Skills
98,284 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Preserve the rationale of a consequential architecture decision in a lightweight ADR when code and maintained documentation will not retain it. Use to create, edit, or review ADRs, or when settled rationale is about to be lost; keep implementation plans elsewhere.
Build AI phone agents with AgentPhone API. Use when the user wants to make phone calls, send/receive SMS, manage phone numbers, create voice agents, set up webhooks, or check usage — anything related to telephony, phone numbers, or voice AI.
Reverse engineer .NET assemblies and executables with dnSpyEx, ILSpy, and de4dot — identifying and unwrapping obfuscators and packers, deobfuscating control flow and string encryption, handling single-file and NativeAOT publishes, and patching IL. Use when a binary is a managed PE, when ILSpy shows mangled names or empty method bodies, or when analyzing .NET malware, a loader, or a Windows application.
Work with advanced layer types including WMS, WFS, WMTS, OGCFeatureLayer, KMLLayer, MapImageLayer, CatalogLayer, MediaLayer, and VideoLayer. Use for OGC services, server-side rendering, georeferenced media content, and live video feeds from ArcGIS Video Server.
Configure FeatureTable for tabular data display and FormTemplate with input elements for feature editing forms. Use when adding spreadsheet-style data grids, building attribute edit forms, configuring form input types and validation, or surfacing related records in forms.
Design or review .NET solution architecture across modular monoliths, clean architecture, vertical slices, microservices, DDD, CQRS, and cloud-native boundaries without over-engineering. USE FOR: .NET architecture choices; layer and domain boundary review; service decomposition; clean architecture, vertical slice, DDD, CQRS, and modular monolith decisions. 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.
Build high-quality, animated, professional web pages that VISUALIZE software architecture, system design, data models, or a product idea — using Three.js (3D) + GSAP (scroll/animation) + SVG diagrams. Produces two things, usually together: (1) a cinematic scroll-story landing page where a 3D low-poly world narrates how a system works, and (2) an interactive architecture map with switchable overlay "lenses", clickable drill-down component diagrams, and crow's-foot ERDs. Every output ships with a built-in EDIT MODE so the human can click components / snip areas / pick 3D objects and batch visual feedback straight to you. Use this skill WHENEVER the user wants to visualize, present, "show", animate, or build an interactive page for an architecture, system design, technical concept, data model, pipeline, or product story — including 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". Prefer this skill over hand-rolling Three.js/GSAP from scratch — it bundles battle-tested templates, a styling/anti-slop guide, a diagram-layout catalog, and an AI-tweakable code convention learned from a long real build.
Answer questions about ArkEnv and help implement environment variable validation. Use when developers: (1) Ask about environment variable validation or typesafety, (2) Want to setup ArkEnv in a project, (3) Need to define or update schemas using ArkType or Standard Schema, (4) Are integrating with Next.js, Nuxt, Vite, Bun, or Node.js runtimes. Triggers on: 'ArkEnv', 'env validation', 'typesafe env', 'createEnv', 'env.ts', 'arkenv'.
This skill helps an LLM generate correct AxGEPA optimization code using @ax-llm/ax. Use when the user asks about AxGEPA, GEPA, Pareto optimization, multi-objective prompt tuning, reflective prompt evolution, validationExamples, maxMetricCalls, or optimizing a generator, flow, or agent tree.
Comprehensive backend development workflow that orchestrates expert analysis, architecture design, implementation, and deployment using the integrated toolset. Handles everything from API design and database architecture to security implementation and DevOps automation.
Use when writing BK-CI backend microservice code, such as adding a Resource, organizing API/Service/DAO layering, dependency injection, determining service ownership, and Spring Boot development conventions. Prefer this when the user is doing Kotlin/Java backend development.
Gather scattered ideas into organized GitHub issues. The bee collects pollen from every flower, checks if the hive already has it, and carefully deposits new work in the comb for later. Never edits code—only organizes the work ahead. Use when creating issues from TODOs or planning work.
The domain expert's product manager in a project repository run by the Boring Factory. Use when the expert brings a need or an idea, wants to clarify, change or resume a feature ("reprends la fiche"), asks what is happening with a feature, has a builder's question to answer, or has a preview to try and accept. Interviews one question at a time, writes the contract and mockups on the contract pull request, and submits the expert's approval only after the expert confirms. Never writes code, except a tiny one-shot change as a draft pull request, and never merges.
Create or edit a PostHog freeform canvas — a sandboxed browser application (data board, document, form, small tool, graphics experiment) stored in PostHog and rendered by the desktop/web app. Use when a task asks to build, generate, update, or fix a standalone canvas app, or when a freeform canvas id is given as the publish target. For grid/home canvases, widget placements, or reusable components, use composing-grid-canvases instead. Covers resolving or creating the target canvas, choosing an implementation approach (React + Quill vs plain HTML/browser APIs), the read → edit → validate → publish → build loop, and which companion canvas skills to load for the details.
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.
Game building mechanics case studies and decision frameworks. Use when designing building systems, evaluating trade-offs, or learning from existing games. Reference-only skill with detailed analysis of Fortnite, Rust, Valheim, Minecraft, No Man's Sky, and Satisfactory building systems.
Use when writing C# / .NET application code (also VB.NET, F#) that connects to a data source through a CData driver — after the connection and SQL have been validated with the cdata-cli discovery skill. Covers mapping the language to the CData ADO.NET Data Provider edition, adding the provider from NuGet (CData.<Source>), activating its license, and connecting via the ADO.NET classes (<Source>Connection / <Source>Command). This is the .NET build-phase companion to cdata-cli; invoke it whenever the target application runs on .NET.
Use when calling the CloudCannon API from code — constructing a client, finding a site or organisation UUID, reading or writing files on a hosted site programmatically, triggering and inspecting builds, or reaching a CloudCannon endpoint the CLI has no command for (DAMs, backups, sync history, site scans, screenshots, provider connections, copying or deleting a site)
Add headless Chrome automation with Puppeteer/Playwright on Cloudflare Workers. Use when: taking screenshots, generating PDFs, web scraping, crawling sites, browser automation, or troubleshooting XPath errors, browser timeouts, binding not passed errors, or session limits.
First-run skill that walks the entire repository, auto-detects Classic vs Adaptive AUTOSAR, and maps it accordingly. For Classic (default): identifies features and SWCs and documents referenced requirement IDs (SW-REQ-*, REQ-*, FSR-*, SYS-REQ-*), port interfaces (S/R, C/S, Mode Switch, Parameter), dependencies on other SWCs and BSW modules (Com, NvM, Dem, Dcm, IoHwAb, Os), and concrete RTE API calls (Rte_Read_*, Rte_Write_*, Rte_Call_*, Rte_IRead_*, Rte_IWrite_*). For Adaptive (C++14, POSIX, ara::): identifies Adaptive Applications, ara::com service interfaces, ara:: functional-cluster usage, and manifests. Also captures repository structure, ASIL zones, signal/service flow, and architectural concerns. Writes findings to .autonomousguy/CODEBASE_MAP.md so every subsequent skill can reference it without re-reading the codebase; can emit a self-contained HTML companion report under analysis/.
Existing-code comprehension and local winnowing preflight. Use for simplify/refactor/clean up/untangle, nested branches, boolean soup, opaque names, mixed responsibilities, cross-file state, or review stalls. Factor the local whole, separate essential/incidental/specification-risk factors, winnow dominated or duplicated factors, and emit the smallest clarity cut. Not for broad architectural layer removal, kernel quotienting, invariant remediation, or greenfield planning.
Comprehensive React component library with 30+ production-ready components using shadcn/ui architecture, CVA variants, Radix UI primitives, and Tailwind CSS. Use when users need to (1) Create React UI components with modern patterns, (2) Build complete component systems with consistent design, (3) Implement accessible, responsive, dark-mode-ready components, (4) Generate form components with React Hook Form integration, (5) Create data display components like tables, cards, charts, or (6) Build navigation, layout, or feedback components. Provides instant generation of customizable components that would otherwise take 20-45 minutes each to hand-code.
Turn a finished plan, spec, or decision map into a build effort with ready-for-agent tickets, or resume its filing and check progress. Use when asked to file the build tickets, break this spec into issues, turn the plan into tickets, slice the work, resume filing build tickets, check progress and close out a build effort, or /conjure.
Scaffold Claude Code configuration specifically for Craft CMS projects. Generates CLAUDE.md and .claude/rules/ files tailored to the project type (plugin, site, module, hybrid, or monorepo). Only for Craft CMS projects — not for Next.js, Laravel, or other frameworks.
Write, restructure, and organize technical documentation around reader tasks and a verifiable throughline, handling doc types, paths, file names, frontmatter, indexes, and lifecycle per project conventions. For technical docs it also protects facts, commands, paths, and identifiers in mixed Chinese-English content and applies the core principles of ASD-STE100 to English explanatory text; when the user provides both a legitimate standards PDF and a local checker, it can assist with checking automatically. Use this skill whenever the user wants to add or substantially rewrite plans, investigations, analyses, research, progress reports, guides, operations manuals, tutorials, reference material, explanations of principles, decisions, incidents, meeting notes, changelogs, or specifications; it also applies when organizing a docs directory and topic indexes. Do not use it for plain translation, polishing a short passage, changing only code, or looking up a single fact.
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.