Skills
99,951 packaged capabilities and playbooks for agents. Install any of them with one command.
All
State-of-the-art Machine Learning for PyTorch, TensorFlow, and JAX. Provides thousands of pretrained models to perform tasks on different modalities such as text, vision, and audio. The industry standard for Large Language Models (LLMs) and foundation models in science.
Personal travel concierge — complete itinerary planning and guide export from origin to destination. Input the origin, destination, number of days, budget, and style preferences to automatically output a closed-loop itinerary including transport recommendations, hotel recommendations, food routes, and a daily budget, with an optional generated guide. Use when the user mentions "做攻略", "旅行规划", "旅游计划", or "行程安排".
Validate wallet balances in TRES Finance against DeBank and generate a discrepancy report. Use this skill whenever the user asks to validate, verify, cross-check, or audit their TRES balances against on-chain data or DeBank. Also trigger when the user asks if their balances are correct or wants to see discrepancies. Only EVM-compatible wallets are supported.
Manage cost basis calculation in TRES Finance: check status, view/change strategy (FIFO, LIFO, AVG, MAX_GAINS, MAX_LOSSES, FIFO_IMPAIRMENT), trigger recalculation, review financial issues, manage reevaluations/impairments, set bulk fiat prices, configure spec-ID lot disposal rules, view per-asset cost basis results, and export cost basis reports. Trigger this skill whenever the user asks about cost basis, gains/losses, realized gains, unrealized gains, COGS, inventory lots, tax lots, cost basis strategy, reevaluation, impairment, fiat value override, spec-ID rules, financial issues (negative balance, missing fiat), or anything related to how their crypto assets are costed. Also trigger when the user says "calculate cost basis", "what is my cost basis strategy", "show me financial issues", "create a reevaluation", "run cost basis", "change strategy to LIFO", or similar.
Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.
Translate natural language UI descriptions into IDS (Iress Design System) component implementations using @iress-oss/ids-components and @iress-oss/ids-tokens. Use when the user describes a UI in plain language and wants IDS component code, or asks to build a form, page, layout, or component using IDS.
UiPath solution planner and designer. Always invoke for PDD / SDD files (`pdd.md`, `*-sdd.md`). Authors a Solution Design Document (SDD) from a Process Definition Document (PDD) or another process-knowledge source (Confluence page, SOP, BPMN model, meeting transcript), then derives the multi-skill, multi-project task list from an SDD, emitting live TaskCreate calls. Known-product single-project build, no PDD/SDD → that skill; ambiguous/“what should I build” → here. For `uip solution` lifecycle and `.uipx` → uipath-solution. For non-solution Orchestrator/IS/auth/traces → uipath-platform. For .xaml/.cs → uipath-rpa. For .flow → uipath-maestro-flow. For building/editing .bpmn → uipath-maestro-bpmn (a .bpmn as design input routes here). For agent.json/.py → uipath-agents. Sole case-SDD author. For caseplan.json build → uipath-maestro-case.
Exhaustive planning interrogation for turning vague or complex requests into precise, implementation-ready plans. Use when the user invokes $ultraplan, says "ultraplan", "ultra plan", "deep plan", "plan mode", "ask me everything", "interrogate this", or asks the agent to resolve all requirements, use cases, edge cases, tradeoffs, and open questions before implementation.
Generate a personalized follow-up sequence for any creator chasing scenario — missing info, unsigned contract, late content, missing metrics, or incomplete whitelisting setup. This skill should be used when chasing a creator for a response, writing a follow-up message to an influencer, nudging a creator about a late deliverable, following up on an unsigned contract, requesting missing campaign metrics, chasing whitelisting or ad access setup, escalating a non-responsive creator, writing a reminder to a creator who ghosted, building a follow-up cadence for overdue items, drafting a polite but firm nudge to an influencer, or managing creator communication when deadlines slip. For writing initial outreach messages, see creator-outreach-sequence-generator. For classifying and triaging creator replies, see reply-triage-classifier. For negotiating rates after a creator responds, see creator-negotiation-assistant.
Use the bundled Himalaya 2 CLI to connect IMAP/SMTP or Microsoft Graph mailboxes and list, search, read, compose, reply, forward, move, delete, flag, and download email. Use when the user asks to connect or operate Gmail, QQ Mail, iCloud Mail, Outlook, or another standard mailbox, or says "连接邮箱"、"绑定邮箱"、"看看我的邮件"、"查邮箱"、"发邮件"、"回复邮件".
Use when you need to pick high-quality Unsplash images for product/design assets (avatars, headshots, portraits, large website backgrounds, and abstract wallpapers) and output real Unsplash URLs plus practical instructions for producing the right resolutions and aspect ratios (1:1, 4:5, 3:4, 16:9, 9:16).
Load or manage Product Design's saved user context. Use when the user asks to set up Product Design, get started, onboard, save product or design sources, see what Product Design remembers, update saved context, or remember Product Design preferences. Examples include product URLs, Figma files, screenshots, reference images, codebase paths, Storybook, tokens, design systems, brand assets, and general product/design notes.
This skill should be used when comparing two videos to analyze compression results or quality differences. Generates interactive HTML reports with quality metrics (PSNR, SSIM) and frame-by-frame visual comparisons. Triggers when users mention "compare videos", "video quality", "compression analysis", "before/after compression", or request quality assessment of compressed videos.
Generate SRT subtitles from video/audio with translation support. Transcribes Hebrew (ivrit.ai) and English (whisper), translates between languages, burns subtitles into video. Use for creating captions, transcripts, or hardcoded subtitles for WhatsApp/social media.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components—not for simple single-file HTML/JSX artifacts.
Intelligently format Markdown articles and publish them to the WeChat Official Account draft box. AI generates creative HTML, uploads images, and publishes to the draft box. Triggered when the user says "发布到微信", "推送到公众号", or "微信文章发布".
Build ServiceNow App Engine Studio applications — sys_scope creation, scoped tables, sys_aw_workspace with lists/forms, the sys_ux_* record chain behind UI Builder workspaces, data brokers, and application export readiness checks. Never create a UI Builder page by inserting a sys_ux_page row.
Use when investigating or improving WordPress performance (backend-only agent): profiling and measurement (WP-CLI profile/doctor, Server-Timing, Query Monitor via REST headers), database/query optimization, autoloaded options, object caching, cron, HTTP API calls, and safe verification.
Run or troubleshoot Wrangler CLI commands in projects that have a wrangler.jsonc, wrangler.json, or wrangler.toml file, including local development, previews, deployment, and resource management. For new projects and projects without a Wrangler configuration file, use the cf CLI instead.
End-of-session persistence of the session's work to Obsidian as a session note per project and the daily note. Use when closing a work session and recording what it changed. Not for mid-session checkpoints, conversation handoffs, standalone project or meeting notes, or repository-wide project context.
Write the technical spec at docs/specs/<slug>/_techspec.md — explore the architecture, settle technical decisions one question at a time, record them as ADRs, and produce a build order that write-tasks can decompose. Entry point for feature work with an approved PRD, and also for refactors and bug fixes, where it mints the spec folder with a minimal _prd.md instead of requiring a product interview.
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.