视频·图像·音频技能

Use apko to build small OCI images from declarative package manifests when supply-chain clarity and minimal contents matter more than a conventional Dockerfile flow.

中文简介正在准备中。当前显示原文说明。

Download a supported video URL with yt-dlp and upload the preserved file plus metadata to archive.org as a repeatable preservation job.

中文简介正在准备中。当前显示原文说明。

Track approved container images and write back the matching GitOps manifest changes instead of hand-editing tags across Argo CD applications.

中文简介正在准备中。当前显示原文说明。

Give Claude Code a video perception layer that extracts frames, transcribes audio, and lets Claude answer questions about local videos or YouTube URLs.

中文简介正在准备中。当前显示原文说明。

Calls Adobe Firefly's text-to-image and generative fill APIs for batch asset creation. Manages Adobe IMS OAuth tokens and enforces Content Credentials (C2PA) metadata on all outputs.

中文简介正在准备中。当前显示原文说明。

Inspect captured RAM images to enumerate processes, modules, handles, and suspicious in-memory behavior before escalation or evidence handoff.

中文简介正在准备中。当前显示原文说明。

Generates marketing images using the mcp-image MCP server. Reads brand guidelines for style consistency. Supports social posts, blog headers, ads, and presentation visuals.

中文简介正在准备中。当前显示原文说明。

Use when you want marketing visuals generated from brand guidelines for posts, blog headers, ads, or decks.

中文简介正在准备中。当前显示原文说明。

Use when the user wants to post or schedule to a Telegram channel or group through Publora, using a bot. Covers Telegram markdown, silent delivery, link previews and forward protection. Bot API caps media captions at 1,024 characters and videos at 50 MB. Not for other platforms (each has its own skill).

中文简介正在准备中。当前显示原文说明。

Use when the user wants to post or schedule to Bluesky through Publora. Handles the 300-character cap, auto-detected hashtags and links, up to 4 images, and videos. Alt text cannot be set through the API. Needs a Bluesky app password, never the main password. Not for Mastodon (use social-post).

中文简介正在准备中。当前显示原文说明。

Use when the user wants to post or schedule to X (Twitter) through Publora, including threads auto-split past 280 characters, up to 4 images, or a video up to 140 seconds. X needs a paid Publora plan. Not for Threads or Bluesky (each has its own skill).

中文简介正在准备中。当前显示原文说明。

Create and schedule Threads posts, multi-part chains, image carousels and reply control via Publora MCP. Use when the user wants to post to Meta's Threads, including long content that Publora splits into a connected chain of replies past 500 characters. Not for Instagram (use instagram-post) or X threads (use x-post).

中文简介正在准备中。当前显示原文说明。

Use when the user wants to post or schedule to YouTube, a Facebook Page or Mastodon through Publora. YouTube needs a video on every post, Facebook publishes to Pages only, Mastodon caps at 500 characters. Not for the platforms that have their own skill.

中文简介正在准备中。当前显示原文说明。

Plan and batch-produce social media content across platforms (Instagram, X/Twitter, TikTok, LinkedIn, YouTube). Generates a week or month of posts with platform-specific formatting, hashtags, hooks, and posting schedule. Use when "social media posts", "social calendar", "plan social content", "Instagram posts", "tweets", "LinkedIn posts", "TikTok ideas", "social media strategy", "batch social", or any request to systematically produce social media content.

中文简介正在准备中。当前显示原文说明。

Full-stack video production from script to rendered video. Combines script generation (optimized for TikTok/YouTube/Reels) with AI-powered video rendering using Remotion, AI voiceovers (Qwen3-TTS/ElevenLabs), music generation (ACE-Step), and browser-based demo recording. Multi-session project tracking with automatic intent reconciliation. Use when "create video", "produce video", "demo video", "product video", or any request to generate AND render video content.

中文简介正在准备中。当前显示原文说明。

Launch a podcast or plan podcast guest strategy — format, content planning, episode production, guest outreach, and distribution. Use when "podcast", "start a podcast", "podcast marketing", "podcast guest", "podcast strategy", "be a podcast guest", "launch a show", or any request related to podcast creation or guest appearances.

中文简介正在准备中。当前显示原文说明。

Take one pillar content piece and produce 15-25 derivative assets across platforms — social posts, email, LinkedIn article, video scripts, newsletter section, infographic brief, and more. The ultimate content multiplier. Use when "repurpose this", "turn this into", "make social posts from this blog", "content repurposing", "1 to many", "atomize this content", "extract posts from", or any request to derive multiple pieces from one source.

中文简介正在准备中。当前显示原文说明。

Produce video scripts and clipping plans for TikTok, YouTube Shorts, Instagram Reels, and long-form YouTube. Generates hook-first scripts optimized for each platform's algorithm, plus a clipping plan to extract short-form from long-form content. Use when "video script", "TikTok script", "YouTube script", "Reels script", "Shorts script", "video content", "clipping plan", "video ideas", or any request to create video content for social platforms.

中文简介正在准备中。当前显示原文说明。

Build an exhaustive first-growth-hire distribution operating system across B2B and B2C channels: LinkedIn, events, AI outbound, AEO, blogs, long-form writing, YouTube, webinars, X, influencers, AI UGC, organic TikTok, paid social, sponsorships, partnerships, lifecycle, referral, and community. Use when "growth hacker", "first growth hire", "distribution hire", "cover every channel", "channel hacking", "0 to ARR growth system", "growth operator", "growth hacker OS", or any request to fan out channel operators and plug the result into Kai workflows.

中文简介正在准备中。当前显示原文说明。

Generate, rank, and gate a reusable hook bank — sourced pains × named hook formula families, scored on clarity/specificity/curiosity/proof-backing, gated at the 10/16 ad threshold, delivered in 3 lengths with per-hook provenance and downstream routing. Use when "hook bank", "generate hooks", "hook generator", "write hooks for", "ad hooks", "scroll stoppers", "opening lines", "hook ideas", "first 3 seconds", "hook matrix", "I need 50 hooks", or any request to batch-produce attention-openers for ads, social, or video.

中文简介正在准备中。当前显示原文说明。

Inspect and manually purge the Soniox artifacts — transcriptions and uploaded audio files — that offline transcription leaves behind, on dev or prod. Use when offline transcription silently stops working, when Soniox answers 429 `limit_exceeded`, when `SonioxTranscriberTest.OfflineTranscribeWorks` and `CleanerDeletesEnqueuedArtifacts` fail together, or when the user says "sweep Soniox", "soniox/sonoix sweep", "sonoix swipe", "purge Soniox", "check Soniox files", or "is Soniox at the cap".

中文简介正在准备中。当前显示原文说明。

阿杭减肥系列视频制作入口。用于减肥口播剪辑、续剪和已确认完整交付，选择本系列范围后调用另行安装的剪辑引擎与减肥封面流程。

中文简介正在准备中。当前显示原文说明。

阿杭AI博主系列视频制作入口。用于AI博主口播剪辑、剪后逐字稿和对应封面，选择本系列参数后调用另行安装的剪辑引擎与封面Skill。

中文简介正在准备中。当前显示原文说明。

Natural-language TV control via the stv CLI. Use for any request about playing, pausing, resuming, or stopping content on a smart TV; controlling volume or mute; switching to Netflix, YouTube, Spotify, Disney+, Apple TV+, or Prime Video; binge-watching a series; casting a URL to the TV; or anything the user says like "거실 TV 켜줘", "뭐 보여줘", "TV 꺼", "볼륨 낮춰", "몰아보기", "다음 화", "좋은 밤", "영화 볼게", "노래 틀어줘", "play / pause / volume / resume / Netflix / YouTube / Spotify".

中文简介正在准备中。当前显示原文说明。