5.515 Plugins aus öffentlichen Claude Code marketplaces. Jedes bündelt Skills, Slash-Commands, Agents, Hooks oder MCP servers, die zusammen installiert werden.
claude-skillsqa-aman/claude-skills1
skiphowmzored/SkipHow1
auteuragiwhitelist/auteur1
quark-drivepmwl0128/quark_drive_skills1Reiche das repo mit .claude-plugin/marketplace.json ein und wir listen jedes plugin auf.
Marketplace einreichenAsk a question, get an answer with citations you can check. It runs from a two-minute lookup to a multi-week investigation with its own folder, and argues against its own findings before handing them over.
research166 ready-to-use Claude Code skills organised by job role, so a PM, QA engineer, designer, marketer or analyst can install the workflows for their own job in one command.
Design and build complete, distinctive web experiences — award-level product pages, cinematic scroll-directed sites, and multi-screen products as one design system. Art direction is committed before any markup, assets come from local CLIs, and nothing ships until it passes the anti-slop and motion gates.
designQuark Drive Skills: four Pokémon Champions skills for dex and metagame facts, exact damage and Speed calculations, and audited Singles/Doubles team building.
Audio/video → timestamped SRT in the source language. Chinese uses Volcano ASR; other languages use OpenAI Whisper with word-level timestamps + punctuation-bounded re-segmentation.
Translate an SRT from one language to another with punctuation-bounded re-segmentation. Simplified Chinese and English are first-class targets. Supports bilingual output.
Time-aligned TTS dub of a video against a target-language SRT. Volcano TTS for Chinese, edge-tts for everything else. Single-speaker by default; opt-in visual diarization for multi-speaker.
Final-composite step: burn SRT into pixels via libass, mix in a dub track, keep the original audio as a low-volume bed — all in one ffmpeg encode (no cascade).
Thin orchestrator for the end-to-end video localization pipeline (transcribe → translate → dub → burn). Use it when the user asks for full localization in one go.
Audio cross-correlation alignment for N recordings of the same event. Outputs `.sync.json` sidecars per file — never re-encodes the originals.
Auto-edit 2+ synced cams into a single MP4. Switches between angles second-by-second based on audio energy. Optional picture-in-picture.
Cut a long-form interview / lecture / podcast into 3–6 stand-alone topical short clips, with per-clip SRT — ready for downstream post-production.
Post-production overlays on top of a clip: AI-generated cover as first frame, HTML/CSS kinetic captions, illustration overlays, chapter chips, end-card CTA. HyperFrames-backed, single final encode.
Horizontal ↔ vertical conversion (16:9 ↔ 9:16, 4:3 ↔ 3:4). Crops a narrow band and tracks the active speaker via MediaPipe + mouth-aspect-ratio variance.
Batch upload videos to YouTube with per-video metadata from `UPLOAD_META.md`. Survives SOCKS/HTTP proxies by using `requests` directly for resumable upload.
Turn a 王建硕-style WeChat article into a narrated 1080×1920 portrait MP4 (30–90s) — Volcano TTS voiceover, HyperFrames CSS/GSAP per-scene animation, subtle SFX, abstract watercolor background.
Turn a single English word into an HLS supercut lesson from a video base — stitches every clip where the word is spoken, prepended with a bilingual intro card (word + IPA + 中文 gloss + usage, Volcano TTS) and a follow-me CTA card.
Polish a 微信公众号 (WeChat Official Account) article, generate a cover image (题图) and explanation illustration, and upload as a draft to mp.weixin.qq.com.
Mine a video's SRT — a monologue / 讲解, or an interview where 王建硕 is one speaker — into multiple standalone 微信公众号 articles, one per distinct topic.
