Skills
99,951 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Translate English text files (.txt, .md) to Chinese for language learning and translation practice. Use when the user asks to translate a text file to Chinese, create a Chinese version of an English document, or generate bilingual materials for translation training. The translation preserves sentence structure and combines broken sentences into complete lines.
Generates Enonic XP controller files (TypeScript/JavaScript) and paired XML descriptors for pages, parts, and layouts. Covers lib-portal imports, HTTP handler exports, region definitions, Thymeleaf/Mustache rendering, and response processors. Use when scaffolding page controllers with regions, part controllers with config access, layout controllers with multi-region support, or response processors for Enonic XP sites. Do not use for content type schemas, headless Next.js/React frontends, GraphQL Guillotine queries, or non-Enonic web frameworks
Comprehensive personal health management: body composition tracking, meal photo analysis with clinical-grade nutritional breakdown, exercise logging, medical lab interpretation (blood panels, FeNO, urinalysis, etc.), supplement guidance, and periodic progress reports. Use when: (1) analyzing food photos or meal descriptions for calories/macros, (2) interpreting medical lab results or health markers, (3) tracking body metrics (weight, body fat, waist circumference), (4) planning exercise routines with injury considerations, (5) generating weekly/monthly health reports, (6) setting up health reminders (meals, movement, supplements, sleep), (7) any question about nutrition, exercise science, or wellness optimization.
Publish Markdown articles to Zsxq (知识星球) as drafts. Use when user wants to publish a Markdown file to Zsxq, or mentions "发布到知识星球", "星球文章", "zsxq article". Handles Markdown content input and saves as draft (never auto-publish).
Perform structured reconnaissance and attack surface enumeration for authorized penetration tests, CTF challenges, and bug bounty programs. Use when the user mentions “recon”, “reconnaissance”, “enumerate”, “attack surface”, “subdomain enumeration”, “port scan”, “fingerprint”, “asset discovery”, or needs to map a target's external footprint.
Brain managed-mode deploy executor for Sealos Cloud. Use when SEALAI_DEPLOY_MODE=managed (a Brain Devbox sandbox) or when the task says to run /sealos-deploy: deploy the workspace repository to Sealos through the MCP-gated managed pipeline — classify, build via Kaniko if needed, generate the canonical template, hand off through template_ready / deployment_completed, and verify. Outside managed mode, use the use-sealos skill instead
Use this skill when the user provides a failed Steel session ID, failed automation run, timeout, browser error, blocked page, or unexpected result and wants evidence-backed diagnosis using session metadata, browser logs, raw agent logs, semantic traces, replay links, screenshots, network failures, or errors. Do not use for first-pass bot mitigation; collect evidence here, then hand off to steel-reliability for proxy, CAPTCHA, identity, or anti-bot fixes.
Use to critique a screen, flow, prototype or running build, accessibility included, and rank what is broken, such as "check this page before I ship", "is this flow ready", "is it accessible", keyboard or screen-reader checks, "it feels off on my phone" or "it feels janky". Not for token compliance, which is token-mapping.
Transform predictable story elements into fresh, original versions. Use when something feels generic, when feedback says "I've seen this before," when elements orbit the protagonist too conveniently, or when you want to make a familiar trope feel new. Applies the 8-step CTF process and Orthogonality Principle
Feishu Mail: inbox triage and unread filtering; read emails and threads (including attachment metadata); compose, reply/reply all, forward; create and edit drafts; handle regular attachments, CID inline images and HTML email; mark emails and threads as read, move them to archive or delete them to the trash; manage receiving rules (filters), signatures and email templates. Use when the user mentions Feishu email, mailbox, inbox, drafts, email attachments, preview or confirmation before sending, receiving rules, email templates or signatures. Preview-only requests, saving a draft or waiting for confirmation are also covered by this Skill. Not for chat messages (feishu-cli-messaging) or looking up users by email address (feishu-cli-platform)
Audit and clean the Remotion GitHub masterplan hierarchy. Use when finding open issues that lack a masterplan ancestor, identifying orphaned issues that need a parent, or recursively removing closed issues from the masterplan rooted at issue #9081.
Expert patterns for Godot 3D lighting including DirectionalLight3D shadow cascades, OmniLight3D attenuation, SpotLight3D projectors, VoxelGI vs SDFGI, and LightmapGI baking. Use when implementing realistic 3D lighting, shadow optimization, global illumination, or light probes. Trigger keywords: DirectionalLight3D, OmniLight3D, SpotLight3D, shadow_enabled, directional_shadow_mode, directional_shadow_split, omni_range, omni_attenuation, spot_range, spot_angle, VoxelGI, SDFGI, LightmapGI, ReflectionProbe, Environment, WorldEnvironment
Expert blueprint for signal-driven architecture using "Signal Up, Call Down" pattern for loose coupling. Covers typed signals, signal chains, one-shot connections, and AutoLoad event buses. Use when implementing event systems OR decoupling nodes. Keywords signal, emit, connect, CONNECT_ONE_SHOT, CONNECT_REFERENCE_COUNTED, event bus, AutoLoad, decoupling.
Act as an active outline partner who develops structure collaboratively. Use when developing, iterating, or improving story outlines. Generates scene beats, character arcs, plot structures, and exploratory prose samples. Contrasts with story-collaborator which drafts finished prose.
Use this skill to extract structured Markdown/JSON from PDFs and document images—tables with cell-level precision, formulas as LaTeX, figures, seals, charts, headers/footers, multi-column layout and correct reading order. Trigger terms: 文档解析, 版面分析, 版面还原, 表格提取, 公式识别, 多栏排版, 扫描件结构化, 发票, 财报, 复杂 PDF, PDF转Markdown, 图表, 阅读顺序; reading order, formula, LaTeX, layout parsing, structure extraction, PP-StructureV3, PaddleOCR-VL.
Turn a raster logo (PNG/JPG/WebP/screenshot) into a clean minimal SVG, with edge smoothness as the primary hard gate and IoU optimized as high as reasonably possible without a fixed global threshold, then into a choreographed logo animation delivered as standalone JS-rendered HTML, applying Disney's 12 animation principles. Use when asked to animate a logo, build a logo reveal / splash screen / brand intro, convert a logo image into animated SVG or HTML, add motion to a vectorized mark, or create loading/idle/hover motion for a brand mark. v2: also handles self-crossing draw-on choreography (split-fill, exact easing subdivision, tip glint), closed variable-width ribbon fitting, and quantitative motion QA (easing probe, ink-delta continuity sweep).
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
Tailwind CSS responsive design and dark mode patterns (2025-2026). PROACTIVELY activate for: (1) dark mode setup (class-based vs media-query, dark: variant), (2) toggling dark mode at runtime (data-theme, html.dark), (3) prefers-color-scheme handling, (4) per-component dark variants, (5) responsive design with dark mode (combining sm:dark:bg-*), (6) system / light / dark / high-contrast theming, (7) CSS color-scheme property, (8) avoiding flash of unstyled content (FOUC) in dark mode, (9) dark-mode color tokens via @theme. Provides: dark-mode toggle implementation, FOUC prevention pattern, color-token templates, and system-preference detection
three.js keyframe animation system: AnimationMixer, AnimationClip, AnimationAction, KeyframeTrack variants, PropertyBinding, PropertyMixer, AnimationObjectGroup, AnimationUtils; mixing and crossfading clips, loop modes, timeScale, weight; addon AnimationClipCreator and CCDIKSolver for procedural rigs. Use when playing glTF clips, blending actions, or authoring procedural tracks; for skin deformation rigging on meshes see threejs-objects; for math interpolants without clips see threejs-math only when not tied to AnimationMixer.
Build rich text editors with Tiptap—a headless editor framework with React and Tailwind v4. Covers SSR-safe setup, image uploads, prose styling, and collaborative editing. Use when creating blog editors, comment systems, or Notion-like apps, or troubleshooting SSR hydration errors, typography issues, or image upload problems.
Runs scoped browser probes for focus, hit targets, overflow, themes, request failures, and performance attribution, with evidence linked to UI rule IDs. Use when asked to "verify this in the browser", "reproduce this UI finding", "re-measure after the UI fix", or "review before and after screenshots"
Use vision models to self-review screenshots against design intent. Catches spacing issues, alignment problems, color inconsistencies, responsive bugs, and accessibility gaps. Use when reviewing designs, comparing implementations to mockups, or doing pre-ship QA.
Generate a full SEO-optimized blog post. Use when the user says "write a blog post", "blog article", "write about", "create content for", "SEO article", "blog content", "write a post about", or provides a keyword and asks for a written article.
A paragraph-level structural blueprint for 10–12-page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides page allocation, paragraph templates, and writing patterns. Use when the user says “写系统论文,” “systems paper structure,” “OSDI paper,” or “SOSP paper,” or wants fine-grained structural guidance for a systems conference submission.
Use this skill when the user asks to “create an agent,” “add an agent,” “write a subagent,” “agent frontmatter,” “when to use description,” “agent examples,” “agent tools,” “agent colors,” or “autonomous agent,” or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
Create, list, inspect, update, or delete AgentMail inboxes through the connected MCP server. Use for ANY inbox lifecycle request — even a quick list-inboxes or a simple delete; deletion safeguards apply regardless of task size. Also use when the user asks for a new agent email address, wants inbox details changed, or removes an inbox; do not use for sending mail (agentmail-send-email), reading or triage (agentmail-check-email), or MCP connection setup (agentmail-mcp).
Deepgram API reference for speech-to-text, text-to-speech, voice agents, audio intelligence, and account management. Use whenever building with Deepgram APIs — REST or WebSocket. Covers authentication, all endpoints, query parameters, request/response schemas, and WebSocket message formats. Reference files are organized by domain: listen (STT — Nova and Flux STT), speak (TTS — Aura and Flux TTS), agent (voice agents), read (text/audio intelligence), models, projects, auth, and self-hosted
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.