(你的理解,包括哪些内容不得更改)、接受标准(你将如何检查:时间范围、片段、帧)和对所有视频都适用的规则?

在填写之前阅读 references/review-protocol.md:它涵盖了口述错误、实际上是规则的反馈以及与产品冲突的反馈。

对每条反馈要问三个问题:

  1. 它真的是规则吗?如果是,则本轮所有视频都适用,而不仅仅是评审者指出的那个。曾经有一位评审者对单个视频给出了覆盖规则,几小时后不得不再次要求将其应用于所有视频。
  2. 产品实际上是否已经实现该规则?在承诺修复之前检查代码。如果没有,则提出一个带有推荐选项的封闭性问题(例如“仅显示已存在的内容”)。
  3. 这是 COVERAGE.md 中缺少的功能吗?如果是,则修复需要添加该行。

向用户展示合并后的表格,最多包含三个封闭式决策(附上默认值)。沉默表示接受默认值。没有备注的视频列为未修改。

3. 为每个有备注的视频开启下一版本

"$PY" "$PVS_HOME/skills/video-review/scripts/bump_version.py" <视频目录> --note "<引用>" ...

它备份 lines.tsv、timings.json 和 video/src 为 v,将 BRIEF 版本升级到 N+1,并打开一个包含这些引用的变更日志节。如果 v 从未被渲染(那将跳过一个版本),它会拒绝操作。v 的渲染产物保持不变:它是对比参考,并且评审者可能共享过的文件永远不会被覆盖。

4. 每个视频一个修复子代理,同时启动

为每个视频填写 references/fix-prompt.md(评审者的原话、你的理解和接受标准、你在代码中已发现的内容及其 file:line、共享规则),然后在同一轮中使用 Agent 工具后台启动每个修复器。在启动之前,自行进行简短的代码查找,以提供“我已找到的内容”;这可以为每个修复器节省相同的搜索,并捕获产品无法满足的反馈。

在它们运行时,不要自行修复任何内容,也不要发送消息轮询它们。监视文件(stages.py、修改时间、渲染日志)。如果修复器需要批准,向用户提出一个封闭性问题并转发答案。如果修复器停止,使用相同的提示加上它停止的位置启动一个新的:状态保留在文件中。

5. 自行检查每个结果

对于每个视频,无论修复器报告了什么:

  1. 与前一个版本进行一致性检查,排除故意更改的片段: "$PY" "$PVS_HOME/skills/render-qa/scripts/parity.py" <旧的mp4> <新的mp4> --skip a:b ...。 已批准的片段发生更改属于回归:将其退回。
  2. 质量检查:"$PY" "$PVS_HOME/skills/render-qa/scripts/qa.py" <视频目录> <新的mp4> --strip ... 在每个更改的节拍处设置片段。加载 render-qa 以了解如何读取;自行查看工作表和片段。
  3. 从你的表格中检查每条反馈的接受标准。未满足的反馈需要退回给同一个修复器(发送消息:问题、时间范围、“不要更改其他任何内容”)。
  4. 填写 BRIEF.md 中的变更日志节。

6. 交付并关闭本轮评审

"$PY" "$PVS_HOME/skills/render-qa/scripts/deliver.py" <视频目录> <新的mp4> --archive-previous

然后,一起关闭本轮评审:成为规则的反馈添加到 kit/RULES.md(附上日期和评审者的原话),以便下次构建继承它们;每个 BRIEF 变更日志应完整。不再更新的规则文件会变得错误,然后规则会在每个提示中被人为重复。如果评审者已在某处上传了之前的版本,说明哪些文件需要重新上传。

7. 报告

视频从到应用的备注查看位置一致性质量检查交付版本

然后:未修改的视频、添加到 kit/RULES.md 的规则、任何未验证的内容,最多三个封闭式决策。使用用户的语言,简短,表格优先。

参考

  • references/review-protocol.md:在填写合并表格之前阅读。
  • references/fix-prompt.md:在启动修复器之前阅读。

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