Plugins

Automated topic-driven video podcast creation — research → script → TTS (7 backends: Edge / Azure / Doubao / CosyVoice / ElevenLabs / Google / OpenAI) → 4K Remotion render → BGM mix → Remotion-native subtitles. Multi-platform: Bilibili / YouTube / Xiaohongshu / Douyin / WeChat Channels. Outputs horizontal long-form (16:9 3840x2160) and vertical shorts (9:16 2160x3840). 15-step workflow with mandatory Studio preview, agent-native JSON envelope CLI, and per-video isolation via --public-dir.

Use when crafting video or motion prompts for any generative model — dramaturgy, camera, physics-safe motion, frame anchors, and clip chaining.

Turn any video into a Chinese-narration recap (understanding -> narration -> cut -> voiceover -> assemble) on ffmpeg + one Xiaomi MiMo API key. A bundle of independent skills + a thin orchestrator. macOS / Linux / Windows.

Turn any video into a Chinese-narration recap (understanding -> narration -> cut -> voiceover -> assemble) on ffmpeg + one Xiaomi MiMo API key. A bundle of independent skills + a thin orchestrator. macOS / Linux / Windows.

Remove backgrounds from videos for transparent clips, alpha-channel footage, and green-screen-free overlays. Segment moving subjects from background using Bria's video editing pipeline. Dedicated video background removal skill — transparent webm/mkv output, solid-color backgrounds for MP4, local file upload, and batch video processing.

Write polished, ready-to-shoot video scripts for YouTube, TikTok, Reels, ads, and more — with .docx export

看视频（抽帧+转录回答问题）与翻译视频（转写+翻译+烧录中文字幕+出文稿）双技能。

Analyze a video transcript and create Claude Code skill files from the teachable frameworks and actionable advice it contains.

Tools for downloading and clipping videos from the internet

Analyze local video files with Gemini multimodal models and timestamped, grounded answers.

from chadpod/viewing-macos-screenshots-claude-code-plugin

Observability & reliability engineer — monitoring, alerting, SRE, incident response, SLOs

Television (tv) fuzzy finder expertise for terminal workflows and channel creation

from emirrtopaloglu/virtuoso

Skills for Claude Code development workflows

Analyze Claude Code plugins and visualize development artifacts as interactive HTML or diagram-enhanced markdown reports. On a capable account, HTML reports publish as claude.ai Artifacts by default (doc-visual, diff-visual, plugin-visual, context-health-visual); add --local for a local design-system + Mermaid file. Six skills: plugin-visual (local/installed/GitHub plugin audits with security + architecture), diff-visual (git diffs, with side-by-side split-diff of the actual changed code and File Map change-flags), doc-visual (markdown docs with Mermaid diagrams), fact-check (claim verification against code + git history, republishing corrections to the same Artifact link), context-health-visual (environment health with skill-security scan and hook schema validation), report-manager (list/open/delete/search/refine, surfacing stored Artifact URLs and republishing to the same link). Every report supports --format md, --lang, and in-browser per-section feedback.

VisionSqueezer for Claude Code — MCP server (optimize_image / sandbox_execute / get_savings_stats) bundled with the vision-doctor, vision-upgrade, and vision-stats skills. One install brings everything.

Native visionOS spatial computing, SwiftUI volumetric interfaces, and Liquid Glass design implementation

Apple Vision Pro 应用与空间计算体验开发专家

Comprehensive visual identity audit for competitive brand research. Analyzes logo, color, typography, packaging, photo direction, SNS, web, and app across competitors.

Research-backed visual design principles for websites, presentations, documents, and any visual medium — grounded in VisAWI, Gestalt psychology, and empirical aesthetics research

Image generation, vector art, generative art, and motion/video production (Remotion, Blender, After Effects).

Writes a durable, committed Markdown ADR/plan as the source-of-truth record, and — only when the content needs visuals markdown can't express (wireframes, annotated split-diffs, before/after columns) — also emits a self-contained rich plan.html to /tmp. Markdown canonical, HTML disposable; no backend.

Generates a Playwright spec that crawls a sitemap and checks every route at 375/768/1440 viewports for horizontal overflow, clipped fixed elements, zero-height containers. CLI emits the spec; user invokes Playwright.

Produce a single self-contained HTML visual report — an explainer, writeup, or diagram-heavy document built with Tailwind and Mermaid via CDN plus hand-crafted CSS/SVG.

Use when someone wants a montage with transitions between shots — action-sequence reel or multi-scene piece where narration is optional.

Visual expression system for AI personas with emotion-based face switching

Data visualization using D3.js, Leaflet and AG Grid - charts, network graphs, timelines, trees, calendars, flowcharts, kanban boards, tables and maps

Interactive HTML visualization companion — push diagrams, mockups, and explorers to a browser window

Interactive HTML visualization companion — push diagrams, mockups, and explorers to a browser window