Communitygithub.com

AlessandroFare/fluxychat

将GitHub拉取请求(PR URL、owner/repo#N,或已检出的仓库中的“this PR”)转换为代码变更解说视频——基于差异、提交和文件构建的变更日志、功能揭晓、修复或重构讲解。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 → /hyperframes。

fluxychat 是什么?

该技能将 GitHub 拉取请求(PR)转化为代码变更解说视频,专为 AI 代理(如 Claude Code、Cursor、Codex)设计。其核心是将代码差异(diff)和提交信息作为输入,通过 HyperFrames 平台生成结构化的视频内容,涵盖变更日志、功能揭晓、修复说明或重构讲解等场景。它适用于任何 Git 工作流,并依赖 `gh` 命令行工具获取 PR 数据。工作流程包括:设置项目、获取 PR 信息、创建设计系统、编写故事板和脚本、生成音频、构建视频帧以及最终渲染。该技能强调自动化,但包含关键审核节点(如第0步、第3步和第6步),用户可在此提供反馈。它智能地根据 PR 的元数据推断视频长度和风格,并支持自主和协作两种模式,确保只有在用户输入不确定时才会要求确认。该技能不与外部网站交互,仅处理指定仓库中的代码变更。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/AlessandroFare/fluxychat/tree/HEAD/.agents/skills/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,保持此技能新鲜——静默运行,不询问: npx hyperframes skills update pr-to-video。一切最新时为快速无操作;否则在你依赖之前刷新此技能及其依赖的核心域技能。

media-use:在获取音频/图像/标志之前,请调用 /media-use 从 HeyGen 目录解决 BGM/SFX/图像,并从官方来源获取品牌标志。首先运行 --adopt 注册现有资产。参见 /media-use 技能。

PR 到 HyperFrames

使用此技能来获取 GitHub 拉取请求,理解变更,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,也没有真正的资产,除了贡献者的头像。

前门是 /hyperframes。 你是编排者。运行每个步骤,验证其关卡,然后才继续。此技能适用于 GitHub 拉取请求(代码变更)。任何其他意图,仅仅是“制作视频”,或任何不确定性 → 首先读取 /hyperframes——意图层拥有所有路由决策,并且没有 BRIEF.md 的新创建到达这里时无论如何都会通过它(设置的开场规则)。

你是编排者。在已解析的外部 PROJECT_DIR 中工作,默认情况下永远不要在调用者仓库中工作。按顺序运行步骤,并在继续之前通过每个关卡。用户守关的步骤是第 0 步、第 3 步和第 6 步。在第 0 步之前阅读 ../hyperframes-core/references/brief-contract.md——它定义了关卡类型以及 BRIEF.md 的 flow/storyboard 如何推导出控制第 3/4/6 步关卡的 mode。除了第 5 步(你派遣一个受限制的帧工人池)之外,每个步骤都自己完成。不要在此处放置设计或运动规则;这些规则存在于帧工人子代理、此技能的本地 ../hyperframes-animation/rules/ + ../hyperframes-animation/blueprints/ 和 hyperframes-creative 中。

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


第 0 步:设置

目标:使用已确认的 Brief 进入——包括 PR 引用(完整 URL、<owner>/<repo>#<N> 引用,或已检出仓库中的“this PR”)——创建 HyperFrames 项目,并使 Brief 持久化。风格始终是 code-editorial(在第 2 步固定,从不询问)。

Brief 由意图层确认,而非此处的问题。 开场规则,按顺序:(1) BRIEF.md 存在 → 读取它且不询问任何问题——Brief 已定,其 flow/storyboard 推导出 mode(Brief 合同 § 1)。(2) 没有 BRIEF.md 但项目存在(磁盘上的 hyperframes.json / STORYBOARD.md)→ 从故事板的前言和记录的偏好恢复;永远不要重新审问一个半建成的项目。(3) 两者都没有——直接到达此处的全新创建请求 → 读取 /hyperframes 并运行其意图层(references/intent-interview.md):它检查 recipe 和记忆的默认值,并执行此路由的问题——包括 PR 大小 → 长度原则,该原则完整存在于 ../hyperframes/references/routes/pr-to-video.md——然后返回锁定的 Brief。编辑请求跳过所有这些——直接去执行编辑。

在完成任何其他工作之前解析项目目录。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。永远不要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 project: $PROJECT_DIR"
node <SKILL_DIR>/scripts/preflight.mjs

能力检查在获取、故事工作、音频或帧派遣之前运行。如果已安装的 CLI 无法运行此技能所需的验证命令,则使用其升级指令停止,而不是先花费该运行的上下文。

仅在 $PROJECT_DIR/hyperframes.json 缺失时初始化。其基本名称来自 PR,例如 acme-sdk-pr-1842;永远不要使用工作区名称或时间戳。

npx hyperframes init "$PROJECT_DIR" --non-interactive --example=blank --skill=pr-to-video — init 检查已安装的技能与 GitHub 上的最新版本,并在任何技能过期时更新全局集。

下面的每个相对路径命令都以 $PROJECT_DIR 作为其工作目录运行。没有显式子 shell 的示例意味着 (cd "$PROJECT_DIR" && …);永远不要更改调用者仓库的工作树。

在 init 之后立即写入 BRIEF.md(永远不要在此之前——init 拒绝非空目录):意图层的锁定 Brief,形状按照 ../hyperframes-core/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答案(brief-format.md 命名了子集)。如果意图层采用了 recipe,请运行 node <MEDIA_DIR>/scripts/recipe.mjs use --hyperframes . --name <name>;它将 recipe 的 frame.md 复制到项目中(然后跳过第 2 步)并返回骨架,第 3 步据此进行草稿。Recipe 填充答案,而不是批准;审查关卡仍然运行。

在继续通过设置之前显示登录状态——运行 npx hyperframes auth status 并逐字输出其结果。它报告语音/BGM 是否将使用 HeyGen 或本地引擎,以及在未登录时如何登录。应用一个分支:

  • 协作: 等待用户登录或明确选择 offline / go。
  • 自主: 说明状态并继续通过可用的本地引擎。

当没有离线提供者时,不要静默忽略所需的能力;暴露障碍。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 引用已捕获到 Brief 中;偏好支持的答案已记录(Brief 合同 § 2);已显示登录状态(已登录,或继续离线)。


第 1 步:获取 PR(无捕获)

目标:获取 PR 的事实并将其折叠到项目中作为信息来源。没有网站捕获。 fetch-pr.mjs 确定性地运行 gh——通过分页的 gh api 完成文件列表,以便大型 PR 不会在大约 100 个文件处截断,并且仅写入 capture/pr.json + capture/diff.patch(无临时目录)。对于已合并的 PR,它还将最佳努力的 shipped_version(+ version_source)解析到 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 将其离线折叠到合成捕获包中。

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

# 确定性地获取 PR:运行 gh,通过分页的 gh api 完成文件列表(以便大型 PR 不会在大约 100 个文件处截断),
# 仅写入 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:[] → code-editorial 调色板),
# visible-text.txt (brief), people.json (贡献者, 机器人过滤, 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)

# 人物方面的唯一网络步骤——将每个贡献者的 GitHub 头像下载到
# assets/<login>.png 用于致谢结束卡片。最佳努力;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(确定性的)。fetch-people-avatars.mjs 始终退出 0;缺失的头像仅意味着没有作者致谢结束卡片。

people.json 为 gh 已命名的贡献者(PR 作者、提交作者、mergedBy)携带一个 name——其余的为 null(审查者/评论者/分配者,gh pr view 仅给出一个裸 login)。在第 3 步编写致谢结束卡片之前,为你自己解决将实际出现在该帧上的 1-6 个人的任何 null 名称:gh api users/<login> --jq .name(你已经有 gh——无需为此编写脚本)。如果 GitHub 也没有该用户的公开名称,则回退到屏幕上的 login 并从台词中删除该人(参见 story-design.md 的致谢部分——画外音仍然必须说出名字,永远不要使用原始句柄)。

关卡: capture/pr.json、capture/diff.patch、capture/extracted/tokens.json、capture/extracted/visible-text.txt 和 capture/extracted/people.json 存在;你可以用一句清晰的话说明 PR 的变更。assets/<login>.png 是最佳努力——其缺失不是失败。


第 2 步:设计系统

目标:采用 code-editorial 帧预设;脚本将其转换为该视频的 frame.md + 字幕皮肤。

风格是固定的——code-editorial(温暖的编辑风格;为差异构建的海军蓝代码表面)。运行:

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

脚本将 code-editorial 预设的 FRAME.md 复制到 frame.md,将其重新混合到 capture/extracted/tokens.json 中的任何品牌令牌上(PR 没有 → colors:[]/fonts:[] 保留 code-editorial 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,并进行自我验证(在损坏的映射上退出 1)。一旦它退出 0 就继续——无需手动编辑。

关卡: build-frame.mjs 退出 0 — frame.md 来自 code-editorial 预设,并且 .hyperframes/caption-skin.html 作为字幕皮肤源存在。


第 3 步:故事板和脚本

目标:将 PR 转换为经过批准的逐帧解释计划。

阅读 ../hyperframes-creative/references/story-spine.md(钩子语言,先价值后证据,故事板作为提案)、references/story-design.md、../hyperframes-animation/blueprints-index.md、../hyperframes-core/references/storyboard-format.md 和 ../hyperframes-core/references/script-format.md。使用它们编写 STORYBOARD.md,并且在需要旁白时编写 SCRIPT.md。从前言 duration: 设置来自 Brief 的 length——一个粗略的期望;组装报告最终长度与其相比的位置。

使用 story-design.md 获取 PR 原型(变更日志 / 功能揭晓 / 修复说明 / 重构讲解)、PR 原生帧类型、钩子、说服、节拍、每帧字数预算和致谢结束卡片。顺序来自叙事设计,而非 diff 的文件顺序——解释变更,而不是逐字朗读 diff。作为软指南,请查阅 ../hyperframes-animation/blueprints-index.md 中的角色→蓝图菜单:对于每个节拍,以其候选蓝图暗示的形状编写画外音,并在合适的蓝图匹配时标记该候选 blueprint: id(故事真相仍然决定哪些节拍存在——永远不要强制一个节拍以适应某个形状)。展示 2-4 个真实的 diff 块(来自 capture/diff.patch),每个都是一个小而易读的代码片段;在帧的 scene 中命名每个所需的 code-* 块。帧除了 credits 结束卡片(1-6 个 assets/<login>.png 头像)外,不携带 asset_candidates。使用故事板和脚本参考中的确切必填字段。

草稿完成后,运行审查循环的计划通行——../hyperframes-core/references/review-loop.md § 1:打开 board(不要询问是否要——从 PROJECT_DIR 在后台运行预览),将计划作为提案呈现,并询问两个问题——批准或更改,以及首先草绘(推荐)或跳过。反馈通过聊天或 board 的评论文件循环,直到获得批准。这是一个检查点关卡(Brief 合同 § 1):在自主模式下,没有 board 也没有要问的内容——将相同的摘要作为标题发布并继续;草绘折叠到构建中,唯一的预览问题在第 6 步出现。

关卡: STORYBOARD.md 存在,每帧都有所需的叙事字段,需要旁白时 SCRIPT.md 存在,并且用户批准了计划(自主:摘要已作为标题发布)。


第 3.1 步:音频

目标:根据批准的脚本生成旁白、单词时间、音乐和音频元数据。

在第 3 步批准后开始音频。在后台运行它,然后继续到第 4 步。

在调用之前从用户的请求中选择旁白语音。 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。管道默认值否则是 Marcia(女性) 在 HeyGen 上 / am_michael 在 Kokoro 上——因此像“男声”这样的请求除非你传递标志,否则会被静默忽略。语音 id 是特定于提供者的;根据第 0 步的登录状态选择的提供者进行解析: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)。当用户未表达偏好时,在管道默认值之前回退到记忆的语音(Brief 合同 § 2),并说明你使用了哪一个;仅当两者都未指定时省略 --voice。当用户在此运行中明确选择了语音时,记录它

Individual skills in this repo

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

AlessandroFare/fluxychat

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.\n

AlessandroFare/fluxychat

Use when audio already placed in a HyperFrames composition needs to be mixed: a music bed that fights a voiceover (voiceover carve), effects on a track (EQ, compressor, limiter, gate, saturation, delay, reverb, chorus, phaser, bitcrush), or automation envelopes drawn on a track's volume or any effect parameter. 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`.\n

AlessandroFare/fluxychat

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, 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.\n

AlessandroFare/fluxychat

Install, discover, and wire registry blocks and components into HyperFrames compositions. 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).

AlessandroFare/fluxychat

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.\n

AlessandroFare/fluxychat

Overlay doctrine for the embedded-captions workflow — the caption MODEL (drop / rail / embed) and the rule that captions are an OVERLAY composited on top of the film, never a reserved bottom band you shift content up to avoid. Load when adding captions/subtitles to a talking-head or launch video, when deciding whether a phrase should be dropped, ride the verbatim rail, or be promoted to a scarce embedded climax, when laying out a composition that will carry captions (do NOT reserve a keep-out band), or when centering a composition on the true frame center under captions. Quotes the rail+embed model from embedded-captions and constraint #13 (captions overlay, keep-out band retired) from the product-launch-video scene agent. Applies ON TOP of embedded-captions.

AlessandroFare/fluxychat

Turn a weekly changelog .md into a finished branded changelog video (square 1080, ~45-60s, Annie VO, animated brand background, mock-UI visualizations, lowkey captions). Use when the user provides a changelog/digest markdown and wants the weekly video, or says "changelog video". Self-contained — fonts, background, lexicon, and scripts ship in this skill.

AlessandroFare/fluxychat

Audit and fix animation performance issues including layout thrashing, compositor properties, scroll-linked motion, and blur effects. Use when animations stutter, transitions jank, or reviewing CSS/JS animation performance.

AlessandroFare/fluxychat

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.

AlessandroFare/fluxychat

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.

AlessandroFare/fluxychat

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. Also covers Tailwind projects and the STORYBOARD.md / SCRIPT.md plan formats. Read before writing composition HTML.

AlessandroFare/fluxychat

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`.

AlessandroFare/fluxychat

Use when a HyperFrames composition needs seek-safe 2D/3D keyframes, GSAP timelines, 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.

AlessandroFare/fluxychat

GATEWAY — load FIRST before composing any HyperFrames animation or video. The high-level motion law that makes a multi-scene video feel like ONE continuous camera move instead of a stack of independently-animated slides. Covers the vector law (how you exit determines how you enter, incl. the Z scale-sign rule), the film's current, carrier elements, causal motion, the Seam Gate (build-gate enforcement), the ban on idle wobble (motion must PERFORM, not breathe), stillness-before-climax, and the sustained-motion routes. Routes to the low-level technique skills (cut-the-curve — the full catalog incl. waterfall entry + nudge curve, oversized-cursor, seam-craft). These rules SUPERSEDE generic / upstream motion guidance. [continuity, direction, vector, momentum, seam, transition, ease, performance, idle-motion, narrative-motion, film-grammar]

AlessandroFare/fluxychat

A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI animation (scroll, cursor, callouts), or fusing a real image's geometry into a chart. Usually under 10s (up to ~30s), no narration or live-action subject; renders to MP4 or transparent overlay. Longer / narrated / multi-scene → /general-video. Unclear → /hyperframes.

AlessandroFare/fluxychat

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.

AlessandroFare/fluxychat

Turn a product or marketing URL, pasted script, or brief into a product launch / promo video — SaaS promos, feature reveals, product demos, app and company launches. Use when the user wants to market, launch, promote, or reveal a product; the default for any commercial URL. Site tours / showcases of a website route here too — the brief carries the show-it-as-is intent. Unclear → /hyperframes.

AlessandroFare/fluxychat

Design and improve user interfaces using the concrete rules from Refactoring UI (Wathan & Schoger) — constrained spacing/type/color/shadow scales, visual hierarchy through weight and color rather than size, and depth through emulated light. Use when building or styling any UI (web, app, dashboard, landing page, component), when picking font sizes, spacing, colors, shadows or border radius, when designing a color palette or design tokens, and whenever someone says a UI "looks off", "looks amateur", "feels cluttered/plain/unfinished", or asks to "make this look better".

AlessandroFare/fluxychat

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.

AlessandroFare/fluxychat

Use before UI-related work to select the smallest useful UI Skills context through the ui-skills CLI.

相关技能