Skills
100,344 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Backend development guidelines for Node.js/Express/TypeScript applications. Layered architecture (Routes → Controllers → Services → Repositories), error handling, validation, middleware patterns, database access, and testing. Use when creating routes, endpoints, APIs, controllers, services, repositories, middleware, or working with backend code.
Reviews, rewrites, creates, harmonizes, and implements user-centered interface copy across design files, screenshots, product specifications, source code, localization catalogs, prototypes, and rendered applications. Use for buttons, navigation, forms, errors, empty states, onboarding, confirmations, settings, consent, notifications, help, and system feedback while preserving product behavior, terminology, voice, accessibility, localization, legal meaning, component structure, and implementation constraints.
Scandit Barcode Capture (`BarcodeCapture`) in native Android (Kotlin/Java) projects — the low-level, full-control single-barcode scanning mode (BarcodeCapture + DataCaptureView + overlay), without the pre-built SparkScan UI. Use for integration, symbology and scan settings, result handling, overlay customization, SDK version migration (v6→v7→v8), replacing third-party scanners (ZXing, ML Kit), or troubleshooting.
Better Auth (TypeScript authentication framework) v1.7 reference. Covers authentication and authorization, sign-up and sign-in, session management, OAuth, passkeys, two-factor authentication (2FA / TOTP), SSO / SAML, SCIM, OAuth Provider (OAuth 2.1 / OIDC), MCP authorization (@better-auth/mcp), infrastructure (dash / sentinel), and plugins (organization, admin, magic-link, anonymous, etc.). betterAuth, createAuthClient, signUp, signIn, getSession. Integrations with Next.js, Nuxt, SvelteKit, Hono, Express, Expo, TanStack, and Effect.
How to use BGPT MCP to search scientific papers and retrieve structured experimental data including methods, results, sample sizes, conflicts of interest, limitations, reproducibility scores, and falsifiability criteria. Use this skill when the user asks to find scientific evidence, search the literature, evaluate research quality, check reproducibility, surface study limitations or conflicts of interest, retrieve raw experimental data, or build evidence-grounded AI workflows. Also trigger when the user references PubMed, arXiv, biorxiv, medrxiv, systematic reviews, evidence-based medicine, GRADE, or critical appraisal.
Use bigquery CLI (instead of `bq`) for all Google BigQuery and GCP data warehouse operations including SQL query execution, data ingestion (streaming insert, bulk load, JSONL/CSV/Parquet), data extraction/export, dataset/table management, cost estimation with dry-run, authentication with gcloud, data pipelines, ETL workflows, and MCP server integration for AI-assisted querying. Modern TypeScript/Bun implementation replacing the Python `bq` CLI with instant startup (~10ms vs ~500ms), automatic cost awareness with confirmation prompts, and native streaming support (JSONL). Handles both small-scale streaming inserts (<1000 rows) and large-scale bulk loading (>10MB files) from Cloud Storage.
BISON v3.0.1 — Conviction Holder. Patient multi-asset (BTC/ETH/SOL) conviction trader. MIN_SCORE 11 across 9 components (4H/1H structure, momentum, SM alignment, funding, volume, OI proxy, RSI). Conviction-scaled margin tiers (25%/31%/37%) and 7-10× leverage. DSL is wide by design — time-cuts DISABLED — so a real directional thesis can run multiple days into the move. Few trades. Long holds. Big moves. v3.0.1 ships a race-window dedup cache that eliminates the ENGINE_FAILURE retry noise on already-held assets, plus a doubled DSL exit interval to throttle REDUCE_ONLY spam when runtime position-state lags HL.
Interviews the user about a go-to-market goal and produces a validated GTM brief covering the motion, the Blitz endpoint choice (Find People, Waterfall ICP, Company Search, or Employee Finder), an ICP/account definition with case-sensitive enum-validated filters, an enrichment plan (email/phone), an output target, the language, and a volume estimate. Use when the user wants to find leads, build a prospect or account list, define an ICP, plan outreach sourcing, or scope a Blitz API search before writing code, or says "who should I target", "build me a lead list", or "plan a GTM motion". Produces gtm-brief.yaml and hands off to blitz-create-script.
Security audit smart contracts for exploitable vulnerabilities from an unprivileged context. Use when analyzing Solidity contracts, reviewing bytecode, testing exploits on forks, or searching for ways to extract funds without owner access. Covers verified and unverified contracts, bytecode disassembly, vulnerability ranking, proof-of-concept exploit generation, DeFi protocol attacks, and cross-chain bridge security.
Static analysis security vulnerability scanner for Ruby on Rails applications. Use when analyzing Rails code for security issues, running security audits, reviewing code for vulnerabilities, setting up security scanning in CI/CD, managing security warnings, or investigating specific vulnerability types (SQL injection, XSS, command injection, etc.). Also use when configuring Brakeman, reducing false positives, or integrating with automated workflows.
Analyze an influencer's recent content and return a brand safety report flagging political controversy, offensive language, sensitive topics, or past scandal indicators. This skill should be used when screening a creator for brand safety, vetting influencer content for risks, checking if a creator is brand-safe, auditing an influencer's content history for red flags, running a brand safety check on a creator, evaluating creator risk before a partnership, flagging controversial creator content, reviewing an influencer for offensive language or sensitive topics, or doing a pre-campaign safety review. For holistic creator evaluation including performance metrics, see creator-vetting-scorecard. For writing campaign briefs with content guidelines and safety clauses, see campaign-brief-generator.
When the user wants to create a budget, forecast future performance, or perform variance analysis. Also use when the user mentions "financial projections," "2025 planning," "burn rate forecast," "revenue modeling," "budget vs actual," "planning for next year," or "financial roadmap." Use this for operational planning and strategic forecasting.
Build or improve a Coval dashboard with metric visualizations backed by real data. Creates new dashboards from scratch or rebuilds existing ones by analyzing usage patterns, metric frequency, and data density. Use when user says "create a dashboard", "build a dashboard", "improve my dashboard", "add widgets", "visualize my metrics", "make a performance dashboard", or "dashboard for my runs".
Build, redesign, extend, or audit a complete role-based professional workbench, operations cockpit, case portal, expert workstation, or data-rich internal tool for any occupation. Use for 工作台、业务驾驶舱、职业后台、运营中心、role dashboard、admin portal、CRM-like workspace or reusable multi-page web apps, especially when every module needs realistic records, distinct dashboards, profession-specific information architecture, Quiet Luxury A visual design, complex interactions, automatic local persistence, offline pure-Web compatibility and verifiable workflows.
Builder user experience systems for Three.js building games. Use when implementing prefab/blueprint save/load, undo/redo command patterns, ghost preview placement, multi-select, or copy/paste building mechanics. Covers the UX layer that makes building feel responsive and intuitive.
Perform comprehensive competitor analysis for any business. Produces an executive-summary markdown report with target customer profile, market positioning, pricing/business model, product features, funding/company size, SWOT analysis, and competitive matrix. All findings are data-grounded. Use when the user asks to analyze competitors, understand competitive landscape, compare a business to alternatives, or perform market research.
Community edition of a deep research agent system that performs multiple rounds of iterative web search and comprehensive analysis on complex topics. Use cases: when the user needs in-depth, thorough research on a specific topic, especially when a detailed analysis report must be generated from the latest web information. Supports multiple rounds of iterative search, intelligent adjustment of search direction, and comprehensive analysis report generation. This skill is a workflow description document with no execution scripts; it relies on the byted-web-search skill for web search.
Generate short marketing videos for products on Douyin Shop/Douyin using Volcano Engine KickArt’s one-click video creation service. Supports providing product links or product IDs, uploading custom image/video assets, submitting asynchronous video creation tasks, checking progress, retrieving the resulting video, and syncing creative assets. Use this skill when users send a Douyin Shop/Douyin product link or mention “upload assets,” “add image,” “add video,” “one-click video creation,” “generate short video,” “marketing video,” “product video,” “create finished video,” or “check video creation progress.”
AI-driven advisor for C: drive space diagnosis and safe cleanup. Locates why space grows and why cleanup is ineffective through NTFS actual-allocated-space measurement, parent-child directory deduplication, app-level growth and post-cleanup regeneration tracking, vendor-managed caches/toolchains, Windows update leftovers, and an inventory of rarely used software and scattered space. Use this skill when the user asks about insufficient C: drive space, cleanup that doesn't work, free space not increasing, caches regenerating, finding rarely used software / large files / hidden usage, migrating data, or reviewing cleanup results.
Implement a permanent cache-first strategy: check cache before hitting the DB, write to cache on first read, invalidate only when data changes. No TTL timeouts. Modeled on Play Framework's cache model. Use when asked to "add caching", "implement cache strategy", "cache DB results", or "reduce DB load".
Foundational context on how the summer camp industry works in the US and Canada, covering what a camp is, day versus overnight, the camp year, the enrollment journey, staffing and J-1 visas, accreditation and jurisdiction, and data and privacy. Load this when working on anything for a summer camp (marketing, operations, staffing, or parent communication) so decisions are grounded in how camps actually operate. The other camp skills build on this context.
Diagnose why a WarmySender campaign is sending little or nothing, across email, LinkedIn and Instagram. Use when the user asks "why isn't my campaign sending?", "campaign stuck", "no emails going out", or wants a delivery health check.
Takes raw campaign tracking data and generates a clean weekly status summary formatted for Slack, email, or a leadership meeting. This skill should be used when building a weekly campaign status update from spreadsheet data, generating a Slack-ready campaign summary, formatting campaign progress for a leadership meeting, turning a messy tracker into a status digest, creating a weekly roundup of creator campaign performance, summarizing campaign health across creators and platforms, preparing a Monday morning status post for your team channel, writing a campaign progress email for stakeholders, or condensing raw metrics into a scannable digest. For full ROI analysis, see campaign-roi-calculator-narrative-builder. For normalizing raw metrics first, see metrics-normalization-formatter. For tracking creator posting compliance, see creator-posting-compliance-tracker.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
End-to-end ArcGIS Portal / AGOL → CARTO migration. Triggers when the user wants to migrate ArcGIS content to CARTO, plan a migration, asks "what's in my Portal", names a Portal/AGOL URL, or asks to migrate the datasets / web maps / simple apps. Runs three phases — discover (enumerate items + write MIGRATION_MANIFEST.md), migrate-data (Hosted Feature Layers / Tables → CARTO tables), migrate-maps (Web Maps + simple Dashboards / Web Experiences / Web Mapping Apps → CARTO Builder maps). Default mode is batch; migrated maps are always tagged `From ArcGIS` and created as private.
Guides the user through building composite score workflows when they ask about composite scores, indexes, multi-variable scores, ranking areas, site scoring, market potential, resilience indexes, risk indexes, weighted scores, PCA, or supervised/unsupervised scoring.
Select and correctly use @cat-kit/* public capabilities in JS/TS projects. Covers deep copy, cloneDeep, structuredClone, debounce and throttle, dates, HTTP, nanoid, and equivalent capabilities from lodash, axios, dayjs and the like. In any JS/TS-based project (frontend or Node.js), use this skill before wrapping your own general-purpose utilities or functions or adding dependencies such as lodash, axios, dayjs, nanoid — check first, then wrap or add dependencies.
Debugs a failing production call, reproduces the bug with Cekura evaluators, implements a fix, verifies it, runs regression tests, then raises a PR with evidence. Use when the user wants to fix a production call bug, investigate a failing prod call, reproduce and fix a production issue, run regression tests before a PR, or says things like "fix this prod call issue", "debug and fix call ID", "test my fix against prod scenarios", "reproduce this production bug", or "regression test before raising PR".
Chart and data visualization libraries. Recharts, Chart.js, D3.js, Victory, Nivo, ECharts. Common chart types, responsive design, and real-time updates. USE WHEN: user mentions "chart", "graph", "data visualization", "Recharts", "Chart.js", "D3", "ECharts", "Victory", "bar chart", "line chart", "dashboard" DO NOT USE FOR: PDF report generation - use `pdf-generation`; data export - use `data-export`.
Moves each step of an agent skill whose correct result is fixed by its inputs into a script the skill runs, leaving the model only judgment. Use when the user says "script the deterministic steps", or when creating a skill, or adding or changing its steps, commands, or parsing. Not for trimming a skill; use cutting-skills.
Skill dedicated to the kitchen renovation pitfall-avoidance guide. Covers all kitchen topics: layout (open/semi-open, removing walls, kitchen right at the entrance), circulation and layout, plumbing and waterproofing and floor drains, cabinet bodies and doors, countertops with water stops and underslung edges, sink selection and installation, storage (tall cabinets/slim cabinets/cutting area), tiles and walls, lighting and daylight, doors (sliding doors/linked doors), reducing housework, safety (lethal practices/toxins/heavy-metal cookware), and overhyped gimmicks. Integrates 24 original practical articles from 西安装修课堂 in reverse order, helping users plan right the first time before renovating and regret less after moving in.
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.