Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Run an opt-in evidence-backed second pass on a complete Blender deliverable. Use when the user explicitly asks to critique, improve, repair, iterate, or apply a practice-makes-perfect loop; when a benchmark fixture explicitly requires retained before-and-after evidence; or when a completed candidate must be improved without regressing its existing technical or visible qualities.
Expert in designing and implementing visceral, satisfying combat systems. Masters hitbox/hurtbox design, frame data, combo systems, enemy archetypes, damage feedback, and the invisible craft that makes players feel powerful. Draws from fighting games, character action games (DMC, Bayonetta), and Souls-like design to create combat that is readable, responsive, and endlessly replayable. Use when "combat system, combat design, hitbox, hurtbox, frame data, hitstop, screen shake, input buffer, coyote time, i-frames, invincibility frames, combo system, attack cancel, recovery frames, punishment window, souls-like combat, action game combat, fighting game, damage feedback, enemy design, boss design, attack telegraph, parry system, stamina system, poise system, weapon feel, game feel combat, melee combat, combat juice, combat, action-game, fighting-game, hitbox, frame-data, game-feel, souls-like, character-action, melee, enemy-design, boss-design, combo, parry, i-frames" mentioned.
Analyze one or more cycling, running, or hiking FIT/KML activity tracks, generate evidence-based single or aggregate reports, open the bundled local Ride Relief report page when the environment supports it, enrich results with user-confirmed public location context, and create shareable PNG or H.264 MP4 route stories on request. Use whenever a user wants to analyze, compare, visualize, or export .fit or .kml activities, including requests that mention a workout but do not yet include track files.
Invoke when the user asks about creative vision, game pillars, core fantasy, design direction, art style decisions, scope arbitration, or creative conflicts. Triggers on: "vision", "pillars", "creative direction", "core fantasy", "tone", "aesthetic", "creative conflict". Do NOT invoke for mechanics design (use game-designer) or technical architecture (use game-technical-director). Part of the AlterLab GameForge collection.
Generate speech from text using Google Gemini TTS models via scripts/. Use for text-to-speech, audio generation, voice synthesis, multi-speaker conversations, and creating audio content. Supports multiple voices and streaming. Triggers on "text to speech", "TTS", "generate audio", "voice synthesis", "speak this text".
Turn real customer reviews, quotes, and case-study results into polished social-proof videos built in HyperFrames -- single-testimonial spotlights, review-wall montages, and stat-driven proof reels with captions and voiceover, cut for vertical, square, and wide. The highest-converting content most businesses never make.
Write clear, emotionally resonant, and well-structured content that readers remember and act upon. Use when writing or editing any text - Twitter posts, articles, documentation, emails, comments, updates - for maximum clarity, engagement, and impact.
Rebuild one public Instagram video post or reel into a deterministic local replica with frozen assets, HTML/CSS, Playwright capture, MP4, and GIF. Trigger on replicate Instagram, reel to MP4, or freeze video locally. Do NOT use for captions, private/auth pages, carousels, Stories, or DMs.
Image generation and editing using Google Gemini's Nano Banana Pro (gemini-3-pro-image-preview) model. Use when user requests: "Generate an image", "Create an image", "Make me a picture", "Draw", "Edit that image", "Change the color", "Remove background", "Add transparency", "Modify this image", "Make it transparent", "Change the style", "Add text to image", or any image creation/manipulation task. Supports text-to-image generation, image editing, multi-turn conversations, and transparency extraction via difference matting technique.
Make explainer reels and deterministic motion graphics with Psychopomp: walkthrough videos of pull requests, code changes, protocols, or lifecycles, with GPU Stage choreography, callouts, rolling numbers, sequence diagrams, animated diffs, and optional ElevenLabs or Fish Audio narration.
Writes product promo animation prompts (Motion Graphics Prompt) for the Seedance 2.0 video generation model. Generates 15-second single-take motion image prompts, supporting 4 aesthetic styles (Apple/Microsoft/Bauhaus/Vercel). Supports the reference image (垫图) mode, automatically marking image placeholders. After generating prompts, videos can be generated directly via the 即梦 Dreamina CLI (installation status auto-detected). TRIGGER when: the user needs to generate Seedance video prompts, product promo animation prompts, motion graphics prompt, or mentions "Seedance", "视频提示词", "产品动画", "宣传视频提示词", "video prompt". Keywords: Seedance, 视频提示词, video prompt, motion graphics, 产品动画, 宣传动画, 垫图, Dreamina
Build silhouette-aware parallax occlusion mapping in Three.js WebGPU and TSL. Use for height-field ray marching, relief UVs, clipped flat or curved silhouettes, inflated shells, self-shadowing, relief-aware shadow depth, and height-derived normals.
Entry-point assistant for academic figure generation. Use this skill whenever the user wants to generate academic figures, paper diagrams, or architecture visualizations — including "帮我画图", "从仓库到配图走一遍", "完整论文配图工作流", "帮我分析这个仓库然后出图", or any end-to-end request from code/paper to figure. The assistant analyzes the input, presents a Figure Plan for user confirmation, then generates colors, prompts, and (when an image model is available) the final image. Routes repo-first (code) or paper-first (document/PDF) inputs.
Use when the user wants prose rewritten, tightened, audited, simplified, polished, humanized, grammar-checked, or made plainer, clearer, shorter, easier to scan, or easier to act on without changing the intended meaning, audience, tone, or explicit constraints. Trigger on requests such as plain English, simple English, make this clearer, make this more direct, clean this up, edit this, review this writing, grammar check, too wordy, too formal, less fluffy, friendlier, shorter, audit then rewrite, keep the tone, mode=strict, STE, ASD-STE100, or ADHD-friendly. Also trigger for docs, prompts, emails, UI copy, support replies, release notes, status updates, incident notes, procedural text, and other LLM-written prose. Prefer this skill when the main job is improving English prose or preserving tone while increasing clarity, including audit-only requests and exact-text-preservation constraints, but not when the real task is fact-checking, policy setting, or substantive content design.
AI audio editing pipeline: Whisper word-level transcription → Claude segment classification (KEEP/CUT_FILLER/CUT_FALSE_START/CUT_STUTTER/CUT_DEAD_AIR) → ffmpeg with 40ms qsin crossfades and room-tone fill → optional Cleanvoice cloud polish; plus GateScan/GateRepair for noise-gate ticking artifacts. Modes: --preview, --aggressive, --polish. Workflow: Clean. USE WHEN clean audio, edit audio, remove filler words, clean podcast, remove ums, cut dead air, polish audio, trim recording, cut stutters, ticking audio, clicking audio, audio clicks, gate artifacts, popping audio. NOT FOR video composition (use Remotion).
Create reproducible Blender Geometry Nodes, modifiers, instancing systems, and procedural environments. Use when a request involves Geometry Nodes, scattering, terrain, architecture, repeated assets, parametric generators, non-destructive variation, or scalable scene assembly.
Apply 人类最强编导的自媒体方法论、短视频脑反应理论 and the user's established plain-spoken Chinese voice to user psychology, account positioning, IP diagnosis, series planning, topic selection, audience-set analysis, content retention, short-video scripting, script review, shooting direction, content optimization, data diagnosis, monetization, course design, and creator coaching. Use for 抖音、小红书、视频号、B站等自媒体任务，尤其是分析用户为何停留、继续观看、记忆、关注、信任和付费，起号、陪跑客户、企业家IP、设计内容系列、寻找爆款选题、用脑科学与人性心理改造内容、判断两个元素能否组合、写或修改口播/Vlog/短片脚本、把方法论改写成用户本人的语言、审核外包编导稿件、复盘数据、课程研发和制定变现节奏。
Turn a website URL, product docs, or a founder's rambling description into a tight 60-90 second explainer video built in HyperFrames -- problem/solution narrative, animated product walkthrough scenes, captions, and voiceover, ready for the homepage hero, sales emails, and onboarding.
Craft high-quality natural-language image prompts for any modern text-to-image or image-edit model that accepts flowing English. Trigger when the user wants help writing, rewriting, improving, or translating an English natural-language image prompt — including "write me an image prompt", "improve this image prompt", "describe this scene for an image model", or "convert these tags into a natural language prompt". Do NOT trigger for requests that are purely about dispatching to an image API, choosing samplers/schedulers, picking LoRAs, or setting up ControlNet — those belong to a runtime skill.
Text-to-speech and speech-to-text via Together AI, including REST, streaming, and realtime WebSocket TTS, plus transcription, translation, diarization, timestamps, and live STT. Reach for it whenever the user needs audio in or audio out on Together AI rather than chat generation, image or video creation, or model training.
UGC video format templates for skincare brands. Contains 20 TikTok-native, lofi video formats with shot-by-shot structure and AI video generation prompts. Use when the user wants to create skincare UGC content — routines, texture shots, ingredient education, or product showcases.
Implement immersive and spatial video experiences on Apple Vision Pro (visionOS 27), including AVKit AVExperienceController, RealityKit VideoPlayerComponent setup, Apple Projected Media Profile (APMP), portal/progressive/full immersive viewing modes, transitions and events, comfort mitigation, and Apple Immersive Video authoring workflows.
Expert voxel artist with deep knowledge of MagicaVoxel workflows, palette design, animation techniques, mesh conversion, and game engine optimization. This skill represents insights from professional voxel artists, Teardown developers, and the MagicaVoxel community - knowledge Claude wouldn't normally have about this specialized art form. Use when "voxel, voxel art, magicavoxel, qubicle, voxel model, voxel animation, voxel game, blocky art, minecraft style, teardown style, voxel character, voxel environment, voxel optimization, voxel export, voxel to mesh, marching cubes, greedy meshing, voxel palette, destructible voxels, voxel, 3d, pixel-art, game-dev, magicavoxel, qubicle, animation, optimization, indie-games, retro, blocky" mentioned.
Expert in traditional Chinese baby naming. Based on the baby's birth chart (birth date and time), gender and surname, combined with yin-yang and five-elements theory and traditional Chinese culture, recommends names with auspicious meanings that match the five elements, or evaluates the merits of an existing name. Use when users request: (1) naming a newborn baby based on Chinese astrology, (2) analyzing name compatibility with birth date and time (八字), (3) suggesting names that balance the five elements (五行), (4) creating names with cultural and poetic significance, (5) evaluating an existing name's quality and compatibility.
Choose, configure, and use Blender MCP integrations for live scene control or deterministic asset evaluation. Use when connecting Codex or Claude Code to an open Blender instance, deciding between Blender Lab MCP and community Blender MCP servers, troubleshooting Blender MCP connectivity, or evaluating whether MCP tools improve a Blender modeling workflow.
World-class creative director for branding, web design, and UI concepts. Use when the user asks for a new design concept, brand identity, website creative direction, UI experience concept, visual identity, or creative strategy for a business, product, or project. Produces detailed, richly described creative concepts — not code or implementations.
Edit English prose to remove repetitive AI phrasing, inflated language, and mechanical structure while preserving meaning and the author's voice. Use for requests to humanize, de-slop, rewrite naturally, or fix tone. Also compose from the author's English notes or transcripts and ask targeted questions when real details are missing. For Brazilian Portuguese, use the companion humanizar skill.
Visual and video content creation. AI images, technical diagrams, mermaid flowcharts, infographics, comics, and special effects. USE WHEN art, diagrams, mermaid, flowcharts, infographics, video, animation, thumbnails, visualizations, generate image, technical diagrams.
Run Indic speech and language tasks through the Sarvam MCP server: translate text, transcribe or dub audio, TTS, localize i18n files, LLM complete, vision extract, or fetch Sarvam API docs/snippets while coding. Use this skill when the user wants Sarvam to act in chat, when sarvam_tools_* / sarvam_code_* are available, or when setting up sarvam-mcp in Cursor, Claude Code, Claude Desktop, Windsurf, Zed, Codex, Gemini CLI, VS Code, Cline, Continue, or LM Studio — even if they only say "translate this to Hindi" or "make it speak." Do not use for LiveKit/Pipecat agent code (voice-agents) or SDK-only coding when MCP is not installed (translate/text, translate/document, speech-to-text, text-to-speech, chat).
Record AI-driven browser demos with screencli. One command creates a polished screen recording with gradient backgrounds, auto-zoom, click highlights, and cursor trails — then uploads it to a shareable link. Use when the user wants to record a demo, screencast, walkthrough, or video of a web app.
For personal writing, including coming up with new articles from scratch and reviewing or polishing existing ones. Use it immediately when the user shares an article and asks for feedback, wants to improve their writing style, does not know what to write, needs to organize a travelogue, TIL, or personal essay, or asks for a check of Chinese quality. Trigger words include 「帮我改文章」「检查一下」「润色」「校对」「不知道写什么」「帮我构思」「写游记」「记录 TIL」「写点什么」. Not for formal business communication.
Guides writing architecture planning using McPhee's structural diagramming method, helping select from 8 structure types (list, chronological, circular, dual/triple profile, pyramid, parallel, custom), create visual diagrams, and place gold-coin moments for engagement. Use when planning or organizing writing structure, outlining before drafting, restructuring disorganized drafts, or when user mentions outlining, organizing ideas, structure planning, article architecture, narrative flow.
Apply the 3D cartoon character short workflow derived from multiple published GoodCase examples. Use when planning, storyboarding, or refining an AI video prompt in this motion pattern, including requests for 视频提示词, 分镜, 动作复刻, reference images, source video, or special generation steps. Read the bundled Case evidence before producing an artifact.
Use this skill to review, tighten, draft, and rewrite prose so it does not read like generic LLM output, AI writing, bland marketing, or generic launch copy. Apply it when the user asks to make writing less generic/AI-sounding, tighten a talk intro, sharpen presentation/slide copy, or improve articles, wiki pages, README text, emails, posts, scripts, product/DevRel copy, launch copy, and other important writing with AI tropes, inflated significance language, generic cadence, weak flow, or marketing fog.
Transcribe or post-process audio with AssemblyAI when explicitly requested or already selected by the project. Choose models, languages, diarisation, and region; retain resumable job IDs and produce speaker-aware local exports. Do not activate merely because a task involves generic transcription.
Knowledge comic creator supporting multiple styles (Logicomix/Ligne Claire, Ohmsha manga guide). Creates original educational comics with detailed panel layouts and sequential image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".
Generate demo animation HTML pages with a sidebar narrative and a 3D card carousel. Supports multiple interaction modes such as scroll paging, Coverflow 3D and Focus expansion, with built-in effects like mode switching (e.g. transport/tunnel), highlighter markup and watermark icons. Suited to protocol flow demos, product feature showcases and step-by-step walkthroughs.
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.