Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Evaluate scientific claims and evidence quality using evidence grading frameworks (GRADE, Cochrane risk-of-bias tools such as RoB 2 and ROBINS-I), assessing experimental design validity and identifying biases, confounders, statistical pitfalls, and logical fallacies. Use when judging evidence quality, grading certainty of evidence, spotting design or causal-inference flaws, identifying biases or confounders, naming statistical fallacies, or teaching critical analysis. For writing a formal submittable peer review use alterlab-peer-review; for a multi-reviewer mock panel verdict use alterlab-paper-reviewer; for IRB/consent/conflict-of-interest ethics use alterlab-research-ethics. Part of the AlterLab Academic Skills suite.
Store and query genomic variant data at scale with TileDB-VCF — ingest VCF/BCF into compressed TileDB arrays, add samples incrementally, run fast parallel region/sample queries, and export back to VCF. Use when managing population-genomics variant datasets that are too large for flat VCF, building joint variant stores, or querying thousands of samples by region. Part of the AlterLab Academic Skills suite.
This skill should be used when the user asks to "analyze this dataset", "run datavoyager", "run data voyager", "explore this data", "what's in this CSV", "statistical analysis of", "find patterns in", or wants an AI-driven, code-executing analysis of a tabular dataset that answers a specific research question.
Reference for androidx Material3 components in Android Jetpack Compose (Kotlin). Button, IconButton, FloatingActionButton, Checkbox, Switch, Slider, TextField, SearchBar, DropdownMenu, Chip, DatePicker, TimePicker, Card, Scaffold, Dialog, BottomSheet, TopAppBar, NavigationBar, NavigationRail, Tab, Snackbar, ProgressIndicator, Badge, Icon, MaterialTheme, ColorScheme, Typography, Shapes
Animation and drawing reference for Android Jetpack Compose (Kotlin). androidx.compose.animation / graphics APIs. AnimatedVisibility, AnimatedContent, animate*AsState, Animatable, AnimationSpec, Canvas, DrawScope, Brush, Path, Color, Image
Android Jetpack Compose (Kotlin) UI foundation reference. androidx, Material3 foundation. Composable, Modifier, CompositionLocal, remember, mutableStateOf, State, LaunchedEffect. Column, Row, Box, LazyColumn, Pager, ConstraintLayout, WindowSizeClass, pane scaffold. BasicText, BasicTextField, TextStyle, IME, clickable, gestures, focus, semantics.
Angular + BEM CSS methodology guide for creating reusable components and shareable front-end code. Enforces component-scoped BEM blocks, max 2-level nesting, proper component decomposition, semantic element naming, correct modifier patterns, and flat selectors. Use when writing, reviewing, or refactoring Angular component styles. Triggers on tasks involving CSS, SCSS, SASS, component styling, BEM naming, or CSS architecture.
Finds and removes signs of AI generation from Ukrainian or English text. Makes the text natural, human, with its own voice instead of template-like "copywriting from ChatGPT". Detects and fixes: inflated significance, bureaucratic language, AI clichés, template phrasing, excessive formatting, sycophantic tone, watery formulations, lack of voice. If the text is written for Viktor Shulha — pulls his style from about-viktor. Use this skill when the user says: «прибери ШІ», «зроби людяним», «гуманізуй», «humanize», «deslop», «remove AI signs», «це звучить як ChatGPT», «перепиши, щоб не пахло ШІ», «перевір на ШІ», «зроби природніше», «звучить як копірайтер», «занадто гладко», «забери воду», «anti-copywriting», «check for AI», «make it sound human», «rewrite without AI tone», «занадто шаблонно», «зроби живим». Also triggers when the user shows text and complains about «гладкість», «штучність», «безликість» or asks to «прибрати канцелярит».
Use when an app's layout must adapt to a window that changes size while the app runs, or when an app must support more than one window. That includes being asked to make an app resizable or support a resizable window, a layout that breaks or does not adapt as the window resizes, and preparing or optimizing an app for the foldable iPhone Duo, split-screen multitasking, or Stage Manager. Modernizes the app by replacing legacy shared-state APIs with context-appropriate alternatives: mainScreen, interfaceOrientation, userInterfaceIdiom, application and scene lifecycle, and safe area insets
Map an applicant's research interests to programmes, tracks, faculty, labs, and departments, and check whether their profile actually matches a programme's declared theme, specialisation, or application focus before writing target-specific materials. Covers PhD, research master's, and joint/consortium programmes such as Erasmus Mundus. Use whenever the user asks which professors or programmes fit their interests, how to shortlist targets, how to compare faculty fit, "does my profile match this programme's focus", "is my background relevant to this specialisation/track/theme", "should I even apply to this one", how to turn interests into searchable research themes, how to prepare target-specific fit notes for SOPs, or "does this programme match my career goal" (a goal-fit flag against the graduate the programme intends to produce, which never drops a target).
Use when enforcing architectural characteristics through automation — phrases like "architecture fitness function", "evolutionary architecture", "architecture tests", "ArchUnit", "dependency rules in CI", "automated architecture checks", "guardrails", "drift detection". Defines fitness functions as automated checks that verify architectural characteristics on every change, catching drift before it accumulates.
Use when discussing object-oriented design principles or component-level structure — phrases like "SOLID", "Single Responsibility", "Open-Closed", "Liskov Substitution", "Interface Segregation", "Dependency Inversion", "SRP", "OCP", "LSP", "ISP", "DIP". Defines the five SOLID principles, with the honest caveats Uncle Bob's original treatment glosses over and the cases where they shouldn't be applied dogmatically.
Use when the user wants to visualize, present, “show,” animate, or build an interactive web page for a software architecture, system design, technical concept, data model, pipeline, or product story — phrases like “intro page,” “architecture visualization,” “interactive diagram,” “scrollytelling,” “3D system map,” “ERD page,” “design walkthrough,” “make our architecture look impressive,” or “present this design to stakeholders.” Also use before hand-rolling Three.js, GSAP or SVG architecture diagrams from scratch, or when the user wants visual feedback on such a page through an edit mode.
Search and retrieve arXiv academic papers by topic, category, or paper ID — with AlphaXiv-enriched AI-generated overviews. Uses arXiv Atom API across cs.AI/cs.LG/cs.CL/cs.CR/cs.MA/cs.SE/cs.IR. Three workflows: Latest, Search, Paper. USE WHEN arxiv, papers, latest papers, research papers, recent ML papers, paper lookup, summarize paper, latest LLM papers, AI safety papers, cs.AI latest. NOT FOR general research (Research), URL parsing, or annual reports.
Skill for creating the same Chinese-style technical résumé: based on the ASu single-column, high-density technical résumé template, it generates or reproduces an editable HTML/PDF from real experience; use only when the user enters "/asu-resume", "我要阿酥同款简历", or explicitly asks for the ASu style, a reproduction of a reference résumé, or this template as HTML/PDF. When the request is only to package experience, rewrite projects, or write an HR self-introduction, use /asu.
Write correct async Rust — runtime choice, Send and Sync bounds, cancellation safety, blocking work inside async contexts, and shared state across tasks. Use when writing or reviewing async code, when a future is held across an await point, when the user hits a Send bound error on a spawned task, when a runtime stalls or deadlocks, or when the user asks about tokio, select!, or spawn_blocking.
PostgreSQL specifics for Atlas: dev database and URL scope (search_path), extensions, roles and grants, default privileges (ALTER DEFAULT PRIVILEGES, default_permission), ownership, row-level security, sequences and serial or identity columns, enums and column type changes, partitions, triggers, concurrent indexes, lock-safe migrations, schema and migration tests, custom lint rules, managed services (RDS, Cloud SQL, Supabase, Neon, Azure), and connection poolers. Use with the atlas skill whenever Atlas manages a PostgreSQL database.
Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants measurable accessibility, performance, responsive, theming, or anti-pattern findings—not when they mainly want an overall UX critique or final visual/detail polish.
Audits a live website for AI-engine discoverability (AEO/GEO). Crawls the site, runs 16 deterministic checks plus a 6-dimension content evaluation, and produces a scored report (A-F) with prioritized fixes. Use to get a baseline before improve-aeo-geo, or to measure progress after changes.
Fetch unresolved review threads on a GitHub PR, verify the validity of each comment, then pick only the valid points and fix and commit them. Handles comments from all reviewers (bots and humans). Activates on requests such as "apply the code review", "handle the review comments", "apply the PR review", "apply PR review comments", "handle review feedback", "autofix", "/autofix". Rather than applying review comments as-is, it applies only those judged valid in verification, either with user approval (default) or automatically (`--auto`).
Stands up an instant no-code REST + GraphQL API over the local Azure SQL Database container using Microsoft Data API Builder (DAB). Use when a user wants to "expose my table as an API", "add a REST API over the database", "generate a GraphQL API", "put an API in front of SQL", "CRUD API without writing code", or "dab init / dab-config.json". Also the way to serve a built-in MCP endpoint FROM the database via DAB (an API surface DAB provides, not a separate SQL MCP server). Prefer this over hand-writing a controller/ORM API when the user just needs REST or GraphQL over existing tables. Triggers include "Data API Builder", "dab start", "instant API over Azure SQL", "expose entities as REST/GraphQL". Reach for this even when the user only says "give me an API for this database".
Builds a serverless API and event-driven handlers over the local Azure SQL Database container using Azure Functions with the Azure SQL bindings. Use when a user wants "a serverless API over SQL", "Azure Functions with a database", "HTTP CRUD with SQL input/output bindings", "run code when a row changes", "react to inserts/updates/deletes", "event-driven on Azure SQL", or "SQL trigger function". The Azure SQL trigger binding (backed by Change Tracking) is the local event-driven mechanism; Change Event Streaming (CES) is cloud-only and cannot run against the local container. Triggers include "func start with SQL", "SqlTrigger", "SqlInput/SqlOutput binding", "local.settings.json SqlConnectionString". Reach for this when building serverless endpoints or change-driven logic on the local Azure SQL engine.
Conducts comprehensive backend design reviews covering API design quality, database architecture validation, microservices patterns assessment, integration strategies evaluation, security design review, and scalability analysis. Evaluates API specifications (REST, GraphQL, gRPC), database schemas, service boundaries, authentication/authorization flows, caching strategies, message queues, and deployment architectures. Identifies design flaws, security vulnerabilities, performance bottlenecks, and scalability issues. Produces detailed design review reports with severity-rated findings, architecture diagrams, and implementation recommendations. Use when reviewing backend system designs, validating API specifications, assessing database schemas, evaluating microservices architectures, reviewing integration patterns, or when users mention backend design review, API design validation, database design review, microservices assessment, or backend architecture evaluation.
Make videos in pure code (mp4, 16:9 and 9:16): narrated explainers with captions and music, and promo / launch videos for websites, apps and software with beat-synced music and sound effects. The user picks only the style: whiteboard, risograph, ink-wash (水墨), launch motion, origami, pop art, op art, Matisse cut-outs, ASCII art, shadow puppets (皮影戏), Bauhaus, pixel art, chat log, toy 3D, old newsreel, film-room breakdown, suspense mystery, isometric miniature world, movie trailer, news clippings, manga (日漫), animated map. Use for science / concept explainers, problem walkthroughs, vocabulary, history, places and maps, how-tos, news / data, and product promos from a URL. Use when the user asks for an "explainer video", "whiteboard animation", "a promo / launch video for this website / app", or in Chinese "做个科普视频" "把这道题做成讲解视频" "白板动画" "讲个历史故事的视频" "给这个网站 / App 做个宣传片" "产品发布视频", or names one of the styles (孔版印刷, 水墨, 折纸, 波普, 欧普, 剪纸, 字符画, 皮影戏, 包豪斯, 像素, 聊天记录, 玩具三维, 老新闻片, 录像分析, 悬疑探秘, 等距微缩世界, 电影预告片, 剪报解说, 日漫, 地图动画).
Use when upgrading from Bevy 0.18 to Bevy 0.19, when `TextLayout::new_with_justify` or `TextFont { font_size: 24.0, font: handle }` stops compiling (now `TextLayout::justify`, `FontSize::Px`, `FontSource`), when `bevy_scene`/`DynamicScene` serialization moved to `bevy_world_serialization` (`WorldAsset`/`DynamicWorld`), when a `#[derive(Resource)]` type now also matches `&T` component queries, or when `init_non_send_resource`/`FeathersPlugin`/`EasyScreenRecordPlugin` changed. Index of every breaking Bevy 0.19 change.
Extract visual content from a BibiGPT video (slides, OCR, on-screen text) and generate a mind map from a saved summary. Use when the user asks what is on screen, to analyze slides / PPT / frames, or to make an XMind mind map. Do not use to summarize audio or get a transcript (`bibi`), search the saved library (`bibi-library`), or manage channel feeds (`bibi-feed`). Do not invent digital humans, lip-sync, or shaders — BibiGPT does not expose those. Triggers: "what's on screen", "analyze the slides", "visual analysis", "画面分析", "PPT 上写了什么", "mind map", "思维导图", "extract visuals". Same `bibi` CLI binary and same BibiGPT account as the other skills
Use when the user asks for RSI bottom fishing, oversold buying, RSI strategy, bottom hunter, or buying when RSI is low. It monitors RSI, confirms signals with bingx-technical-analysis, and supports entry, stop-loss, and take-profit planning through bingx-swap-market, bingx-swap-trade, and bingx-swap-account.
Manage Bitbucket repositories, pull requests, branches, tags, commits, projects, and admin settings using the orbit CLI. Use this skill whenever the user asks about Bitbucket repos, PRs (pull requests), branches, tags, commits, code review, project management, default reviewer conditions, required approvals, merge restrictions, or PR approvals on Bitbucket Server/Data Center or Bitbucket Cloud. Trigger on phrases like 'list PRs', 'show pull requests', 'create a branch', 'open a PR', 'view the latest commits', 'list repos in project X', 'merge the PR', 'decline the PR', 'approve the PR', 'unapprove', 'request changes', 'find a repo', 'search repos', 'which repos are Go', 'search the code', 'needs work', 'mark as needs work', 'reject the PR', 'block the merge', 'check PR activity', 'bypass merge check', 'required approvals', 'reviewer conditions', 'who needs to approve', 'can this merge', 'why can't it merge', 'merge status', or any Bitbucket-related task — even casual references like 'what PRs are open', 'show me the repos', 'tag a release', 'check if it merged', 'who approved it', 'list branches', or 'why can't I merge'. Also trigger when the user provides a Bitbucket Server URL (e.g., https://git.example.com/projects/PROJ/repos/my-repo/) or mentions Bitbucket Data Center. The orbit CLI alias is `bb`.
Create 3D models procedurally with Blender Python. Use when the user wants to generate meshes from code, build geometry with bmesh, apply modifiers, create parametric shapes, procedural landscapes, grids, curves, or any programmatic 3D modeling in Blender.
Design Bolna graph agents: node-based voice flows with LLM, expression, unconditional and event edges, static low-latency nodes, silence repeat with escalation, per-node RAG, function tools, and real-time event injection via REST. Use when a single prompt is too fragile for a multi-step voice workflow — appointment booking, lead qualification, collections, IVR with LLM fallback, payment confirmation, or any flow with branches, compliance checkpoints, or external events.
Books time-based services via USP from a Link wallet. Use when the user wants to book, schedule, reserve, or pay for a service from a business (haircut, lesson, repair, class, appointment, consult). The `booking-agent` CLI owns the booking state machine and refuses to proceed when human gates are skipped. Sign the user in to Link on your own, right after install and at the start of every booking (`booking-agent flow link-auth connect`, then start `booking-agent flow link-auth poll` in the background and post the sign-in URL in the same turn, exactly like `pay poll`); never wait for the user to ask to sign in or to say they approved. After `booking-agent flow business use`, follow `next_command` through `use-ucp-checkout-mode`; businesses without native checkout fail closed. Payment uses `booking-agent flow pay request` (default returns immediately with the approval URL), then start `booking-agent flow pay poll` in the background and post the approval URL to the user in the same turn; the poll finishes checkout once they approve. Confirm through `booking-agent flow book poll --wait`; never start an inbound webhook. Surface the approval URL exactly once. Personal identification (name, phone, email, address) must always come from the user's Link account via `link-cli`, never from chat or placeholders. Before any location-based search, the CLI proposes the Link shipping address and the user confirms it or gives another; online services skip this. Talk to the user in plain everyday language only; never expose CLI, UCP, auth, session, or other implementation details unless they explicitly ask.
Implement features, write code, and set up Banuba Photo Editor SDK. Use when the user asks to implement, create, add, build, set up, or integrate something with Banuba Photo Editor SDK. Trigger with "help me add", "set up", "build a photo editor". Not for looking up existing docs - use explain-video-editor-photo-editor-docs for that.
Use when preparing to fine-tune, post-train, distill, or LoRA/QLoRA-tune an LLM, when generating synthetic or instruction training data, building SFT/DPO/preference sets, reasoning traces or tool-call trajectories, when choosing rank/alpha/learning rate, when deciding fine-tuning vs RAG, or when a tuned model regressed — hallucinates, lost general ability, repeats, or ignores its format.
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.