Start with the job, then find an open-source answer

Qt AI Skills is the official agent-skill collection for Qt development and quality assurance. It covers Qt C++ and QML reviews, QML best practices, UI design, documentation generation, profiling, test creation and execution, Figma token and component conversion, and Qt 6 CMake projects. Selected review workflows combine deterministic linting with parallel AI analysis, and an official Qt documentation MCP server provides API lookup. The skills support Claude Code, Codex, Gemini CLI, and GitHub Copilot, but results still require careful review.

Railway Skills packages an installable `use-railway` skill for Claude Code, Codex, Cursor, Grok Build, and compatible environments. The Railway CLI setup can install the skill, configure the local MCP server where supported, and check whether the user is authenticated. The skill routes requests to action-oriented guidance for Railway tasks, while actual use requires a Railway account and an authenticated CLI session.

This collection covers contracts, HR, finance, writing, research, and automation, backed by MCP tools for PDF operations, spreadsheets, Word documents, presentations, and format conversion. It also includes extensible jurisdiction or industry knowledge and several prebuilt professional personas. Some document operations require building and connecting the local Office MCP server first.

This bilingual skill teaches engineers how to design the systems surrounding an AI model loop. Six chapters and eleven deep-dive references cover memory, skill loading, tools and permissions, context engineering, multi-agent coordination, and lifecycle design, with tradeoffs and common failure modes. The patterns were distilled from source-level analysis of the Claude Code runtime, but they are presented as runtime-agnostic principles for people building coding agents, plugins, or orchestration systems—not as a source mirror or a beginner user guide.

Skilld turns NPM dependencies or GitHub sources into local skills built from maintainers' documentation, release notes, and issues, keeping guidance tied to the versions you actually use. LLM enhancement is optional, semantic search is available across indexed references, and a no-agent mode still produces a base skill and portable prompts. It requires Node.js 22.6 or newer.

AgentSkills detects supported AI tools on your computer and provides one desktop interface for viewing, installing, editing, uninstalling, and synchronizing their skills. Browse packages from skills.sh or ClawHub, edit SKILL.md files in place, and copy a skill across agents with one action while disk changes refresh automatically. The app supports Windows, macOS, and Linux and is aimed at people who use several coding agents.

zot packages a coding-agent loop into a single Go binary with interactive TUI, print, and JSON modes plus read, write, edit, and shell tools. It supports many direct APIs, selected subscription logins, cloud platforms, and local Ollama-style models, with session recovery and cost tracking. Optional subprocess extensions can be written in any language, and a built-in Telegram bridge enables remote conversations.

Godcoder is an open-source desktop coding agent that sends model requests directly from the user’s machine to a configured provider without a project-operated intermediary; any code or context included in those requests is still handled by that provider. It combines file editing, terminal access, sessions, MCP servers, voice integration, and local context search. Harness mode scaffolds and improves an agent workflow in a sandbox, while CoWork mode can practice operating the bundled Open Cowork desktop environment for GUI-driven tasks.

This progressive sample shows how to protect an ASP.NET Core Web API with the Microsoft identity platform and call it from a WPF desktop application after user sign-in. Later chapters add on-behalf-of access to Microsoft Graph, personal Microsoft accounts, and proof-of-possession tokens. Running the examples requires .NET and Visual Studio on Windows, a Microsoft Entra tenant, and an eligible user account, so it is intended as learning material rather than a finished application.

simple-modern-uv is a compact template for Python 3.11–3.14 projects, paired with an Agent Skill that can create a new package, modernize an existing repository, or apply later template updates. It sets up uv, Ruff, BasedPyright, and GitHub Actions, and can migrate projects from Poetry, setuptools or pip, and PDM while tailoring license and PyPI publishing files.

amux is a self-hosted, tmux-native control plane for running many Claude Code, Codex, and Gemini sessions from a web dashboard, mobile PWA, or iOS app. It adds watchdog-based recovery, persistent sessions, an atomically claimed Kanban board, inter-agent messaging, REST orchestration, live output inspection, and token tracking. It is designed for developers coordinating a larger fleet of long-running coding agents.

SkillsVote connects skill collection, profiling, just-in-time recommendation, and post-task attribution into one lifecycle workflow. It offers a hosted integration for recommendation and feedback, plus a local-first option for private SKILL.md libraries. Local attribution and evolution are still on the roadmap rather than fully available.

Flutter Markdown Editor opens existing .md files from the file explorer and creates new ones with formatting controls for headings, links, tables, and other Markdown elements. Users can switch between editor and preview or view both at once, with image preview, LaTeX rendering, themes, and a multilingual interface. The app is mainly designed for mobile use, though the repository also publishes builds for some desktop platforms.

WSL UI gives Windows users a graphical way to monitor WSL2 distributions, inspect CPU, memory, and disk usage, and open terminals, file explorers, or IDEs. It supports restart, export, import, clone, restore, custom actions, configuration editing, and disk mounting, and can install distributions from stores, container images, LXC catalogs, or custom URLs. The application is specifically for Windows systems using WSL rather than a general Linux manager.

Core Data Agent Skill gives compatible AI coding tools focused guidance for Apple’s persistence framework. Its decision tree routes the agent to references on model configuration, fetch optimization, batch operations, saving, schema migration, performance, persistent history, CloudKit integration, and project audits. Developers can install it through the standard skills command, as a Claude Code plugin, or by manually linking the folder. It is intended for Swift projects needing practical Core Data diagnosis and implementation advice without imposing a particular application architecture.

claude-android-skill gives Claude Code an opinionated workflow for modern Kotlin applications, covering Jetpack Compose, MVVM and unidirectional data flow, layered architecture, offline-first storage, Hilt, and testing. Once copied into the skills directory, it activates for Android requests and can use bundled references, Gradle templates, and a feature-module generator. The repository is still marked as work in progress and is designed around this specific Android stack.

KubeShark is a Kubernetes skill for Claude Code and Codex that targets common agent mistakes such as deprecated APIs, wildcard RBAC, missing resource limits, and mismatched selectors or ports. Its failure-mode-first workflow diagnoses risks before loading only the relevant references for Kubernetes, Helm, Kustomize, cloud platforms, security, or policy engines. Outputs include assumptions, tradeoffs, validation steps, and rollback notes. It guides coding work; it is not a cluster monitoring or runtime observability product.

Oxylabs Agent Skills help an assistant choose among proxy networks, Web Unblocker, structured scraping, remote headless browsers, and video data services based on the task. The collection installs through a Claude Code plugin or a generic skills command and includes product-specific usage patterns. Running those services requires the corresponding Oxylabs account credentials in environment variables.