Communitygithub.com

1999AZZAR/designer-mcp

将GitHub拉取请求(PR URL、owner/repo#N 或已检出的仓库中的 'this PR')转化为代码变更解说视频——变更日志、功能展示、修复说明或重构步骤演示,基于差异对比、提交记录和文件内容构建。输入是代码变更,而非网站。非产品推广视频或非PR主题解说视频。不确定时,请使用 /hyperframes。

designer-mcp 是什么?

该技能旨在将GitHub拉取请求(PR)自动转化为高质量的代码变更解说视频。它专为开发者设计,帮助团队快速理解代码变更、进行代码审查或创建变更记录。支持Claude Code、Cursor、Codex等AI代理平台。工作流程从设置HyperFrames项目和确认PR引用开始,通过步骤0的初始化和步骤1的PR信息抓取(使用`gh` CLI获取PR数据、差异补丁和贡献者头像),到步骤2的设计系统建立(固定为代码编辑风格),再到步骤3的故事板和脚本撰写(根据PR类型和叙事设计生成帧序列和旁白脚本),步骤3.1处理音频(旁白、背景音乐和音效),步骤4进行视觉设计,步骤5通过帧工作池生成HTML帧,最后步骤6渲染最终视频。技能强调严格的关卡验证(如步骤0、3、6需要用户确认),确保每个阶段输出正确后才继续。它还集成了媒体资源管理(通过`/media-use`技能)和偏好系统,支持在线(HeyGen)和离线(Kokoro)语音引擎。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/1999AZZAR/designer-mcp/tree/HEAD/skills/video/engine/pr-to-video

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

首先,保持技能更新——运行前请先向用户确认: npx hyperframes skills update pr-to-video。如果一切已是最新,则快速无操作;否则在依赖它之前刷新此技能及其依赖的核心领域技能。

媒体使用:在获取音频/图片/标志之前,先调用 /media-use 从HeyGen目录和品牌官方来源获取BGM/SFX/图片和品牌标志。先运行 --adopt 注册现有资源。请参阅 /media-use 技能。

PR 转 HyperFrames

使用此技能摄取一个GitHub拉取请求,理解变更内容,规划代码变更解说视频,并在HyperFrames中逐帧构建。输入是 代码变更(通过 gh 读取),而不是网站——没有捕获步骤,也没有真实资源,除了贡献者的头像。

入口是 /hyperframes。 你是协调器。按顺序运行每个步骤,验证其关卡,然后继续。此技能只适用于 GitHub拉取请求(代码变更)。任何其他意图、仅提及“制作视频”或任何不确定性 → 首先阅读 /hyperframes——意图层拥有所有路由决策,且没有 BRIEF.md 的新创建请求也会经过它(设置步骤的起始规则)。

你是协调器。在已解析的外部 PROJECT_DIR 中工作,默认不要进入调用者仓库。按顺序运行步骤,并在继续之前通过每个关卡。用户关卡为步骤0、步骤3和步骤6。在步骤0之前阅读 ../hyperframes/references/brief-contract.md——它定义了关卡类型以及 BRIEF.md 的 flow/storyboard 如何派生模式,该模式控制步骤3/4/6的关卡。自己执行所有步骤,但步骤5除外,在该步骤中你将调度一个受限的帧工作池。不要在这里放置设计或运动规则;这些规则位于帧工作子代理、此技能的本地 ../hyperframes-animation/rules/ + ../hyperframes-animation/blueprints/ 和 hyperframes-creative 中。

工作流程:步骤0 设置 → hyperframes.json;步骤1 摄取 → capture/extracted/ + assets/<login>.png;步骤2 设计系统 → frame.md;步骤3 故事板/脚本 → STORYBOARD.md 和 SCRIPT.md;步骤3.1 音频 → audio_meta.json;步骤4 视觉设计 → 增强的 STORYBOARD.md;步骤5 帧 → compositions/frames/NN-*.html 和 index.html;步骤6 最终渲染 → renders/video.mp4。


步骤0:设置

目标:确认简报后进入——包括 PR引用(完整URL、<owner>/<repo>#<N> 引用或已检出仓库中的“此PR”),创建HyperFrames项目,并持久化简报。风格始终是 代码编辑风格(在步骤2固定,不再询问)。

简报由意图层确认,而非在此处提问。 起始规则,按顺序:(1) BRIEF.md 存在 → 读取它,不询问任何问题——简报已确定,其 flow/storyboard 派生模式(brief contract § 1)。(2) 没有 BRIEF.md 但项目存在(磁盘上有 hyperframes.json / STORYBOARD.md)→ 从故事板的frontmatter和已记录的首选项恢复;绝不对半建成的项目重新询问。(3) 两者都没有——直接到达的新的创建请求 → 读取 /hyperframes 并运行其意图层(references/intent-interview.md):它检查食谱和记忆的默认值,并引导此路由的问题——包括PR大小→时长原则,该原则完整存在于 ../hyperframes/references/routes/pr-to-video.md——然后返回锁定的简报。编辑请求跳过所有这些——执行编辑。

在做任何其他工作之前,先解析项目目录。保留用户提供的项目目录;否则使用解析器打印的持久化外部缓存位置。绝不在调用者仓库中创建 videos/:

PR="<url | owner/repo#N>"
if [ -n "${EXPLICIT_PROJECT_DIR:-}" ]; then
  PROJECT_DIR="$(node <SKILL_DIR>/scripts/project-dir.mjs --pr "$PR" --project-dir "$EXPLICIT_PROJECT_DIR")"
else
  PROJECT_DIR="$(node <SKILL_DIR>/scripts/project-dir.mjs --pr "$PR")"
fi
echo "PR-to-video 项目: $PROJECT_DIR"
node <SKILL_DIR>/scripts/preflight.mjs

能力预检在抓取、故事工作、音频或帧分发之前运行。如果安装的CLI无法运行此技能所需的验证命令,则以它的升级指令停止,而不是消耗本次运行的上下文。

仅在 $PROJECT_DIR/hyperframes.json 缺失时初始化。其basename来自PR,例如 acme-sdk-pr-1842;绝不使用工作空间名称或时间戳。

npx hyperframes init "$PROJECT_DIR" --non-interactive --example=blank --skill=pr-to-video —— init 检查已安装的技能是否与GitHub上的最新版本一致,并在任何技能过时的情况下更新全局集合。

以下所有相对路径命令都以 $PROJECT_DIR 作为其工作目录运行。没有显式子shell的示例表示 (cd "$PROJECT_DIR" && …);绝不更改调用者仓库的工作树。

初始化后立即写入 BRIEF.md(绝不能在此之前——init 拒绝非空目录):意图层的锁定简报,形状见 ../hyperframes/references/brief-format.md。将 <MEDIA_DIR> 解析为已安装的 /media-use 技能目录。然后使用 node <MEDIA_DIR>/scripts/prefs.mjs record --hyperframes . 记录每个偏好支持的回答(brief-format.md 指名了子集)。如果意图层采用了食谱,运行 node <MEDIA_DIR>/scripts/recipe.mjs use --hyperframes . --name <name>;它将食谱的 frame.md 复制到项目中(则跳过步骤2)并返回步骤3从中起草的骨架。食谱填充答案,而非审批;审核关卡仍然运行。

在通过设置之前显示登录状态——运行 npx hyperframes auth status 并逐字中继其输出。它报告语音/BGM将使用HeyGen还是本地引擎,以及在登出时如何登录。应用一个分支:

  • 协作模式: 等待用户登录或显式选择 offline / go。
  • 自主模式: 说明状态并通过可用的本地引擎继续。

当没有离线提供商时,不要静默省略必需的能力;明确提出障碍。不要将此决策合并到另一个问题中,或将密钥写入每个仓库的 .env。认证所有权和离线回退:/media-use references/setup-providers.md § Providers。

关卡: hyperframes.json 和 BRIEF.md 存在;PR引用已捕获在简报中;偏好支持的回答已记录(brief contract § 2);登录状态已显示(已登录,或继续离线)。


步骤1:摄取PR(无捕获)

目标:获取PR的事实并将其纳入项目作为信息来源。没有网站抓取。fetch-pr.mjs 确定性地运行 gh——通过分页的 gh api 完成文件列表,以便大PR不会在约100个文件处截断,并且只写入 capture/pr.json + capture/diff.patch(无临时目录)。对于已合并的PR,它还会解析一个尽力而为的 shipped_version(+ version_source)到 pr.json 中,以便结束卡片可以引用真实版本,而不是发明一个。然后 ingest.mjs 将其离线地纳入合成抓取包。

PR="<url | owner/repo#N | N>"

# 确定性地抓取PR:运行gh,通过分页的gh api完成文件列表
# (这样大PR不会在约100个文件处截断),只写入capture/pr.json +
# capture/diff.patch——无临时目录。gh auth / not-found / private 错误在此处退出1。
(cd "$PROJECT_DIR" && node <SKILL_DIR>/scripts/fetch-pr.mjs --pr "$PR" --out-dir ./capture)

# 离线转换 → capture/extracted/{tokens.json (colors:[] → 代码编辑风格调色板),
# visible-text.txt (简报), people.json (贡献者, 已过滤机器人, name+login,
# avatarFile=assets/<login>.png)}。
(cd "$PROJECT_DIR" && node <SKILL_DIR>/scripts/ingest.mjs \
  --pr-json ./capture/pr.json --diff ./capture/diff.patch --out-dir ./capture/extracted)

# 人员管理的一个网络步骤——将每个贡献者的GitHub头像下载到
# assets/<login>.png,用于演职员名单结束画面。尽力而为;始终退出0。
(cd "$PROJECT_DIR" && node <SKILL_DIR>/scripts/fetch-people-avatars.mjs \
  --people ./capture/extracted/people.json)

如果 fetch-pr.mjs 退出1(gh auth / not-found / private),报告其stderr并停止——不要编造PR内容。如果 ingest.mjs 退出1,读取其stderr(通常是格式错误的 pr.json),修复并重新运行(确定性)。fetch-people-avatars.mjs 始终退出0;缺失的头像仅意味着没有给作者的演职员名单结束画面。

people.json 为 gh 已命名的贡献者(PR作者、提交作者、mergedBy)携带一个 name——其余贡献者(审核者/评论者/指派者,gh pr view 只提供纯 login)为 null。在步骤3写入演职员名单结束画面之前,为你将实际出现在该帧上的1-6人自行解析任何 null 名字:gh api users/<login> --jq .name(你已经有了 gh——无需编写脚本)。如果GitHub也没有该用户的公开名字,则在画面上回退为登录名,并从旁白行中移除该人(请参阅故事设计.md的演职员名单部分——旁白仍然必须说名字,绝不说原始句柄)。

关卡: capture/pr.json、capture/diff.patch、capture/extracted/tokens.json、capture/extracted/visible-text.txt 和 capture/extracted/people.json 存在;你能够用一句清晰的话描述PR的变更。assets/<login>.png 是尽力而为——其缺失不算失败。


步骤2:设计系统

目标:采用代码编辑风格帧预设;脚本将其转化为此视频的 frame.md + 字幕皮肤。

风格是固定的——代码编辑风格(温暖的编辑风格;适用于差异对比的海军蓝代码表面)。运行:

node <SKILL_DIR>/scripts/build-frame.mjs --preset code-editorial --hyperframes .

脚本将代码编辑风格预设的 FRAME.md 复制到 frame.md,将其与 capture/extracted/tokens.json 中的任何品牌令牌重新混合(PR没有这些 → colors:[]/fonts:[] 保留代码编辑风格自己的调色板,一个完整的设计),将预设的字幕皮肤复制到 .hyperframes/caption-skin.html,并自我验证(映射错误时退出1)。一旦退出0即继续——无需手动编辑。

关卡: build-frame.mjs 退出0——frame.md 从代码编辑风格预设存在,且 .hyperframes/caption-skin.html 作为字幕皮肤源存在。


步骤3:故事板和脚本

目标:将PR转化为经批准的逐帧解释计划。

阅读 ../hyperframes-creative/references/story-spine.md(钩子语言、证据在前、故事板作为提案、可溯源视觉)、references/story-design.md、../hyperframes-animation/blueprints-index.md、../hyperframes/references/storyboard-format.md 和 ../hyperframes/references/script-format.md。使用它们来编写 STORYBOARD.md,以及当需要旁白时编写 SCRIPT.md。从简报的 length 设置frontmatter的 duration:——一个粗略的期望;组装会报告最终时长与其的偏差。

使用 story-design.md 确定PR原型(变更日志/功能展示/修复说明/重构步骤演示)、PR原生帧类型、钩子、说服力、节拍、每帧单词预算和演职员名单结束画面。序列来自叙事设计,而非差异对比的文件顺序——解释变更,而不是朗读差异对比。作为软指南,查阅 ../hyperframes-animation/blueprints-index.md 中的角色→蓝图菜单:对于每个节拍,按照其候选蓝图暗示的形状编写旁白,并在匹配时标记该候选 blueprint: id(故事真相仍然决定哪些节拍存在——绝不要强行让节拍适合某种形状)。特色展示2-4个真实的差异块(来自 capture/diff.patch),每个都是一个小而可读的片段;在帧的 scene 中命名每个片段想要的 code-* 块。帧不携带 asset_candidates,除了 credits 结束画面(1-6个 assets/<login>.png 头像)。使用故事板和脚本参考中所需的精确字段。

起草后,运行审核循环的计划通过——../hyperframes/references/review-loop.md § 1:将计划作为提案呈现,并提出两个问题——批准或修改,以及先看草图(推荐)或跳过。反馈以聊天回复的形式到达;循环直到批准。这是一个检查点关卡(brief contract § 1):在自主模式下无需询问——作为预先提示发布相同的摘要并继续;草图合并到构建中,一个预览问题留在步骤6。

关卡: STORYBOARD.md 存在,每帧具有所需的叙事字段,当需要旁白时 SCRIPT.md 存在,并且用户批准了计划(自主模式:摘要作为预先提示已发布)。


步骤3.1:音频

目标:从已批准的脚本生成旁白、单词计时、音乐和音频元数据。

在步骤3批准后开始音频。在后台运行它,然后继续步骤4。

在调用之前,根据用户的要求选择旁白语音。 如果请求指定了语音、性别或语调,选择一个匹配的语音ID并通过 --voice <id> 传递它。流水线默认值否则是 Marcia(女性) 在HeyGen上 / am_michael 在Kokoro上——因此像“男声”这样的请求会被静默忽略,除非你传递了标志。语音ID是提供商特定的;根据步骤0的登录状态选择的提供商进行解析:HeyGen(已登录)通过 node <MEDIA_DIR>/audio/scripts/heygen-tts.mjs --list(或 GET /v3/voices?engine=starfish);Kokoro(离线)通过 <MEDIA_DIR>/audio/references/tts.md 中的语音表(前缀 am_/bm_ 男性,af_/bf_ 女性)。当用户没有表达偏好时,在流水线默认值之前回退到记忆中的语音(brief contract § 2),并说明你使用了哪个;仅当两者都没有指定时才省略 --voice。当用户本次运行显式选择了语音时,记录它(prefs.mjs record --key voice)。

node <SKILL_DIR>/scripts/audio.mjs --script ./SCRIPT.md --storyboard ./STOR

…

[已截断以进行翻译]

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

1999AZZAR/designer-mcp

SOTA animation and physics heuristic guide using motion.dev

1999AZZAR/designer-mcp

Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet `anchor` rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subject matting; split multi-shot footage before applying it.

1999AZZAR/designer-mcp

Turn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video: there is no site or footage to capture, so the visuals are invented per scene (typography, abstract graphics, diagrams, data-viz). Use for topic explainers, concept breakdowns, how-tos, listicles. Not a video built from a website (/product-launch-video — promo or tour). Unclear → /hyperframes.

1999AZZAR/designer-mcp

Import Figma content into a HyperFrames composition — rendered assets, brand tokens, components, storyboard sections → reconstructed motion (frames read as states, not slides) (REST/CLI), connector-assisted motion when available, and shaders from a connector or native export. Use when the user pastes a figma.com link or asks to bring a Figma design, frame, logo, brand, or animation into a video/composition.

1999AZZAR/designer-mcp

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated motion-first unit, including an animated title. Route fresh creation through hyperframes before using this skill.

1999AZZAR/designer-mcp

All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). Also covers auditing an existing composition's choreography (animation map) and 24 named text-animation effects. HyperFrames-native: single paused timeline, seek-safe, deterministic.

1999AZZAR/designer-mcp

Use when audio already placed in a HyperFrames composition needs to be mixed: fade-in/fade-out, crossfade, track gain or volume, volume automation, ducking, a music bed that fights a voiceover (voiceover carve), effects on a track (EQ, compressor, limiter, gate, saturation, delay, reverb, chorus, phaser, bitcrush), automation envelopes drawn on a track's volume or any effect parameter, or one submix bus carrying a chain, a fader and an automation clock for several tracks at once (`<hf-audio-group>`). Don't use for sourcing or generating audio — finding BGM, SFX, or making a voiceover is `/media-use`. Don't use for clip timing or track layout, which is `/hyperframes-core`.

1999AZZAR/designer-mcp

Use the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, cloudrun, feedback, lambda, doctor, browser, info, upgrade, skills, compositions, timeline, docs, benchmark, telemetry, transcribe, auth, tts, and remove-background. Also use when diagnosing build or render failures. validate, inspect, and layout are deprecated aliases; use check. Covers local, HeyGen-hosted cloud, AWS Lambda, and Google Cloud Run rendering.

1999AZZAR/designer-mcp

The HyperFrames composition contract — build one renderable project. Use for composition structure, the `data-*` timing attributes, `class="clip"`, tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Read before writing composition HTML.

1999AZZAR/designer-mcp

Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use `hyperframes-animation`.

1999AZZAR/designer-mcp

Use when a HyperFrames composition needs a punch-in, punch-out, zoom, reframe, Ken Burns treatment, camera move, visual match/whip handoff, or other seek-safe 2D/3D keyframes; also for GSAP, CSS keyframes, Anime.js, WAAPI, FLIP, paths, masks, SVG morph/draw, text trails, 3D depth, or `hyperframes keyframes` diagnostics. Don't use for broad scene strategy, brand design, media sourcing, captions, or general video planning.

1999AZZAR/designer-mcp

Search, install, and wire registry blocks and components into HyperFrames compositions. Use BEFORE hand-building any named visual — whenever a brief, a user, or a storyboard names a look, effect, treatment, or transition such as CRT scanlines, glitch, chromatic aberration, film grain, a shimmer sweep, a chart, a code or terminal window, a map, or a confetti burst — because roughly 400 hosted items already cover many of them and the search ranks all of them with nothing installed, no project, and no account. Also use when running hyperframes add or hyperframes catalog, installing one item or every block matching a tag, wiring an installed item into index.html, or working with hyperframes.json. Covers discovery, install locations, block sub-composition wiring, component snippet merging, and authoring a new block or component to contribute upstream (idea → scaffold → validate → PR).

1999AZZAR/designer-mcp

Mandatory entry point: read this first for any request to make, create, edit, animate, or render a video, animation, or motion graphic, including a promo, explainer, captioned clip, title card, overlay, slideshow or interactive deck, Remotion port, or any HyperFrames HTML composition. Also use it to inspect, diagnose, validate, preview, publish, or batch-render an existing HyperFrames project. Inputs may be a website URL, GitHub PR, Figma design or URL, text or brief, existing footage, or music. It resumes project state, captures intent when applicable, selects and installs the owning workflow, and routes domain capabilities. HyperFrames is the default output framework unless the user explicitly chooses another framework for the deliverable or asks only to record a browser session.

1999AZZAR/designer-mcp

Use when building or editing a HyperFrames project that people open in Studio: how the timeline should be laid out so it reads well (one caption track, one element kind per track, every scene a sub-composition) and where captions and key content may sit (safe zones). Don't use for how to perform an individual edit (split, trim, retime, volume, copy, swap): that is `creator-editing-recipes.md` in `/hyperframes-core`.

1999AZZAR/designer-mcp

Agent Media OS, the single skill for every media need in a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or paste-ready block + ledger record (one verb, `resolve`); generate via TTS / music / image models when the catalog misses; produce voiceover, transcription, captions, and background removal through one shared audio engine; operate on media (cut / reframe / transform); and reuse assets across projects. Also use for vague feedback that real footage looks dark, flat, boring, should feel retro/camcorder/print/ASCII, needs privacy, or needs a media reveal.

1999AZZAR/designer-mcp

Turn a music track (an audio file, a video to pull audio from, or a track generated from a mood brief) into a beat-synced video — lyric video, slideshow, or kinetic promo. The music drives all pacing; any user-supplied images/videos are cut onto the same beat grid, and a complete video needs zero assets. Narrated pieces → the input-matched workflow (see /hyperframes). Unclear → /hyperframes.

1999AZZAR/designer-mcp

Port an existing Remotion (React) composition''s source to HyperFrames HTML. Use ONLY on an explicit ask to port/convert/migrate/translate a Remotion source — one-way, Remotion-only. A passing Remotion mention, reference-only code, or "make something like my Remotion video" is a fresh build (/general-video). Unclear → /hyperframes.

1999AZZAR/designer-mcp

Author a HyperFrames slideshow — a presentation, pitch deck, or interactive deck with discrete slides, fragment reveals, branching, hotspot navigation, and built-in presenter mode with speaker notes; also converts an existing page into a deck. Output is a navigable deck, not a rendered MP4. If the user didn't explicitly ask for a slideshow, confirm before authoring. Unclear → /hyperframes.

1999AZZAR/designer-mcp

Package an existing talking-head / interview / podcast video with timed, designed GRAPHIC OVERLAY cards — kinetic titles, lower-thirds, data callouts, quotes, side panels, picture-in-picture — synced to the transcript, on a 16:9 / 9:16 / 4:5 canvas of your choice; the clip plays untouched underneath. Trigger on "graphic overlays", "on-screen graphics", "package / dress up my video". Not plain subtitles (/embedded-captions). Unclear → /hyperframes.

1999AZZAR/designer-mcp

All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). Also covers auditing an existing composition's choreography (animation map) and 24 named text-animation effects. HyperFrames-native: single paused timeline, seek-safe, deterministic.

相关技能