Skills
100,344 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Migrate Python OpenAI Agents SDK applications to Pydantic AI and, when warranted, Pydantic AI Harness. Use for `agents.Agent`, `Runner`, function tools, handoffs, guardrails, sessions, human approval, streaming, or `SandboxAgent`. Do not use for applications built directly on the OpenAI Responses API without the Agents SDK runtime.
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
| Nuxt 4 server-side development with Nitro: API routes, server middleware, database integration, and backend patterns. Use when: creating server API routes, implementing server middleware, integrating databases (D1, PostgreSQL, Drizzle), handling file uploads, implementing WebSockets, or building backend logic with Nitro
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries.
Make short-form UGC video ads (TikTok, Reels, Shorts) for the product in the current repo with DansUGC ReelClaw and real human creator reactions from the DansUGC library. Edit and render every reel locally on this machine with the ReelClaw HyperFrames templates (TikTok Sans, safe-zone captions), and check each render frame by frame before delivery. The dansugc MCP server supplies reaction clips, viral-format suggestions, trending music, and research; it does not render. Use when the user asks for UGC ads, reaction ads, TikTok/Reels ads, “make N ads for this app,” ReelClaw, DansUGC videos, HyperFrames reels, “make viral reels” when the user is unsure which formats to use, ad hook variations, or editing or re-cutting an ad (caption style, position, timing, trims).
Deploys and configures static sites on Render's global CDN—build commands, publish paths, SPA routing, redirects, custom headers, and PR previews. Use when the user needs to deploy a static site, set up a React/Vue/Hugo/Gatsby frontend, configure SPA fallback routing, add redirect rules, customize response headers, or choose between a static site and a web service for their frontend. Trigger terms: static site, CDN, SPA, single-page app, React deploy, Vue deploy, Hugo, Gatsby, Docusaurus, Jekyll, staticPublishPath.
Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off. This skill covers the platforms (n8n, Temporal, Inngest) and patterns (sequential, parallel, orchestrator-worker) that turn brittle scripts into production-grade automation. Key insight: The platforms make different tradeoffs. n8n optimizes for accessibility
Iterates one-by-one through a multi-bug report with a hard confirmation gate before any code touches disk. Use this skill when the user has a report of 2+ bugs and wants to work through them sequentially. Trigger phrases: "let's tackle these", "let's iterate", "go one by one", "loop through the findings", "work through the bugs", "bug iteration", or any time the user presents a numbered list of bugs and signals they want to resolve them in order. Do NOT trigger for a single bug (just investigate and fix) or when the user wants a fresh debug pass (use a dedicated debug/investigation pass for that).
This skill should be used when the user asks about "Cloudflare Workers with Bun", "deploying Bun to Workers", "wrangler with Bun", "edge deployment", "Bun to Cloudflare", or building and deploying applications to Cloudflare Workers using Bun
Build autonomous AI agents with Claude Agent SDK. Structured outputs guarantee JSON schema validation, with a plugins system and hooks for event-driven workflows. Prevents 14 documented errors. Use when: building coding agents, SRE systems, security auditors, or troubleshooting CLI not found, structured output validation, session forking errors, MCP config issues, subagent cleanup
Executes the Antagonistic-Review process from the Elephant-Goldfish Model (EGM) via an automated multi-agent review loop to audit documents against qualitative standards and structural templates, and automatically apply approved fixes. Use when reviewing design docs, READMEs, feature specifications, implementation plans, or verifying document completeness and tone.
Create, read, and manage calendar events and reminders using EventKit and EventKitUI. Use when adding events to the user's calendar, creating reminders, setting recurrence rules, requesting calendar or reminders access, presenting event editors, choosing calendars, handling alarms, observing calendar changes, or working with EKEventStore, EKEvent, EKReminder, EKCalendar, EKRecurrenceRule, EKEventEditViewController, EKCalendarChooser, or EventKitUI views.
Generate or edit images using the OpenAI Image API (gpt-image-2). Use when the user asks to generate, create, draw, render, illustrate, mock up, or edit an image, icon, logo, mockup, illustration, OG image, blog hero, marketing asset, or similar visual. Also use when the user supplies a reference image and asks to modify, restyle, or remix it. Triggers on: "generate an image", "create an image", "make a picture of", "edit this image", "restyle this", "make a mockup of", "draw a", "render a", "illustration of".
Build, test, and deploy applications using GitHub Actions workflows. Create CI/CD pipelines, configure runners, manage secrets, and automate software delivery. Use when working with GitHub repositories, automating builds, running tests, or deploying applications.
Expert patterns for game economies, including currency management (multi-currency, wallet systems), shop systems (buy/sell prices, stock limits), dynamic pricing (supply/demand), loot tables (weighted drops, rarity tiers), and economic balance (inflation control, currency sinks). Use for RPGs, trading games, or resource management systems. Trigger keywords: EconomyManager, currency, shop_item, loot_table, dynamic_pricing, buy_sell_spread, currency_sink, inflation, item_rarity
A one-stop skill for retrieving Amazon Ads reports, covering all report types for Sponsored Products (SP) / Sponsored Brands (SB) / Sponsored Display (SD). The script automatically creates, waits for, downloads, and extracts reports, returning readable structured data directly. The single source of truth for actually available report types and each type’s column list/groupBy/filters is `references/report-types/{adProduct-dir}/{reportTypeId}.md`. Trigger this skill when users mention pulling or downloading Amazon Ads reports, or retrieving any reports for SP/SB/SD campaigns, keywords, search terms, advertised products, purchased products, ad groups, traffic anomalies, Prompt expansion, etc. This skill depends on linkfox-amazon-ads-auth. Sponsored Television (ST) / Amazon DSP are not yet covered.
MPSTATS daily time-series performance for a single SKU on the Russian Ozon marketplace. Returns date-level metrics for an Ozon product, including sales, price, stock, and rating, with optional search rank/visibility data to validate growth trends, seasonality, and anomalies. Trigger this skill when users mention Ozon trends, sales trends, price movements, daily data, stock trends, search rank, product history, MPSTATS trend, Ozon daily performance, Ozon time series, Ozon search visibility, or Russian marketplace product history. Trigger it even if “MPSTATS” is not explicitly mentioned, as long as the user wants daily or period-based trends for an Ozon product.
Commit the changes, sync with remote main, push the current branch, and create a Pull Request. Refuses to run directly on main. Use with /livre, or when the user wants to deliver/ship their work: “commit et push,” “ouvre une PR,” “livre ça,” “ship,” “envoie la PR,” “finalise et pousse.” Natural follow-up to /branche.
Redis vector search guidance covering HNSW vs FLAT algorithm choice, vector index configuration (dims, distance metric, datatype), filtered hybrid search combining vector similarity with TAG or NUMERIC filters, and the RAG retrieval pattern with RedisVL. Use when defining a VECTOR field in FT.CREATE, integrating embeddings (OpenAI, Cohere, sentence-transformers), tuning HNSW parameters (M, EF_CONSTRUCTION, EF_RUNTIME), building a retrieval-augmented generation pipeline, or filtering vector results by attribute
Sets up and configures background workers on Render for queue-based job processing. Use when the user needs to process async jobs, consume from a queue, run Celery/Sidekiq/BullMQ/Asynq/Oban workers, handle graceful shutdown with SIGTERM, wire a worker to Key Value, or choose between workers and cron jobs for background work. Trigger terms: background worker, async jobs, queue consumer, Celery, Sidekiq, BullMQ, Asynq, Oban, job processing, SIGTERM, graceful shutdown.
Build production-ready web scrapers for any website using Bright Data infrastructure. Guides you through site analysis, API selection, selector extraction, pagination handling, and complete scraper implementation. Use this skill whenever the user wants to build a scraper, create a crawler, extract data from a website, scrape product pages, handle pagination, build a data pipeline from a web source, or automate data collection from any site — even if they don't explicitly say 'scraper'. Triggers on phrases like 'build a scraper for', 'scrape data from', 'extract products from', 'crawl pages on', 'get data from [website]', or 'I need to pull data from'.
Turn vague features, bug clusters, roadmap items, launch work, or playtest findings into an execution-ready planning packet by choosing the right packet type, separating discovery from delivery, and making blockers, dependencies, and the next move explicit. Use for backlog cleanup, feature slicing, sprint or milestone prep, release planning, or translating roadmaps into delivery plans across developer workflow, web/fullstack, product/ops, marketing/GTM, or game work. Also owns the retired `sprint-plan` name: sprint capacity from velocity and availability, Definition-of-Ready story selection, dependency and critical-path mapping, sprint goal, and sprint plan summary. Route sizing to `task-estimation`, issue-state governance to `triage`, plan review to `plannotator`, daily syncs to `standup-meeting`, retros to `sprint-retrospective`, and pre-planning concept framing to `bmad`, `bmad-idea`, or `bmad-gds`.
Guidance for the Turborepo monorepo build system. Covers turbo.json, task pipelines, dependsOn, caching, remote cache, the “turbo” CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure and best practices, and boundaries. Use when configuring tasks/workflows/pipelines, creating packages, setting up a monorepo, sharing code between apps, running changed/affected packages, debugging cache, or working with apps/packages directories.
Vue Material Component Framework. Use when writing, debugging, or configuring code that imports vuetify v4.x. Covers createVuetify setup, components and labs, composables, theming, icons, dates and locale, styles and SASS variables, treeshaking, and v3 to v4 migration.
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.
Audit how a brand appears in AI-powered search (ChatGPT, Perplexity, Claude, Gemini). Use when user mentions "AI search," "how do I show up in ChatGPT," "AI discoverability," "AEO," "LLM visibility," or wants to understand their brand's AI presence.
How to work in artist directories. Use when adding or updating artist context (identity, brand, voice, audience), adding songs, organizing files inside an artist directory, or figuring out where something belongs. Also use when the user mentions an artist by name and the task involves their files, context, or content — even if they don't say "artist directory." This includes tasks like researching an artist, creating content for an artist, updating an artist's brand, or adding a face guide.
This skill should be used when the user asks about "bun build", "Bun.build", "bundling with Bun", "code splitting", "tree shaking", "minification", "sourcemaps", "bundle optimization", "esbuild alternative", "building for production", "bundling TypeScript", "bundling for browser", "bundling for Node", or JavaScript/TypeScript bundling with Bun
Help users transition from individual execution to a coaching-centric leadership style that scales through the growth of their team. It focuses on identifying skill deficits, providing reflection space, and leveraging frameworks to accelerate professional maturity
Expert guidance for using the GitLab CLI (glab) to manage GitLab issues, merge requests, CI/CD pipelines, repositories, and other GitLab operations from the command line. Use this skill when the user needs to interact with GitLab resources or perform GitLab workflows.
Expert multiplayer for desync, rollback, dedicated --headless servers, interest culling, and bandwidth spikes: ENet/WebRTC choice, authority, secure RPCs, client prediction/reconcile, and adaptive sync. Trigger on rubber-banding, cheat-able clients, peer floods, late join, or profiler Network spikes — not only greenfield online games. Keywords: multiplayer, RPC, ENetMultiplayerPeer, MultiplayerSynchronizer, authority, client prediction, rollback, interest management, headless, desync.
Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural or human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
Audit, design, and migrate Identity and Access Management — cloud provider IAM (AWS, GCP, Azure), identity providers (Okta, Entra ID / Azure AD, Auth0, Google Workspace), application authorization (RBAC, ABAC, ReBAC), and federated identity. Use when the user mentions 'IAM,' 'identity,' 'access management,' 'least privilege,' 'role design,' 'SSO,' 'SAML,' 'OIDC,' 'OAuth,' 'JIT access,' 'just-in-time access,' 'break-glass,' 'service accounts,' 'RBAC,' 'ABAC,' 'privilege creep,' 'role explosion,' 'identity governance,' 'IAM strategy,' 'identity migration,' 'Okta,' 'Entra ID,' 'Azure AD,' 'Auth0,' 'Cognito,' or needs identity consultant-level guidance.
Drill down into product listings by seller ID on MPSTATS for the Russian Ozon marketplace. Returns comprehensive metrics for all SKUs under that seller, including sales volume, revenue, price, rating, inventory, turnover, and lost sales, with multidimensional numeric filtering, sorting, and currency conversion. Use for store structure analysis, breakdowns of a seller’s bestsellers, and competitor store benchmarking. Trigger this skill when the user mentions Ozon seller products, Ozon store analysis, Ozon seller drill-down, Ozon seller SKUs, Ozon store bestsellers, Ozon competitor stores, MPSTATS seller, Ozon seller drill-down, Ozon shop audit, Russian marketplace seller SKUs, or Ozon store structure. Even if the user does not explicitly say “MPSTATS,” trigger this skill whenever they intend to view sales performance for all products in a store by Ozon seller ID.
Tests/benchmarks a third-party LLM endpoint (OpenAI- or Anthropic-compatible): availability, fidelity, speed, concurrency, protocol compliance, quality regression. Use before hand-rolling a curl loop, when onboarding a provider, or debugging "system prompt 不生效" / a tok/s claim — 测评/压测一个模型或渠道. Not for TTS/voice-clone supplier eval (use the audio skill)
OpenFGA authorization modeling best practices for defining types and relations, writing relationship tuples, deriving can_* permissions, applying type restrictions and usersets, and authoring .fga.yaml check/list_objects/list_users tests. Use when authoring, reviewing, or refactoring OpenFGA models, tuples, permissions, .fga files, .fga.yaml test files, or OpenFGA SDK integrations in JavaScript, TypeScript, Go, Python, Java, or .NET.
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.