Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Establish the architecture for Next.js 15+ applications using the Scope Rule and Screaming Architecture. Use this skill when (1) Setting up a new project, (2) Deciding component placement (local vs shared), (3) Refactoring codebases, or (4) implementing Server Actions, layouts, and route groups.
Execute architectural refactoring from an assessment document with deterministic, chunked operations and aggressive verification at every step. Use when you have an architectural assessment, clean architecture review, refactoring recommendations, or seam-ripper output and need to actually perform the refactoring safely. Also use when asked to "refactor based on this assessment", "execute these architectural recommendations", "fix architectural drift", "refactor in chunks", or any request to systematically restructure a codebase according to a plan. Designed specifically to prevent the kind of agent drift that causes architectural problems in the first place.
Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use this skill when designing clean architecture for a new microservice, when refactoring a monolith to use bounded contexts, when implementing hexagonal or onion architecture patterns, or when debugging dependency cycles between application layers.
Ask what would be lost from the plan if this session ended now — decisions about the system made in conversation and never written down — drive each to a home or an approved forget, then answer honestly whether anything would have to be decided again.
Upload a screenshot, an image or a screen recording to Argos and get a shareable URL plus ready-to-paste Markdown, so it can be embedded in a pull request, an issue, a changelog or a chat message — or attached to a branch or pull request, where Argos posts and maintains the comment itself. Use whenever you have produced a visual artifact — a Playwright video or trace screenshot, a before/after of a UI change, a recording of a reproduction — and need it visible to a human who cannot run your shell. GitHub has no public API for comment attachments, so this is how an agent working from a terminal gets an image into a pull request at all. Also covers reading back the comments a human pinned to those screenshots, so you can act on visual feedback you cannot see.
Package a TeX/LaTeX project into a clean tarball or zip for arXiv upload: file selection, build-artifact exclusion, 00README.XXX generation, ancillary file organization, archive validation. Triggers on: "package for arXiv", "create arXiv tarball", "bundle submission", "zip for arXiv", "prepare arXiv upload", "arXiv submission archive". Companion to arxiv-preflight and arxiv-figures.
Read, inspect, or summarize arXiv papers using a clean-markdown-first paper-reading workflow. Use when the user provides an arXiv URL or id, asks to read a paper, analyze a preprint, summarize a research paper, compare claims against evidence, or extract assumptions, limitations, strengths, and weak links from a paper.
Write or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop. Use for documentation, READMEs, runbooks, procedures, error messages, release notes, incident reports, and API guides. Also use when the user says "STE", "Simplified Technical English", "ASD-STE100", "de-slop", "make this readable", "write for non-native readers", or asks for docs that translate well. Enforces the standard's 53 rules: 20/25-word sentence limits, one word one meaning, simple tenses, active voice, condition before command.
This skill should be used when the user asks to "find a class", "search for symbol", "find usages", "find implementations", "search codebase", "find file", "class hierarchy", "find callers", "module dependencies", "unused dependencies", "project map", "project conventions", "project structure", "what frameworks", "what architecture", "find Perl subs", "Perl exports", "find Python class", "Go struct", "Go interface", "find React component", "find TypeScript interface", "find Rust struct", "find Ruby class", "find C# controller", "find Dart class", "find Flutter widget", "find mixin", "find Scala trait", "find case class", "find object", "find PHP class", "find Laravel model", "find PHP trait", or needs fast code search in Android/Kotlin/Java, iOS/Swift/ObjC, Dart/Flutter, TypeScript/JavaScript, Rust, Ruby, C#, Scala, PHP, Perl, Python, Go, C++, or Protocol Buffers projects. Also triggered by mentions of "ast-index" CLI tool.
Astro content-focused web framework. Covers islands architecture, content collections, and multi-framework support. Use when building content-heavy or static websites. USE WHEN: user mentions "Astro", asks about "islands architecture", "content collections", "Astro components", "client directives", "Astro.glob", "static site generation with Astro", "multi-framework in Astro" DO NOT USE FOR: Next.js - use `nextjs-app-router` instead; Nuxt - use `nuxt3` instead; SvelteKit - use `sveltekit` instead; Gatsby - use Astro as modern alternative; pure React/Vue/Svelte - use respective framework skills
Structure asyncio code: task management, cancellation, rate limiting, blocking calls kept off the event loop. TRIGGER WHEN: building async APIs, concurrent or I/O-bound systems needing non-blocking operations, or choosing between asyncio, threading and multiprocessing.
Atlassian CLI (acli) expertise for interacting with Jira Cloud and Atlassian organization admin from the terminal. Use when scripts invoke `acli`, user asks about Atlassian CLI, Jira CLI, JQL-driven automation, bulk Jira operations, or managing Jira work items, projects, boards, sprints, filters, fields, dashboards, Atlassian org admin users, or Rovo Dev authentication.
Fetches any company's job openings directly from its Applicant Tracking System (ATS) via the Crawlora API—Greenhouse, Lever, Workday, Ashby, SmartRecruiters, Workable, Personio, Recruitee, iCIMS, Oracle Recruiting, Rippling, Pinpoint, Eightfold, Gem, UKG, and Teamtailor—and returns clean JSON. Use when the user wants all open roles from a company's ATS-hosted careers page, the full details of a single job posting, or a hiring-velocity snapshot for a company, given its ATS platform and company or board slug.
Interactive system flow tracing across CODE, API, AUTH, DATA, NETWORK layers with SQLite persistence and Mermaid export. Use for security audits, compliance documentation, flow tracing, feature ideation, brainstorming, debugging, architecture reviews, or incident post-mortems. Triggers on audit, trace flow, document flow, security review, debug flow, brainstorm, architecture review, post-mortem, incident review.
Audit websites for SEO, technical, content, and security issues using squirrelscan CLI. Returns LLM-optimized reports with health scores, broken links, meta tag analysis, and actionable recommendations. Use when analyzing websites, debugging SEO issues, or checking site health.
Use this skill whenever anyone asks about migrating from Auth0 to Descope — whether they're a developer doing it themselves or a technical lead evaluating the move. Triggers on: “how do I migrate from Auth0”, “replace Auth0 with Descope”, “we're moving off Auth0”, “Auth0 to Descope”, “switch from Auth0”, “our app uses express-openid-connect / nextjs-auth0 / auth0-fastapi / other Auth0 SDK and we want to use Descope instead”, or any question about Auth0 features (Actions, FGA, Organizations, Token Vault, CIBA) in the context of Descope. Works for any language or framework with a Descope SDK. Always use this skill before producing migration guidance — do not rely on memory alone.
Author or upgrade Model Advisor checks for Simulink and System Composer models. Covers the full lifecycle: guideline authoring, check specification, Model Advisor check implementation, and qualification testing. Use when creating new checks (edit-time, standard batch, config-parameter, auto-fix), converting legacy StyleOne/StyleTwo/StyleThree checks to modern DetailStyle, creating a guideline for modeling, enforcing a modeling rule, or testing/qualifying a check. Triggers on any modeling constraint (e.g., "blocks shall...", "signals must match...", "parameters shall be set to...").
Use when setting up an autonomous ML experimentation harness (an “autoresearch” loop): a fixed harness that owns data and metrics plus a hackable training script an LLM iterates on under a fixed time budget. Use when scaffolding harness.py/train.py/program.md, designing structured training-dynamics logging for agents to read, or enforcing that experiments cannot game the metric
Background job processing patterns including job queues, scheduled jobs, worker pools, and retry strategies. Use when implementing async processing, job queues, workers, task queues, async tasks, delayed jobs, recurring jobs, scheduled tasks, ETL pipelines, data processing, ML training jobs, Celery, Bull, Sidekiq, Resque, cron jobs, retry logic, dead letter queues, DLQ, at-least-once delivery, exactly-once delivery, job monitoring, or worker management.
Research-grounded, read-only audit that validates a repository's codebase, architecture, and business logic against real-world knowledge from authoritative sources (arxiv, PubMed, Google Scholar, JSTOR, OpenAlex, Crossref, Semantic Scholar) plus standards bodies (NIST, IETF/RFC, OWASP, ISO, sector regulators). Use when you want an audit that flags algorithms, architectural choices, or business rules violating established norms, standards, or best practices — e.g. 'is our APR calculation correct per lending norms?', 'does our crypto follow NIST?', 'is this consensus approach sound?' — each finding tied to a real, fetched citation. Extracts falsifiable claims across algo/arch/biz layers, routes each to the right source class, verifies against fetched evidence, and adversarially refutes before reporting; emits a severity-graded cited report with UNCONFIRMED for anything ungrounded. Not a linter, SAST, or CVE scanner — it reasons about norms, not syntax.
A workflow and scripts for end-to-end handling of baserCMS repository security advisories (including GHSA and triage): list advisories, verify findings, fix issues individually, create private forks/branches/PRs, and verify locally. Use for requests such as “check security advisories,” “verify triaged vulnerabilities,” “create a fork and PR for each advisory,” or “bundle vulnerability fixes into pull requests.” Covers relying on local verification (/code-review・basercms-unittest) because Copilot/GHA cannot be used on advisory forks, retries while waiting for pushed changes to appear, splitting hunks in shared files, and common conflict resolution when syncing with base.
Enforce a precise, minimal design system inspired by Linear, Notion, and Stripe. Use this skill when building dashboards, admin interfaces, or any UI that needs Jony Ive-level precision - clean, modern, minimalist with taste. Every pixel matters.
Java Layered Architecture Design Pattern — A complete implementation guide for the classic five-layer architecture using Spring Boot + MyBatis-Plus. Suitable for bootstrapping new Java projects, refactoring existing architectures, establishing team development standards, and database migration scenarios.
Calculate and analyze Customer Acquisition Cost (CAC) and Customer Lifetime Value (LTV) to evaluate unit economics and marketing efficiency. Use this skill when the user needs to assess whether their customer acquisition is profitable, optimize marketing spend allocation, or evaluate business model viability — even if they say 'are we spending too much on ads', 'what's each customer worth', or 'is our growth sustainable'.
Analyze supply chain operations using the SCOR model across Plan, Source, Make, Deliver, and Return processes. Use this skill when the user needs to optimize supply chain efficiency, evaluate supplier performance, improve logistics, or design an end-to-end supply chain strategy — even if they say 'our deliveries are slow', 'supply chain costs are too high', or 'we keep running out of stock'.
Build and review Blazor applications across server, WebAssembly, web app, and hybrid scenarios with correct component design, state flow, rendering, and hosting choices. USE FOR: building interactive web UIs with C# instead of JavaScript; choosing between Server, WebAssembly, or Auto render modes; designing component hierarchies and state. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
In-depth technical blog writing. Not a content generator, but a tool for expressing opinions. Forces forming a judgment → Chinese and English versions → mermaid/architecture diagrams first → SEO + FAQ + distribution. Trigger words: 写博客, 写文章, blog, 介绍新工具, 参考这个链接写, 整理资料成文. Use this skill when the user needs to: (1) write a technical blog (2) organize materials/write an in-depth piece referencing a URL (3) introduce a new tool/technology (4) produce a technical article with architecture/flow diagrams
Guide for posting content to the Bluesky social network using the bsky terminal app. This skill should be used proactively when working in public repositories and there is interesting, shareable content (new features, insights, achievements, or announcements worth sharing with the community). Use it when asked to post to Bluesky, or when content seems worth sharing publicly.
Researches Bluesky profiles, posts, follower/follows graphs, account search, and trending topics via the Crawlora API, returning clean JSON. Use when the user wants a Bluesky account's stats, a post's thread/engagement, a Bluesky account search, or what's trending on Bluesky — instead of scraping the app or the AT Protocol API directly.
Researches books, authors, and audiobooks via the Crawlora API — Goodreads (books, authors, reviews, lists, quotes), Apple Books (books, audiobooks, series, reviews, charts), and Audible (audiobook catalog search, product detail, narrators/series, reviews, charts, editorial lists) — returning clean JSON. Use when the user wants a book's ratings/reviews, an author's bibliography, curated reading lists, or audiobook details and charts.
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.