Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
This skill should be used when the user asks to "create an avatar from a photo", "generate a portrait avatar", "make a profile image", "convert headshot to styled portrait", "team member avatar", "character-style avatar", or needs likeness-preserving avatars in any style (including pixel art).
Drop a video and describe what you want — trimmed clips, color-corrected scenes, synced music, or a fully polished final cut. This best-video-editor skill handles the heavy lifting so you don't need years of editing experience or expensive software. Cut, crop, merge, enhance audio, add captions, and export in mp4, mov, avi, webm, or mkv. Built for creators, marketers, and storytellers who want professional results fast.
Bilibili video download — paste a Bilibili video link and parse it in one click to get a watermark-free video download link. Use when the user needs to download Bilibili videos, save Bilibili videos, or get direct Bilibili video links. Trigger words: B站视频下载, bilibili视频下载, B站视频解析, 下载B站视频, 哔哩哔哩视频下载.
Hand off a model from Blender (via BlenderMCP) into Unity (via MCP for Unity) — export the current Blender model, import it through import_model_file, and place it in the open scene. Use when the user has BlenderMCP and MCP for Unity both connected and wants to bring a Blender model into Unity. Does NOT drive Blender's own generators; BlenderMCP owns how the model got into Blender.
Blender automation with geometry creation, materials, modifiers, and Mixamo animation retargeting. Core Features: WebSocket-based real-time control, automatic bone mapping with UI review, two-phase confirmation workflow, quality assessment, multi-project support, comprehensive CLI commands. Use Cases: Create 3D primitives (cube, sphere, cylinder, etc.), manipulate objects (transform, duplicate, delete), manage materials and modifiers, retarget Mixamo animations to custom rigs with fuzzy bone matching.
Chinese content quality acceptance tool, the main entry point (gateway) of the writing series. Performs a comprehensive checkup (16 items) on a Chinese draft from four perspectives — editor, reader, author, platform — and outputs a score + issue list + routing recommendations. It does not revise; it only accepts and routes. Triggers: review my Chinese article, check this article quality, Chinese writing diagnosis, proofread this piece, is this article good enough. Not for: direct rewriting (→ humanize-ai / editor-revisor), only changing title/layout/punctuation (→ packaging-workshop), can't find your own voice (→ voice-dissolver).
Master the AI tools that generate unlimited content at scale. From stunning images to professional videos, voiceovers to compelling copy - create content that used to require entire teams. Use when "need images, create video, generate content, voiceover, marketing visuals, social media content, ad creative, content, images, video, audio, writing, marketing, creative" mentioned.
Check long-form Chinese web novels for continuity and logical consistency. Use when users worry that a long story will contradict itself, fall apart after a hundred chapters, or drift from its established setting; want to check timeline consistency, whether character behavior makes sense, resources appearing from nowhere, identities being suddenly revealed or concealed, injuries not carrying over, power levels jumping, or want a logic check of one arc or the whole book. Check six logic chains and the timeline chapter by chapter, identify conflicts with earlier chapters or records, and suggest fixes.
Distill a crush into an AI Skill. Import chat history, photos, social media, generate Relationship Memory + Persona, with continuous evolution. | Distill a crush into an AI Skill, import chat history, photos, social media, generate Relationship Memory + Persona, with continuous evolution.
Douyin content creation and operations assistant. Douyin operations, Douyin follower growth, short video creation, Douyin titles, Douyin tags, Douyin SEO, Douyin account operations, Douyin data analysis, Douyin topic selection, Douyin scripts, Douyin copywriting, Douyin comment section operations, Douyin persona positioning, Douyin posting times, DOU+ campaigns, Douyin traffic, short video operations, video ideas, livestream scripts, hashtag strategy, duet and remake ideas, Douyin monetization, product promotion Xingtu, Douyin con.
Digital signal processing algorithms and techniques for real-time audio. Covers filter design (biquad, Moog ladder, SVF, FIR, Linkwitz-Riley), audio effects (delay, reverb, dynamics, modulation, distortion, stereo processing), sound synthesis (oscillators, bandlimited waveforms, FM/PM, noise generation, envelopes), spectral analysis (FFT, envelope detection, beat detection), and DSP utilities (fast math, interpolation, denormal prevention, dithering). Use this skill whenever implementing audio DSP in C/C++, building synthesizers or effects, writing filter code, generating waveforms, or any task involving digital audio processing — even if the user doesn't explicitly mention "DSP."
Generates high-fidelity visual assets, logos, and UI mockups using the media-management MCP server. Trigger this skill whenever the user asks to generate an image, create a logo, produce a hero banner, design a UI icon, or build a visual asset. It is explicitly designed to handle technical specifications including file formats (PNG, JPEG, WEBP), specific dimensions (e.g. 1024x1024), and transparency requirements. Use this skill when the user needs to integrate generated imagery into application code or web pages. It ensures consistent output quality and provides a standardized SVG fallback if the generation tool is unavailable
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases. Credits: Original skill by @blader - https://github.com/blader/humanizer
Generate a magazine-style character sheet from a portrait. Provide EITHER portrait_url (must be R2-hosted) OR portrait_image_base64 (PNG/JPEG, ≤10 MB; the API will upload it to R2 first). Optional ≤10-word description for name/age/vibe hints.
Speech synthesis using MiMo-V2.5-TTS models. Supports preset voice synthesis, text-to-voice design, voice cloning, natural language style control, and streaming output. Trigger whenever the user wants to generate speech audio from text, especially with Chinese voices and style control. Requires MIMO_APIKEY environment variable.
H3 prompt writing for lyric spatial text-overlay MVs: locking beats to lyrics, dividing work across three cards (character / scene / text), and multi-shot Vocal / Typography / Visual scripts. Applies to stylized MV prompts. Not applicable to ordinary subtitle burn-in instructions.
Create parametric OpenSCAD 3D models of workshop tools (drill presses, vacuums, saws, etc.) for workshop layout planning. Use when asked to "model a tool", "create OpenSCAD for [tool]", "add [tool] to workshop", or when planning workshop layouts that need tool representations. Supports brand-accurate colors (Bosch, Festool, Makita, DeWalt, Milwaukee) and standardized code structure with customizer parameters.
Optimizes audio memory, CPU cost, and playback quality through import settings and mixer configuration. Use when asked to reduce audio memory or Audio Mixer CPU cost, change clip Load Types, sample rates or codecs, or force 3D audio to mono.
Content Packaging Workshop — the final step in the writing series. Handles the presentation layer after content is finalized: title polishing, opening hooks, layout optimization, punctuation cleanup (integrates with zan-punct-fix), image suggestions, platform adaptation. Does not change the body content. Six modules can each be triggered independently. Triggers: help me polish the title, this title isn't good enough, how to write the opening, check the layout for me, paragraphs are too dense, punctuation check, review the images, which platform does this article suit, going to publish — run through the packaging, check if there are presentation problems, the content is fine but tiring to read, do a pre-publish check for me. EN: "polish the title", "fix the opening hook", "check layout", "fix punctuation", "review images", "platform formatting", "pre-publish checklist". Not for: body content rewriting (→ humanize-ai / editor-revisor), content quality diagnosis (→ chinese-write-checker), voice calibration (→ voice-dissolver).
Make a papercut reel, video or explainer end to end. Short vertical (9:16) cut-paper explainers from a link (repo, product page, announcement), idea to mp4. Also routes partial asks to the stage skills and hands out the style prompt for other tools
Write or fix the hook of a papercut reel. Produces the SAY / WRITE / SHOW / ALIGN block, five variants scored with the hook check, the frame-0 cover title and the motion out of the hook. Use for "write a hook for...", or when a reel's first three seconds lose people
Check a papercut reel's stills against the style DNA and the storyboard. Renders contact sheets at a few timestamps, runs the full checklist, then writes the delivery summary. Use for "QA the reel", "check my scenes look like paper", "is this ready to post"
Turn a link into a papercut reel script. Researches a sourced facts list, writes the 75-95 word script on the 10-beat spine, a banner fact track, a staging table with one set per banner, and the humour pass. Use for "write the script", "research this repo for a reel"
Install, check or upgrade the papercut toolchain. Runs the doctor, asks how much to set up (Minimal, Standard, Full), then runs install.sh with flags and fixes dependency errors. Use for "set up papercut-explainer", "install papercut", "check my papercut install", "set up the voice", "why won't it render"
Storyboard a papercut script before any code. Writes the Camera / Cut table, one block per scene with frame-level events on each stressed word, the SFX plan and the proof beat. Use for "storyboard this script" or "plan the camera moves and cuts"
Voice a papercut reel and time it to the picture. Three paths, local Qwen3-TTS, your own recording or another TTS, or a placeholder voice. Covers delivery rules, voice.json, captions and scene timing. Use for "set up the voice", "re-voice this", "time the script"
Proofreading Chinese web novels for typos and checking sensitive/forbidden content before submission. Use when the user wants to check typos (的地得/在再/做作 etc.), scan for sensitive or banned words, self-check a manuscript before submitting, ask "will this passage be blocked/flagged/rejected", or "mark typos like 番茄 does and give one-click replacement suggestions". Scans sentence by sentence and provides an "original word → suggested word" table for one-click replacement by the author.
The machine has to stay one machine while the camera does all the work. Lock the vehicle part by part, then fill the runtime with a numbered cut list that moves the camera every second. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (Cars and vehicles at speed; 中文触发词: 汽车与载具速度片, 汽车, 赛车, 摩托, 载具), or asks how published cases of this type were prompted. Read references/cases.md before drafting
Every shot carries its own timecode and shows one visible change on a body. The dread comes from the chain — a look, veins, a bite, the next person — and the ending seals a door without settling anything. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (Horror and suspense; 中文触发词: 恐怖悬疑短片, 恐怖, 悬疑, 惊悚), or asks how published cases of this type were prompted. Read references/cases.md before drafting.
One traveller moves through a place scene by scene, each scene carrying its own timecode, its own location and one short line. The polish is bought with film grain and golden-hour light. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (Cinematic travel vlog montage; 中文触发词: 电影感旅行漫游, 旅拍, 城市漫游, 旅行), or asks how published cases of this type were prompted. Read references/cases.md before drafting
Publish the approved final video to platforms such as YouTube, Douyin, WeChat Channels, and Xiaohongshu. Use when the user asks to post a video, publish it across platforms, upload to YouTube, post to Douyin/WeChat Channels/Xiaohongshu, or schedule a post. Check the video version, thumbnail, subtitles, title and description, and AI/copyright disclosures for each platform, then prepare a platform-specific publishing package. Upload as private, draft, or scheduled only after the user authorizes each platform, using official APIs, form-filling assistants, or upload tools available at runtime; never publish everywhere with one click. If uploading is unavailable, provide a manual publishing package.
Design of satisfaction beats and face-slapping scenes for Chinese web novels. Use when the user wants to design face-slapping, hiding one's strength, showing off, comeback, revenge, or crushing the villain, or complains that the plot "isn't satisfying enough / is too bland / readers say there are no payoff moments". Produces a three-part payoff loop and a four-beat face-slap structure, and ensures payoff escalation without repetition.
Creative Designer skill. Takes a post concept, a client product photo, or a real lifestyle photo and produces on-brand social media visuals using the client's brand style guide. Four modes — Generate (AI image from concept), Composite (client product photo anchored in an AI-generated scene), Brand (apply text overlay treatment to a real client photo), Stop-Motion Reel (6-frame action sequence exported as MP4). Reads brand-style.md, builds prompts, generates/edits images via Nano Banana MCP, outputs images + prompt log + creative brief.
Social-SBTI — scrapes public activity from Jike / X and generates a spoof SBTI personality card. Wizard-style flow: user triggers → pick platform → paste URL → automatic check/configure credentials/scrape/score/render → card output. Trigger scenarios: - user says "跑一下 social-sbti" / "启动 social-sbti" - user says "帮我分析 @某某 的 SBTI" - user says "用 social-sbti 分析 @某某" - user says "给 XXX 来个社交版 SBTI 人格卡"
Create and debug Three.js shaders with ShaderMaterial, RawShaderMaterial, uniforms, varyings, GLSL vertex and fragment programs, texture sampling, procedural effects, onBeforeCompile extensions, shader chunks, instancing, and GPU performance checks. Use when writing custom GLSL, extending a built-in material, animating shader uniforms, or diagnosing shader compile, coordinate-space, and rendering issues. Triggers on: Three.js shader, ShaderMaterial, RawShaderMaterial, GLSL, uniforms, varyings, onBeforeCompile, fragment shader, vertex shader, fresnel, displacement, shader chunk.
Generate cinematic AI image prompts for YouTube thumbnails, LinkedIn posts, and social media visuals in Dhruv's signature style. Use when user asks for a thumbnail, image prompt, social media visual, cover image, or any AI-generated image for content.
A one-shot skill that generates a fun short video about "my claw's first reaction after getting a FluxA card". Uses Kling video generation via FluxA Agent Wallet x402 payment — no Kling API key required. The agent guides the user to choose a scenario, generates a 4-act storyboard prompt, pays for Kling via x402, and saves the video locally.
Twitter Video Maker — Create Engaging X and Twitter Video Posts with AI. Text tweets plateau at a few hundred impressions. Video posts on X get ten times the algorithmic push — but nobody opens Premiere for a thirty-second opinion. Paste your thread or talking points, choose a format — animated text on a branded background, a talking-head recording with burned-in captions, or a screen walkthrough with highlight callouts — and the AI delivers a file sized for the feed within seconds. Auto-fits the 2:20 duration ceiling. Bold subtitles bake in because most of the timeline scrolls on mute. Your handle stays pinned so quote-tweets still credit the source. Line up an entire week of posts in one conversation. Built for brand accounts posting daily, indie founders documenting the build, newsletter writers repurposing editions into clips, and commentators who learned that nothing goes viral on X faster than a face plus a hot take. Supports mp4, mov, webm, png.
UE5.6-UE5.8 PCG building generation workflow for modular buildings, blockouts, facade rules, and runtime generation. Use when requests involve Procedural Content Generation (PCG), Shape Grammar, lot-based building spawn, deterministic random seeds, density/filter pipelines, or converting designer constraints into reusable PCG graphs.
Voice calibration before writing — before rewriting, first figure out which real me is hidden in this text. By default it outputs a voice anchor card (can be passed directly to humanize-ai / editor-revisor as a protected zone); deep mode outputs a full voice map plus follow-up questions. It does not rewrite. Triggers: dissolve the AI taste, find my real voice, what did I actually want to say here, get the real me back in the text, AI smoothed away my edge, doesn't sound like me. Not for: direct rewriting (→ humanize-ai / editor-revisor), content checkup (→ chinese-write-checker), title/layout/punctuation polishing (→ packaging-workshop).
End-to-end writing assistant for WeChat Official Account articles. Supports trending topic selection, article writing, AI de-flavoring polish (removing the machine feel), image suggestions, and one-click publishing to the Official Account drafts folder. Suited to technical bloggers, self-media creators, and corporate Official Account operations. Use this skill when users need to write Official Account articles, polish content, find images, or publish to WeChat.
Write and ship a blog post for your project that reads like a human wrote it and pulls SEO traffic to your site. Use when a contributor wants to draft, edit, or publish a blog post, add a post to the site, write about the project for search/traction, or make an existing draft sound less like AI. Enforces the house voice (no em dashes), picks a non-cannibalizing angle, uses ASD-STE100 Simplified Technical English for technical prose, wires the post into your site, and runs the humanizer pass before shipping.
Write articles from documents — convert PDF, DOCX, EPUB, URL, YouTube, or text into a series of Vietnamese articles in a chosen style (7 presets or custom 5 dimensions). Supports documents from a few pages to 100K+ words with tier-based processing. Output at CWD/writer-agent/.
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.