Communitygithub.com

社交影片格式化工具 (Social Video Formatter)

將已完成製作的影片重新構圖並匯出為適用於各社群平台的格式,包括 9:16 ↔ 16:9 裁切、內嵌字幕、平台原生首幀、循環設計,以及符合 TikTok、Reels、Shorts、X 和 LinkedIn 各自規格(長寬比、長度、安全區域)的設定。

社交影片格式化工具 (Social Video Formatter) 是什麼?

此技能專為已完成的影片(故事、動態與品牌元素均已定稿)進行最後的社群平台適配,確保其在動態消息中能完美呈現。它與「remotion-video-production」工具包搭配使用:您在此決定重新構圖、安全區域、字幕樣式和循環方式,然後將具體規格傳遞給 remotion-compose(負責編寫新的 `<Composition>` 寬高及內嵌字幕)和 remotion-render(負責按平台匯出)。此技能支援的觸發詞包括「調整為直式」、「裁切為 9:16」、「加入字幕」、「為 TikTok/Reels/Shorts 格式化」等。其工作流程依序為:確定目標平台並查閱規格表、選擇重新構圖策略(重新佈局、中心裁切、模糊背景或追蹤裁切)、繪製安全區域、設計平台原生的首幀畫面、指定內嵌字幕的位置與樣式、設計循環方式,最後產出匯出規格。此技能明確不處理專案架構、撰寫合成程式碼或執行渲染,僅負責產出規格。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/SkillMedev/skills/tree/HEAD/skills/social-video-formatter

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

社交影片格式化工具

您拿到一部已經 正確 的影片—故事、動態和品牌都已完成—然後讓它在動態消息中 落地。這與製作影片是截然不同的工作。一個在筆電上看起來很棒的橫向示範影片,在直式的動態消息中就會毀掉:它會被加上黑邊變成一條細帶、字幕出現在 UI 按鈕下方、第一幀是黑色的、而且不會循環。此技能會逐一修復這五個問題,並針對每個平台,發出機械工具包所需的確切規格。

這是品味層。它與 remotion-video-production 工具包配對使用:您在這裡決定重新構圖、安全區域、字幕樣式和循環方式,然後將具體的規格傳遞給 remotion-compose(用來編寫新的 <Composition> 寬高及內嵌字幕)和 remotion-render(用來按平台匯出)。請勿在此撰寫合成程式碼或執行渲染—只需命名規格並交辦。

當收到任何重新構圖、調整大小、裁切、轉為直式、加入字幕或「為社群平台格式化/匯出」的要求,或提及特定平台(TikTok、Reels、Shorts、X/Twitter、LinkedIn)時,甚至是單純說「讓它在手機上能看」,都應主動觸發此技能。

工作流程

按順序執行。先重新構圖再處理字幕(字幕的安全區域取決於新的長寬比),並在移交給渲染工具前,設計好首幀和循環方式。

步驟 1 - 確定目標平台並查閱其規格

詢問要上架哪些平台,然後從 references/platform-specs 的表格中查詢每個平台的硬性限制。每個平台需要四個數字:長寬比、解析度、最大長度,以及安全區域邊距(平台 UI—使用者名稱、字幕、動作列、進度條—所覆蓋的像素帶)。切勿憑空猜測這些數字;位於動作列間距內的字幕在裝置上是看不見的,但在預覽中卻看起來很正常。一個來源影片通常會擴展為兩到三個匯出版本(例如一個用於 TikTok/Reels/Shorts 的 9:16 主版本,再加上一個用於 LinkedIn/X 的 1:1 或 16:9 版本)。

步驟 2 - 選擇重新構圖策略 (9:16 ↔ 16:9)

裁切會改變哪些像素保留下來,因此主體必須位於新畫面內。根據每個匯出版本選擇一個策略—請參閱 references/reframe-strategies:

  • 重新佈局 (最佳)。 完全不裁切 16:9 的像素—為新畫布重新編寫場景:將並排的內容堆疊起來、放大文字、將主體移至垂直中央。這會變更 remotion-compose(新的寬高,相同的內容),而且效果總是優於裁切。交辦目標尺寸。
  • 中心裁切。 為取得 9:16 而保留 16:9 畫面的中間部分。速度快,但會捨棄外側三分之一—僅適用於主體位於中心時。
  • 填充 / 模糊背景。 將整個 16:9 畫面放入 9:16 中,並在上下方以模糊的縮放副本填滿。適用於談話性頭像或螢幕錄影;在動態設計作品中會顯得偷懶。
  • 追蹤裁切。 裁切到主體,並隨著時間推移移動裁切視窗以跟隨動作。效果最強,工作量也最大;需為 remotion-compose 指定關鍵影格。

從 9:16 轉為 16:9 則是反向的相同邏輯:重新佈局以利用新的水平空間,而不是將垂直片段加上黑邊塞入橫向條帶。

步驟 3 - 將安全區域映射到新畫面上

針對每個匯出版本,疊加平台的安全區域邊距,並將所有必要元素—字幕、標誌、行動呼籲按鈕 (CTA)、關鍵主體—保持在安全矩形內。右側/底部的間距(動作列 + 字幕區塊)是 9:16 畫面上常見的殺手。執行下方的 safe_area.js,將百分比邊距轉換為您確切解析度下的像素框,然後將這些數字作為佈局邊界傳遞給 remotion-compose。將不安全區域視為任何必須被閱讀的元素的禁區。

步驟 4 - 設計平台原生的首幀

首幀就是縮圖,也是讓人停下滾動的關鍵;自動播放從靜音開始,因此第 0 幀必須在沒有音訊的情況下傳達意義。不要以黑色、標誌開場或淡入中場面開始。要以一個可閱讀的鉤子開場:結果展示、一句大膽的字幕,或是主體已經在畫面上。這是對 remotion-compose 的編輯,作用於開場場景(或預先加上 1-2 秒的鉤子)。確切指定第 0 幀的內容。

步驟 5 - 指定內嵌字幕

假設為靜音播放:字幕是強制性的,而非選擇性的,並且必須 內嵌(渲染到像素中),因為上傳的 .srt 側車字幕檔案在各平台上的表現不一致且無法設定樣式。為 remotion-compose 指定:位置(在安全區域內,通常是下方三分之一處,但在字幕區塊間距之上)、樣式(大尺寸、高對比、半粗體,並帶有描邊或實色背景以確保在任何背景上都能閱讀)、時間(與語音同步的短語級區塊,而非一整面文字牆),且畫面上絕不超過約 2 行。對於逐字動畫字幕,請將動態設計移交給 kinetic-typography,並僅在此指定安全區域框和時間。

步驟 6 - 設計循環

動態消息會立即重播片段,因此一個乾淨的循環能倍增觀看時間。選擇一種:

  • 無縫循環 - 最後一幀與第一幀匹配(相同的構圖、位置、顏色),使重播幾乎無法察覺。最適合短篇的氛圍/品牌循環。
  • 鉤子回返循環 - 以一句引導觀眾回到開頭的台詞結尾(「…這就是第一步」),使重看變得有意識。
  • 硬停止 - 一個明確的 CTA 結束卡片;適用於較長的敘事性作品,循環會顯得很突兀。

對於無縫循環,開場和結尾是 remotion-compose 的一項限制(匹配第 0 幀和最後一幀)。指明循環類型及匹配的影格。

步驟 7 - 產出匯出規格並交辦

填寫下方的 export-spec 範本—每個平台一個區塊。該規格是給機械工具包的簡報:remotion-compose 根據長寬比編寫一個帶有安全區域佈局、首幀和內嵌字幕的 <Composition>;然後 remotion-render 匯出每個項目(一個 9:16 的匯出是一個在 1080×1920 編寫的 Composition,遵循 remotion-render 的直式預設)。請勿在此渲染—只需交付規格。

品質標準

只有當所有條件都滿足時,匯出品才是 A+ 等級:

  • 每個平台的匯出都指定了真實的長寬比、解析度、最大長度和安全區域框—從規格表中查詢,而非猜測。
  • 在任何目標平台上,沒有必要元素(字幕、標誌、CTA、主體)位於不安全的間距中;已用 safe_area.js 的框進行驗證。
  • 重新構圖是重新佈局或追蹤裁切,否則主體將會被遺失—絕非盲目的中心裁切或在動態作品上偷懶地使用模糊背景填補。
  • 第 0 幀在關閉聲音時可閱讀:一個鉤子、結果或主體—絕非黑色、裸露的標誌或淡入中。
  • 字幕是內嵌的、位於安全區域內、以短語分塊、≤2 行、高對比。
  • 循環類型是有意選擇的,且無縫循環的開場/結束影格已被指定為匹配。
  • 輸出是一份交給 remotion-compose / remotion-render 的規格—此技能沒有撰寫任何合成程式碼,也沒有執行任何渲染。

請勿

  • 請勿建立專案架構、撰寫合成程式碼或在此執行渲染—只需命名規格,並交由 remotion-setup / remotion-compose / remotion-render 處理。
  • 當主體不在中心時,請勿將 16:9 的來源以中心裁切方式轉為 9:16;您會把主體裁掉。請改用重新佈局或追蹤裁切。
  • 請勿將字幕、CTA 或標誌放在右側/底部的間距中,因為平台的動作列和字幕區塊會遮蓋它們。
  • 請勿依賴為社群平台上傳的 .srt/.vtt 側車字幕;請將它們內嵌到像素中,以確保它們總是被渲染,且您可以控制樣式。
  • 請勿以黑色、標誌開場或淡入開始—第 0 幀就是縮圖。
  • 請勿將一個 16:9 的檔案上傳到每個平台;直式動態消息會將其加上黑邊變成一條細帶。請按長寬比分別匯出。
  • 請勿超過平台的最大長度,並期望它「仍能貼文」—它會被截斷或拒絕;請在剪輯時修剪到限制內。
  • 請勿在此設計逐字字幕動畫—那是 kinetic-typography 的範疇;僅指定安全區域和時間。
  • 請勿在此規劃分鏡或鏡頭順序—如果影片還不存在,那是 video-storyboard 的範疇;此技能重新構圖的是已經剪輯完成的影片。
  • 請勿在此調整元素的運動方式(緩動、間距、跟隨動作)—那是 motion-design-principles 的範疇;此技能僅指定新的畫布和邊界。
  • 請勿在此為重新構圖選擇調色盤、對比度或光線—將這些決定交由 motion-color-and-light。
  • 請勿在此指導產品示範的內容或螢幕編排—那是 product-demo-director 的範疇;此技能假設內容已鎖定。
  • 請勿在此設計配樂、節奏同步或音效—字幕假設為靜音自動播放,但音訊是 sound-and-music-sync 的工作。

相關技能

這是影片工具包中的一個工藝技能;當請求實際上涉及其他技能的關注點時,請移交給同級技能,並將格式規格交給機械技能:

  • video-storyboard - 在影片存在之前規劃節拍和鏡頭順序。在此技能 之前 使用。
  • product-demo-director - 指導示範內容和螢幕上的編排。
  • motion-design-principles - 動畫的緩動、間距和移動工藝;在為新長寬比重新佈局畫面時依賴它。
  • motion-color-and-light - 調色盤、對比度和光線決策。
  • kinetic-typography - 逐字動畫字幕運動(您指定安全區域和時間;它設計動畫)。
  • sound-and-music-sync - 配樂和節奏同步;此技能刻意不觸及的音訊層。
  • remotion-compose / remotion-render - 消費此技能匯出規格以編寫按長寬比區分的 <Composition> 並匯出 MP4 的機械技能。

計算工具

獨立 Node 腳本。儲存為 safe_area.js 並使用 node safe_area.js 執行。它將每個平台的百分比安全區域邊距轉換為該平台解析度下的像素框,以便您可以將確切的佈局邊界交給 remotion-compose。無依賴項。隨著規格變化編輯 platforms 區塊。

// Social safe-area calculator. Run: node safe_area.js
// Insets are the % of each edge the platform UI covers (top/right/bottom/left).
// Right + bottom are large on 9:16 because of the action rail and caption block.
const platforms = [
  { name: 'TikTok',         w: 1080, h: 1920, top: 6,  right: 11, bottom: 17, left: 3 },
  { name: 'Reels',          w: 1080, h: 1920, top: 7,  right: 12, bottom: 18, left: 3 },
  { name: 'Shorts',         w: 1080, h: 1920, top: 5,  right: 12, bottom: 13, left: 3 },
  { name: 'X (in-feed)',    w: 1080, h: 1080, top: 4,  right: 4,  bottom: 12, left: 4 },
  { name: 'LinkedIn',       w: 1080, h: 1350, top: 4,  right: 4,  bottom: 10, left: 4 },
]

function box(p) {
  const insetX = (pct) => Math.round((pct / 100) * p.w)
  const insetY = (pct) => Math.round((pct / 100) * p.h)
  const x = insetX(p.left)
  const y = insetY(p.top)
  const safeW = p.w - insetX(p.left) - insetX(p.right)
  const safeH = p.h - insetY(p.top) - insetY(p.bottom)
  return { x, y, safeW, safeH }
}

for (const p of platforms) {
  const b = box(p)
  console.log(
    p.name.padEnd(14),
    `${p.w}x${p.h}`.padEnd(11),
    'safe box -> x:' + String(b.x).padEnd(4),
    'y:' + String(b.y).padEnd(4),
    'w:' + String(b.safeW).padEnd(5),
    'h:' + b.safeH
  )
}

執行範例輸出

TikTok         1080x1920   safe box -> x:32   y:115  w:929   h:1479
Reels          1080x1920   safe box -> x:32   y:134  w:918   h:1440
Shorts         1080x1920   safe box -> x:32   y:96   w:918   h:1574
X (in-feed)    1080x1080   safe box -> x:43   y:43   w:994   h:907
LinkedIn       1080x1350   safe box -> x:43   y:54   w:994   h:1161

解讀:在 TikTok 上,將所有必須閱讀的元素佈局在 x 32→961, y 115→1594 的範圍內。右側間距(動作列:按讚、留言、分享)佔用了最後約 119px,而底部(使用者名稱 + 字幕)則佔用了約 326px—在裝置上,位於這些區域的任何東西都會被遮蓋,儘管在 Studio 預覽中看起來正常。將這些作為佈局邊界傳遞給 remotion-compose;在一個 1080×1920 的直式 Composition 上,將字幕和 CTA 定位在框內,而不是原始畫面邊緣。

範本:export-spec

每個平台填寫一個區塊。這是 remotion-compose 和 remotion-render 會使用的簡報—從 safe_area.js 貼上安全區域數字。

SOCIAL EXPORT SPEC. [FILL: video name]. Source: [FILL: 16:9 master, 1920x1080]

PLATFORM: [FILL: TikTok / Reels / Shorts / X / LinkedIn]
  Aspect / resolution:   [FILL: 9:16 / 1080x1920]
  Max length:            [FILL: e.g. <= 60s in-feed]
  Safe box (px):         x:[FILL] y:[FILL] w:[FILL] h:[FILL]   (from safe_area.js)
  Reframe strategy:      [FILL: re-layout / center crop / blur-pad / punch-and-track]
    -> remotion-compose: [FILL: new Composition WxH + layout notes / crop keyframes]
  First frame (frame 0): [FILL: the muted hook shown at 0 - never black/logo/fade]
  Captions:              burned-in, [FILL: position in safe box], <=2 lines,
                         phrase-chunked, [FILL: style - size/contrast/backing]
  Loop:                  [FILL: seamless / hook-back / hard stop]
    -> if seamless:      frame 0 matches last frame at [FILL: position/color]
  Render:                remotion-render [FILL: preset, e.g. 1080x1920 H.264 MP4]

(repeat the block for each target platform)

references/platform-specs

在發佈前,請根據每個平台當前的創作者文件進行驗證;這些是穩定的形態,但限制會隨時間變化。長寬比和安全區域比確切的最大長度更重要。

  • TikTok - 9:16, 1080x1920。動態消息中的最佳長度是短篇(約 60 秒以下),上傳可以長得多。右側有厚重的動作列,底部有較高的字幕區塊;將必須閱讀的內容保持在高處並居中。有聲音文化,但仍需為無障礙和靜音自動播放加上字幕。
  • Instagram Reels - 9:16, 1080x1920。最長約 90 秒。與 TikTok 類似的右側/底部 UI,加上底部的個人檔案/音訊列。網格裁切是 1:1,因此中心也必須能作為一個方形縮圖被閱讀。
  • YouTube Shorts - 9:16, 1080x1920。最長 60 秒(任何更長的內容顯然會被截斷)。頭部的 UI 覆蓋層較淺,但底部有文字覆蓋層;將內容保持在幀內中心偏上。自動播放支援字幕(CC 按鈕),但還是要內嵌以確保樣式。
  • X (原 Twitter, in-feed) - 1:1, 1080x1080(或接近;裁剪行為取決於載入方式,但 1:1 最安全)。主題標籤列在底部,因此將 CTA/標誌放在上方或中央。影片在時間軸中循環,因此無縫循環是巨大的優勢。
  • LinkedIn - 4:5 (1080x1350)。原生直式。底部有「查看更多」截斷點,因此將長字幕保持在安全框內,並將關鍵視覺放在上半部。專業基調—無縫循環如果感覺過於「病毒式」可能不合適;硬停止搭配 CTA 或鉤子回返通常更好。

Individual skills in this repo

This repo contains 19 individual skills — each has its own dedicated page.

SkillMedev/skills

Designs REST API surfaces - resource naming, HTTP method and status-code semantics, error shapes, pagination, and filtering - and delivers an endpoint spec a consumer can build against without asking questions. Use when someone asks "how should I name this endpoint", "what status code should this return", "should this be PUT or PATCH", "how do I paginate this list", or is reviewing an API before it ships to external consumers. Do NOT use for planning breaking-change rollouts and deprecation windows - use api-versioning-strategist instead; for GraphQL type and resolver design - use graphql-schema instead; for generating client SDKs from an existing spec - use api-client-generator instead; for designing inbound webhook endpoints - use webhook-receiver-hardener instead.

SkillMedev/skills

Produce an accurate, properly timed caption track (SRT or WebVTT) from a video's audio - transcribing or aligning to the voiceover script, timing cues to speech, and enforcing line-length and reading-speed rules so captions are readable and in sync. Use when someone says "generate captions", "make subtitles from the audio", "transcribe and caption this", "export an SRT or VTT", "the captions are out of sync", or "the subtitles flash by too fast to read". Do NOT use to burn-in, style, reframe, or position an existing caption track for a platform (9:16, brand styling, safe areas) - that is social-video-formatter; do NOT use to animate text word-by-word as a motion graphic - that is kinetic-typography; do NOT use to write the spoken script in the first place - that is narration-script.

SkillMedev/skills

Turns data and charts into a decision-driving narrative structured as headline finding, trend, implication, and recommended action - with finding-led chart titles, context for every number, annotation guidance, and honest flags on any conclusion the data cannot support. Use when someone says "turn these numbers into a story", "what's the takeaway from this data", "help me present these results to leadership", or has charts but no narrative. Do NOT use for compressing a long document into a one-pager - use executive-summary instead - or for running the analysis that produces the findings - use eda-playbook instead.

SkillMedev/skills

Use when a task needs live or historical money data - "convert USD to EUR", "current/past exchange rate", "FX rate on this date / over this range", or "current price of Bitcoin/Ethereum, market cap, 24h change". Frankfurter (ECB reference rates, no key) is the FX default; CoinGecko's free keyless tier covers crypto. Do NOT use for stock quotes or equities - no keyless stock API survives verification, say so instead of guessing; do NOT use for country economic indicators like GDP or inflation series - use government-open-data instead; if the request is a vague "I need live data", route through public-data-api-picker.

SkillMedev/skills

Builds a driver-based FP&A operating model linking business inputs to P&L, balance sheet, and cash flow outputs. Use when building an annual plan, preparing investor materials, running scenario analysis, or stress-testing the business.

SkillMedev/skills

Use when a task needs live geographic lookups - "geocode this address", "what's at these coordinates" (reverse geocoding), "lat/lon for this city", "which country/state is this ZIP or postal code in", or "country facts: capital, currency, population, flag". Nominatim (OpenStreetMap) is the geocoding default; Zippopotam for postal codes; APICountries for country facts. All keyless. Do NOT use for weather at a location - use weather-climate instead; do NOT use for country-level statistics over time (GDP, population trends) - use government-open-data instead; if the request is a vague "I need live data", route through public-data-api-picker.

SkillMedev/skills

Runs the full Getting Things Done loop - capture, clarify, organize, reflect, engage - building a trusted system of context lists, a projects list with defined next actions, and a weekly review habit. Use when someone says "I'm overwhelmed and things are slipping through the cracks", "set up GTD for me", "help me do a brain dump and organize it", or "my to-do list is a mess". Do NOT use for just running the weekly review ritual itself - use weekly-review instead - or for clearing an email backlog - use inbox-zero.

SkillMedev/skills

Processes any email backlog to zero using the 4Ds - Delete, Delegate, Defer, Do - with a mass-archive strategy for the obvious, a touch-each-email-once discipline, and a keep-it-clear system of batched processing windows, ruthless unsubscribing, filters, and a minimal folder setup. Use when someone says "I have 5,000 unread emails", "help me get to inbox zero", "email is eating my whole day", or treats their inbox as a to-do list. Do NOT use for drafting the reply emails themselves or prioritization rules for an ongoing support queue - use email-triage instead - or for protecting focus time around the email windows - use deep-work-planner instead.

SkillMedev/skills

Write landing-page copy section by section - hero, social proof, features-as-benefits, objections, CTA - leading with one promise and proving it down the page. Use when someone asks "write my landing page", "improve my hero headline", "what should the homepage say", "turn these features into benefits", or is shipping a new page for a launch or campaign. Do NOT use for testing and optimizing an existing page's conversion rate - use landing-page-cro instead; for the one-line claim itself use positioning-statement; for the full message ladder use messaging-hierarchy.

SkillMedev/skills

Improves an existing landing page's conversion rate through evidence-first CRO - audit heatmaps and recordings, write structured hypotheses, prioritize with ICE scoring, and run one-variable tests to statistical significance. Use when someone asks "why isn't my landing page converting", "audit this page before we scale spend", "which A/B test should we run first", or after a CVR drop or ahead of a paid-traffic push. Do NOT use for writing a new landing page from scratch - use landing-page-copy instead. Do NOT use for auditing the ad accounts sending the traffic - use paid-acquisition-audit instead. Do NOT use for reading the results of a finished experiment - use ab-test-analyzer instead.

SkillMedev/skills

Runs structured coaching sessions using values clarification and the GROW model, ending every session with one committed action, a deadline, and an if-then plan for the likely obstacle. Use when someone says "I feel stuck in my life", "help me figure out what I want", "hold me accountable to my goals", or "coach me through this decision". Do NOT use for building a stress toolkit - use stress-management instead - or a journaling practice - use journal-framework; for a standing goal-tracking system, use goals-accountability. Coaching, not therapy: signs of clinical distress route to a licensed professional.

SkillMedev/skills

Adapts English content for a target language and region - swapping idioms, setting the right formality register, replacing cultural references, converting dates, units, and currency - and delivers the localized text with a notes column explaining each adaptation and flagging what needs a native reviewer. Use when someone asks "localize this copy for the Japanese market", "adapt our marketing copy for the Mexican market", "make this translation sound native instead of literal", or a literal translation reads foreign, stiff, or risky. Do NOT use for auditing in-product UI text quality - use ux-writing-audit instead.

SkillMedev/skills

Turns a natural-language video brief into a complete, ready-to-preview Remotion composition - extracts duration, scenes, brand colors, aspect ratio, and real copy; plans the frame budget; and writes data-driven React/TypeScript using useCurrentFrame, interpolate, spring, AbsoluteFill, and Sequence, registered in Root.tsx. Use when someone says "build a 20-second product demo video", "animate a feature walkthrough", "write the Remotion code for this marketing clip", or wants a scene-by-scene composition they can scrub in Studio. Do NOT use for rendering, iterating, or batching the finished MP4 - use remotion-render instead - or for installing and scaffolding the project - use remotion-setup instead.

SkillMedev/skills

Scaffolds a new Remotion video project wired for Claude Code Agent Skills - Node check, create-video scaffold, skills install, folder conventions, Google Fonts, and a smoke-test render. Use whenever someone wants to start making videos with Remotion and Claude, even just "make product videos with Claude.

SkillMedev/skills

Classifies incident severity (SEV1-4) using impact, scope, and urgency signals and decides who to page. Use when an alert fires or a report comes in and a severity call must be made quickly.

SkillMedev/skills

Use the Skill Me catalog from inside any conversation - discover, install, and manage Claude skills through the Skill Me MCP, and load installed skills automatically each session.

SkillMedev/skills

Write one platform-native caption from a topic and brand voice, with a front-loaded hook, native length, and a single earned CTA. Use when the user gives a topic (and optionally brand voice or a described image/video) and asks for an Instagram, LinkedIn, X/Twitter, or TikTok caption. Do NOT use when the user wants a dedicated standalone LinkedIn post - use linkedin-post-writer instead; or a multi-post X thread - use tweet-thread-builder instead; or to adapt one existing piece of content into versions for several channels - use cross-platform-reformatter instead.

SkillMedev/skills

Writes and tunes PySpark jobs - join strategy and broadcast size limits, shuffle-partition sizing, skew diagnosis and salting, UDF avoidance, caching, and output file layout - with concrete size and skew thresholds. Use when someone asks "why is my Spark job slow", "should I broadcast this join", "one task takes forever while the rest finish", "my job OOMs during a join", or is writing a new PySpark ETL job. Do NOT use for Kafka topic, consumer-group, or streaming-pipeline design - use kafka-pipelines instead; do NOT use for single-machine dataframe work that fits in memory - use pandas-expert instead.

SkillMedev/skills

Builds clean, performant, accessible SwiftUI views with correct state ownership, scoped invalidation, and smooth list scrolling, and reviews existing SwiftUI code against a concrete frame-time and re-render budget. Use when someone asks "why does my SwiftUI list stutter", "should this be @State or @Observable", "my whole screen re-renders when one row changes", "how do I animate this transition", or wants a SwiftUI view built or refactored. Do NOT use for cross-platform React Native apps - use react-native-pro instead; do NOT use for Flutter widget trees - use flutter-widget-architect instead; do NOT use for Android Compose UIs - use jetpack-compose-builder instead.

相關技能