Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Entry point for VoiceDrop. All capabilities live in the MCP (voicedrop.cn/mcp, 44 tools: article reading/writing and versions, writing style and distillation, mining and rewriting, community and tipping, compute, sharing/WeChat official accounts/Xiaohongshu, bookshelf reading and book writing/revision). This skill does one thing — connect you to that MCP: use its login tool to do 6+4 phone pairing login and get a token, then wire it into your client. Trigger words: "voicedrop", "登录 voicedrop", "voicedrop 登录", "接 voicedrop mcp", "voicedrop token", "/wjs-voicedrop".
Yichen's personal unified entry point for audio and video transcription, routing between StepFun Step ASR and Volcano Engine Doubao ASR based on output requirements, security boundaries, and availability. For plain-text transcription of local audio or video, timestamps, SRT subtitles, rough cuts of spoken narration, and pre-transcription health checks; when the user explicitly specifies a provider, do not switch silently. Use when a local audio or video file needs transcription and the correct ASR backend is unclear, or when the user explicitly invokes $yichen-asr.
Execute AdCP Creative Protocol operations with creative agents - build creatives from briefs or existing assets, preview renderings, and discover format specifications. Use when users want to generate or transform ad creatives, preview how ads will look, or understand creative format requirements.
Multimodal AI processing via Google Gemini API (2M tokens context). Capabilities: audio (transcription, 9.5hr max, summarization, music analysis), images (captioning, OCR, object detection, segmentation, visual Q&A), video (scene detection, 6hr max, YouTube URLs, temporal analysis), documents (PDF extraction, tables, forms, charts), image generation (text-to-image, editing). Actions: transcribe, analyze, extract, caption, detect, segment, generate from media. Keywords: Gemini API, audio transcription, image captioning, OCR, object detection, video analysis, PDF extraction, text-to-image, multimodal, speech recognition, visual Q&A, scene detection, YouTube transcription, table extraction, form processing, image generation, Imagen. Use when: transcribing audio/video, analyzing images/screenshots, extracting data from PDFs, processing YouTube videos, generating images from text, implementing multimodal AI features.
Use when generating dance or motion-transfer videos with Alibaba Cloud Model Studio AnimateAnyone (`animate-anyone-gen2`) using a detected character image and an action template. Use when cloning motion from a dance/action video into a target character image.
Use when generating lightweight talking-head portrait videos with Alibaba Cloud Model Studio LivePortrait (`liveportrait`) from a detected portrait image and speech audio. Use when you need long-form or simple broadcast-style portrait animation beyond the typical short expressive models.
Use when generating images with Alibaba Cloud Model Studio Z-Image Turbo (z-image-turbo) via DashScope multimodal-generation API. Use when creating text-to-image outputs, controlling size/seed/prompt_extend, or documenting request/response mapping for Z-Image.
Build portable, first-person colored ASCII city engines and small GIS-derived city packs. Use when designing terrain-following walking, raycast character rendering, city-provider schemas, or reproducible public-GIS ingestion. Do not use for conventional 3D/WebGL games, multi-level interiors, general GIS analysis, or committing full-resolution GIS archives.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
AI-powered video production suite: editing, transcoding, captioning, analysis, creation, shortform pipeline, image/video generation, web screenshots, AI audio/video enhancement. Uses FFmpeg, Whisper, PySceneDetect, FLUX.2, Veo, Playwright, Real-ESRGAN, Demucs, and Remotion. GPU-accelerated with NVIDIA NVENC. Use when user says "video", "ffmpeg", "trim", "cut", "transcode", "caption", "export", "analyze", "download", "create video", "shorts", "tiktok clips", "generate image", "generate video", "screenshot", "upscale", "enhance", "denoise", "separate vocals", "face restore", "slow motion", "remove background", or "/video".
Explicit-only last resort. Draws game art from code, with no image model - pixel sprites from a PixelSpec, flat vector props, UI and icons from portable SVG, rigged characters with planted feet, FX with a JS runtime, seam-proven autotiles, playable top-down layouts with collision, stylized parallax and ambient plate motion - palette-exact, with QA and review sheets. Use only when the user explicitly asks for code-drawn art, or when generate2dmedia route_media.py finds no image or video route (no-route, exit 3). Never the default - image generation (generate2dsprite, generate2dmap, video2dsprite) comes first for characters, props, maps and FX. Not for painterly, detailed or likeness art, HD-2D plates or realistic fire, smoke or water. Always disclose the result as code-drawn.
ElevenLabs AI music generation - create original music from text prompts via inference.sh CLI. Capabilities: text-to-music, custom duration up to 10 minutes, genre/mood/instrument control, royalty-free commercial use. Use for: background music, soundtracks, jingles, podcasts, video scores, game audio. Triggers: elevenlabs music, eleven labs music, ai music, generate music, music generation, compose music, ai composer, create song, soundtrack, background music, jingle, elevenlabs compose, music ai
Use when the user wants to create, generate, or compose music—whether from text description, custom lyrics, or instrumental background music. After submit, proactively poll task status every ~15–30s and message the user each time until completed/failed/timeout—do not wait for the user to ask for progress. Triggers: generate music, write a song, compose, create music, AI music, background music, instrumental, beats.
Drive the grok build CLI (run `grok`) for search, research, and media creation. Use for Grok/X web search with citations; large-scale parallel research via grok headless + subagents; generating images (image_gen) and videos (image_to_video) through the logged-in grok session at zero API cost; and ffmpeg post-processing like green-screen / chroma-key removal, concatenation, and watermarking. Cross-platform (macOS/Linux/Windows). Optional xAI search/media API as a paid fallback. Triggers include grok, grok build, 生图, 生成图片, 生成视频, 绿幕抠像, 批量调研, xAI search.
Removes the AI flavor from Chinese text so it reads like it was written by a human. Use when editing, reviewing or rewriting Chinese content. A Chinese localization of blader/humanizer (Wikipedia "Signs of AI writing"), combined with Chinese community discussions, AIGC detection research (CCL 2023 and others) and a practical word list. Identifies and fixes Chinese-specific AI writing patterns: grand openings, uplifting endings, lecture-style signpost words, the "not X but Y" binary construction, piled-up parallelism and antithesis, internet jargon, Europeanized translationese, dash abuse, overly dense punchlines, templated paragraphs and more.
Analyze nonfiction manuscripts for reader engagement signals, including heading-level word counts, slow starts, long slogs, weak takeaway titles, value pacing, beta-reader comment dropoff, and abandonment risks. Use when auditing a book, guide, manual, course-like draft, or technical manuscript for value density, reader experience, or beta-feedback engagement patterns.
Expert guide for the NotebookLM CLI (`nlm`) - a command-line interface for Google NotebookLM. Use this skill when users want to interact with NotebookLM programmatically, including: creating/managing notebooks, adding sources (URLs, YouTube, text, Google Drive), generating content (podcasts, reports, quizzes, flashcards, mind maps, slides, infographics, videos, data tables), conducting research, chatting with sources, or automating NotebookLM workflows. Triggers on mentions of \"nlm\", \"notebooklm\", \"notebook lm\", \"podcast generation\", \"audio overview\", or any NotebookLM-related automation task.
Create grounded paid-media creative concepts, copy angles, refresh hypotheses, and measurable test briefs across advertising platforms. Use for ad copy, creative briefs, UGC concepts, headlines, creative fatigue, asset ideas, or a creative refresh.
Removes and identifies AI watermarks and provenance marks in images and video the user generated or edited. Covers Gemini sparkles, SynthID, Microsoft InvisMark, Meta Content Seal, C2PA, EXIF/XMP/IPTC metadata, and Sora/Veo/Seedance/Doubao/Dola/Hailuo/Vidu/Kling and Wan labels. Use when the user wants to strip or clean AI watermarks and generation labels, or asks whether a file was AI-generated or carries AI provenance, even if they do not name remove-ai-watermarks. Do not use for stock-agency, marketplace, classifieds, or other third-party paid-asset watermarks.
Create polished audio content and save to Spotify. Produces episodes with TTS narration, a rich timeline (chapters plus in-player images, external links, and Spotify entity cards), and a cover image. Also use for raw media saves, show/episode management, and timeline navigation.
Professional short-drama scriptwriting skill. For short-drama topic selection, story outlines, character design, episode lists, single-episode scripts, self-checks and export; suited to Chinese short-drama scenarios such as urban romance, domineering CEO, sweet romance, rebirth and suspense.
Based on the story content described by the user, polish the storyline and split it into a storyboard script, then batch-generate storyboard illustrations in a consistent style. Offers 8 visual style choices and recommends the best style based on story type. Calls the Gemini API to generate images and saves them to the Obsidian image directory. Trigger words: "分镜故事", "故事板", "做个分镜", "创建故事板", "storyboard", "画个故事".
Generate thumbnail concepts and ideas for YouTube, TikTok, and other video platforms. Creates detailed visual briefs with composition, text, colors, and emotion suggestions. Use when planning thumbnails, improving CTR, or briefing designers.
This skill should be used when the user asks to "generate a UI sound theme", "create button click sounds for my app", "design notification sounds", or "build a coordinated audio theme for my dashboard or wallet app", "make game menu sounds", "create HUD feedback sounds", "design TV navigation sounds", "audit the sounds on my existing site", "check that transaction sounds are wired", "review UI audio wiring", or "edit a generated UI sound". Generates, audits, edits, and wires cohesive UI audio themes mapped to semantic interactions via ElevenLabs and ffmpeg, with an interactive local picker for auditioning, revising, reassigning, and accepting candidates.
Building AAA-quality games and real-time experiences with Unreal Engine 5. Use when "unreal, ue5, ue4, unreal engine, blueprints, blueprint, actor component, gameplay ability, gas unreal, niagara, nanite, lumen, world partition, level streaming, unreal multiplayer, unreal replication, gamemode, gamestate, playerstate, playercontroller, pawn, character class, uclass, ustruct, uenum, uproperty, ufunction, unreal, ue5, blueprints, c++, gamedev, aaa, real-time, rendering, nanite, lumen, niagara, gameplay, replication, multiplayer, gas" mentioned.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.