Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Put the USER into a ~45s Japanese-anime football short as the hero — from their photo + their favorite team + the opponent. Anime-fies the user's face into a consistent character sheet, designs a dramatic 3-act match (come on → equalizer → winner) with the user scoring, writes three 15s cel-shaded scene prompts (CAPS names + Japanese dialogue), generates them on Seedance off the sheets, and stitches them. The "anime match" trend (Higgsfield+Claude) rebuilt on the Pika MCP, but the star is YOU. Triggers: "/world-cup-anime", "put me in an anime soccer video", "make me the anime football hero", "anime match with my photo". Requires the Pika MCP.
Generate unified, on-brand Instagram Reel covers for Yuval (YUV.AI Neon Phoenix system) — the signature look is a giant Hebrew headline BEHIND the subject cutout + a punch line IN FRONT (depth effect), on rich black with a dim neural-net field, series-colored chip + phoenix mark. Use whenever Yuval asks for an Instagram/Reel/TikTok/YouTube cover, thumbnail, עטיפה, קאבר, תמבנייל, cover image for a video, or wants his Instagram grid to look consistent. One command per cover; background removal included in the pipeline.
Pull recent YouTube transcripts from pre-selected channels and generate topic ideas from them. Use when someone says "mine YouTube", "find video ideas", "what are creators talking about", "YouTube research", "transcript ideas", "content mining", "what should I talk about", "topic ideas from YouTube", or wants to turn other creators' videos into their own content angles. World Code integrated — ideas map to your Bridge when available.
Viral video replication on short-video platforms. Supports referencing the structure of popular videos to generate videos in a similar style. Use this skill when the user mentions "viral replication" or expresses an equivalent intent to reference the style of a popular video and create content in a similar style.
Novel Character Profile Builder (小说人物档案创建工具) — A bilingual CN/EN skill for creating structured, detailed character profiles for fiction writing. Generates complete markdown profiles including backstory, personality, relationships, character arcs, and consistency checks. Supports protagonist, antagonist, and supporting character templates with built-in conflict detection and relationship matrix tools. Ideal for web novel (网文), fantasy, romance, and literary fiction authors.
Use when the user provides a plot summary, scene idea, character relationship, emotional beat, or short video concept and wants a cinematic AI video prompt. First diagnose the story, then rewrite it into a model-ready prompt for Kling, Seedance, Veo, Sora, Runway, Jimeng, or general AI video models.
Create short vertical videos (TikTok / Reels / Shorts / 抖音 / 快手 / 小红书) from a topic, a product link/image, or a script you already wrote. ClipForge runs the full pipeline — script → footage → voiceover → subtitles → BGM → compose — with a free, no-API-key path (free stock + Edge TTS + local FFmpeg). Use when the user wants to turn an idea, product, or written narration into a finished short video. Pipeline-correctness rules are hard; everything creative is your call.
Source pre-2016 cinema with gothic/occult sensibility, literary texture, and historical grandeur — build watchlists, curate Criterion/MUBI picks. Uses Perplexity for film discourse, Exa for web search, Firecrawl for scraping. Triggers on film recommendations, watchlist, gothic cinema, occult film, arthouse, pre-2016 movies.
Extract reusable visual systems from reference technical diagrams, architecture diagrams, scientific schematics, roadmaps, workflows, frameworks, and technical infographics. Create complete modular prompts, generate style-consistent PNG figures from new content, and save, search, name, validate, or reuse Style Packs with their original reference images. Use for 参考图风格抽取、技术图视觉语法、同风格技术图、技术路线图、架构图、科研示意图、方法框架图、风格模板库、保存或复用图片风格.
Godot 4.x game development (verified on 4.7) - scaffold, inspect and edit projects, scenes, UI, resources headlessly; author tilesets, ASCII-painted levels, themes, animation, audio buses, custom Resources, collision/navmesh bakes, shaders, export presets; draw pixel art from ASCII, clean generated art, synthesize sound effects and looping music; look up the installed engine's exact API; lint GDScript, scenes and shaders without Godot (Godot 3 renames, un-inferable :=, dead node paths, input actions, res:// paths); catch editor-only node warnings; move files safely; unit-test, smoke-run every scene with input fuzzing, debug, export; verify it all as text (node trees, UI layout, 2D/3D placement, level, image, audio read-backs), no vision or hearing needed. Use when Codex needs to build or fix a Godot game, write or repair .gd/.tscn/.tres/.gdshader files, add art, sound, levels or UI, migrate Godot 3 code, reorganize a project, or validate, test and export.
Menulis dan menyunting bahasa Indonesia sesuai konteks pembaca, tujuan, medium, serta EYD V. Gunakan untuk koreksi ejaan, parafrasa, penyuntingan, penjelasan kaidah, atau penyusunan naskah riset/akademik, cerita/puisi, komunikasi profesional, artikel populer, serta dokumentasi teknis dan teks antarmuka. Pertahankan fakta, tingkat kepastian, dan suara penulis; sesuaikan kedalaman revisi dengan permintaan.
Expert UI design skill. Creates high-fidelity HTML designs, interactive prototypes, slide decks, animations, and visual explorations. Use when user asks to design, prototype, create UI, make slides, create mockups, build interactive demos, design interfaces, or explore visual options. Triggers: /design, /prototype, /ui, /mockup, /slides, /deck, "design a", "prototype", "mockup", "make a UI", "create slides", "build a deck" 新手引导：输入 `/design 新手`、「这个怎么用」「第一次用」「能干嘛」时，走 SKILL.md 的〈新手上路〉，不要直接开始干活。
Use this skill whenever the user wants to isolate a piece of code, animation, or 3D experiment into a standalone JOYCO Lab experiment and publish it. Triggers include: "isolate this", "publish this to the lab", "create a lab experiment", "extract this animation/effect/scene", "submit to JOYCO lab", "make this an experiment". Also trigger when the user shows you a self-contained visual effect, animation, 3D scene, canvas sketch, or interactive component and wants to share or showcase it. Even if they don't say "lab" explicitly — if there's isolatable creative/technical code and a desire to share it, use this skill.
Execution skill สำหรับ Kie.ai API (Grok Imagine ผ่าน kie.ai proxy) — รับ prompt จาก /art-tech-engineer แล้ว gen ภาพ/วีดีโอผ่าน Kie.ai REST API รองรับ text-to-image, image-to-image, image-to-video, และ upscale ใช้เมื่อถูกระบุให้ใช้ Kie.ai โดยตรง หรือเมื่อ orchestrator delegate มา
Place a real product into a believable lifestyle or in-use scene (kitchen, bathroom, desk, outdoor, gym, bedroom, festive) for listing images, ads and social posts while keeping the product identical. Use for lifestyle scenes, lifestyle images, in-use photos, context shots.
Coordinate the end-to-end CAD/source-asset to SimReady workflow. Use for broad requests such as CAD to SimReady, source asset to simulation-ready USD, or prop packaging that require conversion, material/physics assignment, SimReady conformance, validation, and optional package creation; deploy or verify Content Agents services first when property assignment is enabled; route single-stage work through nested references.
Turn a user-provided photograph into a minimal two-sided 2:3 zine-style postcard. Preserve the original photo above, then create a sparse hand-drawn source-specific motif, minimal metadata, three sampled color swatches, and a matching functional postcard back
【Internal suite skill · Users usually don’t need to invoke it directly in the full workflow; simply describe the request to the orchestrator short-drama-director, which will route it to this skill automatically】【漫剧老李 V7.4.26 suite · Subskill】Feed adaptation engine (delivery layer): the final step from storyboard to feed-ready prompts. A/B/C output modes (C director-track clean version by default) + six pre-output gates (pacing / dialogue duration / word count / feed-ready semantics / image count / numbering consistency **+ asset-form consistency**) + asset mapping and character anchoring + **《Asset Connection Sheet》** + multi-segment transition strategy + cleanup of production jargon. **This package does not hold images**—images are generated by the user on external platforms; defaults to M1 (numbered placeholders), and must not request images or block the workflow due to missing images. Triggers: convert to Seedance, generate prompts, feed, prompt package, @ImageN, asset mapping, character anchoring, multi-segment transitions, too many words, clean up production jargon, asset form, connection sheet. This skill is a suite member; enter the complete workflow through the orchestrator short-drama-director.
【Internal suite skill · Users usually don’t need to invoke it directly in the full workflow; simply describe the request to the orchestrator short-drama-director, which will route it to this skill automatically】【漫剧老李 V7.4.26 suite · Subskill · Track ② Overseas drama】Overseas drama script specialist engine: rules for the script layer of non-Chinese body text / authentic regional speech in North America and elsewhere / multilingual / dialect projects. Core capabilities—language and style contract (established before writing and carried across stages, not a post-draft polishing label), three calibration states (region_unvalidated / evidence_calibrated / human_reviewed; models must not upgrade them independently), North American English dialogue adaptation, no inferring permissions from identity, monolingual listener boundaries, and local-detail eligibility. Triggers: overseas drama, English script, North American English, American dialogue, multilingual, dialect, localization, ESL, subtitles. This skill is a suite member; enter the complete workflow through the orchestrator short-drama-director; the track is selected and locked by the orchestrator at 〇·0.
【Internal suite skill · Users usually don’t need to invoke it directly in the full workflow; simply describe the request to the orchestrator short-drama-director, which will route it to this skill automatically】【漫剧老李 V7.4.26 suite · Subskill · Track ① Domestic drama】Specialist engine for scriptwriting and novel adaptation: executes a six-stage screenwriting chain (source registration → IP and character development → series development bible → episode planning → final script → five-seat roundtable review + polishing/rewriting after authorization), adapting novels, web fiction, outlines, or existing scripts into professional short-drama/animated-drama scripts with traceable sources, complete episodes, and performable dialogue. **Also includes an “external script polishing layer”—external standard scripts (only “Character: dialogue,” with no expression/action/state fields) → add performance and staging layers → adapt to this package’s storyboard rules; polishing adds only, changes nothing (no dialogue/events/characters changed), and the output must be returned to the user for confirmation**. Built-in anti-flattery principle, creative notes, five-perspective review, alert for overly high consensus in consultations, seven-dimension dialogue diagnostics (**checkup**) + **dialogue humanization engine (★ added 2026-10-13 · generation side: forms of address + written-to-spoken comparisons + four crumb-scattering methods + mechanical-sounding symptom list + stage ⑤ stopover)**, platform pacing matrix. Triggers: write a script, adapt a novel, novel to script, script adaptation, episodes, episode planning, development bible, story bible, IP development, script review, roundtable review, script polish, dialogue diagnosis, edit dialogue, pacing diagnosis, external script polish, adapt external script, add expressions to script, adapt script to storyboards, make dialogue conversational, humanize dialogue, dialogue sounds too mechanical, dialogue not conversational enough, unnatural forms of address, forms-of-address system. This skill is a suite member; enter the complete workflow through the orchestrator short-drama-director; **the track is confirmed and locked by the orchestrator at 〇·0 (1 domestic drama / 2 overseas drama / 3 commentary / 4 other), track ② overseas drama must be combined with sd-overseas-engine; the source type is confirmed and locked by the orchestrator at 〇·1 (1 original / 2 adaptation / 3 reference hit / 4 rapid topical); ③④ must first go through sd-recon-engine to produce an 《Reference Intelligence Card》 and be confirmed by the user; this engine preserves its source and classification (T1/T1.5/T2) in “① Source Registration”**.
Use this skill to create multiple social media assets as a coordinated pack. Triggers: "social media content", "content pack", "social assets", "campaign assets", "instagram content", "tiktok content", "launch kit", "marketing kit", "content series", "social media kit", "multiple posts", "content calendar", "batch content" Orchestrates: multiple images, short videos, and audio for social platforms.
Turn articles into hand-drawn explainer video B-roll. Given a WeChat Official Account article (text or link), prioritize extracting its original images, then turn its logic into an animated explainer video in a hand-drawn line-art style. Call real video models (Volcano Engine Seedance 2.0 or libtv Agent) to generate “hand-drawn growth” animation frame by frame, then assemble the final video. White background, black single-line icons, a single blue accent, thin curved arrows, 4:3 by default, designed to play under narration. Trigger when the user says “turn an article into an explainer video,” “hand-drawn explainer B-roll,” “animated whiteboard,” “make this article into an animated explainer,” or “generate B-roll with Seedance.”
Create Spotify playlists using spoti-cli CLI. Use when: (1) user wants a playlist, (2) user says "playlist", "spotify", "music for", "songs for", (3) user describes a mood or activity implying music ("deep work", "chill", "workout"), (4) user asks for music based on their day/vault/logs. Supports vault-aware playlist generation by reading Obsidian daily logs to infer mood and context.
Guides organizational and business storytelling—narrative structure (setup, tension, resolution), audience-tailored stories for executives, customers, boards, and teams, honest data and metrics framing, product and strategy narratives, incident and postmortem storytelling, and actuarial or insurance risk narratives for non-technical audiences. Covers story spine, key messages, and visual or slide narrative outlines. Use when the user says "tell the story", "storytelling", "narrative for executives", "data story", "board presentation narrative", "explain with a story", "story arc", "key message", "compelling narrative", "pitch story", or "incident story"—not cross-department reframing only (cross-department-translation), company-wide comms cadence and crisis wording packs (communication-lead), long-form creative fiction or screenwriting, brand copy without strategy context, or technical documentation and API reference (tech-writer-researcher).
Transcribe and automatically rough-cut a newly recorded Chinese talking-head video containing slips, false starts, repetitions, unclear delivery, and retakes, then create a verified preview and an editable Jianying draft. Use when a user asks an AI agent to clean up a Chinese spoken video, with or without an authoritative .md/.txt script, while preserving intended content and exposing every omission or uncertain take.
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.