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

Venice Skills packages the Venice API into separate, on-demand Agent Skills for authentication, chat, Responses, embeddings, image generation, image editing, and other surface areas. Each folder contains a `SKILL.md` that an agent runtime can load when the corresponding endpoint is needed, and the catalog is maintained alongside the API specification. You can install the full `skills` directory or only selected folders into Claude Code, Codex, Cursor, Hermes, and compatible hosts. This is instruction material for agents, not a standalone Venice client.

LRReader is a desktop reader and management client for LANraragi. Connect to one or more servers to browse and search archives, open them in the reader, save bookmarks, edit archive metadata or categories, and handle selected server administration from the app. It requires LANraragi 0.9.10 and supports Windows 10 as well as modern Linux distributions. The Linux build is still experimental and does not yet include every feature available on Windows.

Warteschlangensimulator lets users build queueing networks as flowcharts for production, logistics, and service processes, then simulate waiting times, bottlenecks, and resource utilization. Runs can be animated and followed by statistical evaluation, while command-line operation and automated parameter studies support repeated experiments. Windows and Linux packages are available, making it useful for teaching, research, and planning scenarios where static averages are not enough.

ClaudeMeter shows five-hour session usage, seven-day usage, and Sonnet-specific limits in the macOS menu bar, with color-coded icons, pacing warnings, configurable threshold notifications, and automatic refresh. It can import a Claude session from local browser cookies or accept a session key manually, stores that credential in Keychain, and exports usage percentages as JSON for status-line scripts or dashboards. This is an unofficial client that accesses Claude’s web API through browser authentication; the project warns that this may violate Anthropic’s terms and could affect the account.

Codex Skills Library packages common engineering workflows into small, reusable skills instead of requiring teams to repeat prompts. Its domains include codebase orientation, debugging, refactoring, tests, documentation, APIs, frontend and backend work, data, infrastructure, security, performance, reliability, architecture, and planning. Each skill is triggered through natural language and reveals its workflow only when relevant. Users browse the `skills/` directory, select the task they need, and can adapt or extend the library for their team.

This collection provides Agent Skills and plugins for Expo and React Native development. Installed through supported Codex, ChatGPT, or Claude plugin flows, the workflows can generate platform-aware app icons, scaffold projects from templates, create local Android and iOS release artifacts, and add a shared cross-platform theming system. The repository is aimed at mobile developers who want coding agents to handle repetitive setup and platform-specific details. Individual plugins may still require their companion CLI, an OpenAI-backed image service, or local Android and Xcode build tooling.

AEGIS Desktop is a Windows client for operating an existing OpenClaw environment through a dedicated graphical interface. It combines multi-tab chat, voice sessions, agent management, cron jobs, cost analytics, configuration, terminal access, plugins, files, and memory tools. The app is only a frontend: AI execution and data remain in a local or remote OpenClaw Gateway, so users need a working gateway before the desktop client becomes useful.

yt-dlp GUI wraps yt-dlp in a desktop app for Windows, macOS, and Linux, letting users paste a link, choose video quality or audio output, and manage downloads without writing commands. It supports playlists, concurrent queues, pause and resume, clip trimming, subtitle extraction, thumbnail saving, and live-chat archiving, plus a browser extension that passes URLs and cookies to the app. The yt-dlp binary is downloaded during setup, and some YouTube formats may also require Deno.

DingTalk Wukong Skills is a multi-skill collection extracted from Wukong v0.9.2 for Claude Code, Gemini CLI, Codex, and similar agents. It covers DingTalk OA, tasks, calendars, and documents; Word, Excel, PowerPoint, and PDF handling; and travel or local-information queries for 12306, Ctrip, and Dianping. A skill-creation utility is included. Because the repository nests skills across several directories, installation must use full-depth discovery. The package reflects a specific Wukong release rather than a live DingTalk client.

Manage Linear work without leaving Claude Code: create projects and sub-issues, update statuses, apply labels, and sync batches of code changes. The skill supports simple MCP actions alongside TypeScript SDK scripts and direct GraphQL queries, so teams can move from routine commands to more customized automation. A Linear API key is required.

Kasetto is a declarative CLI for keeping AI-agent environments consistent across projects, machines, and teams. A YAML file and lockfile define skills, commands, MCP configurations, and instruction files, which can then be synchronized into Claude Code, Codex, Cursor, and many other agents. It also supports composable configs, private repositories, locked CI runs, and secret injection from existing credential managers.

Use Claude Code to run an ongoing D&D 5e campaign with dice rolls, combat, NPCs, character state, and story progress preserved between sessions. An optional companion can stream narration and party status to a TV or tablet while players submit actions from their phones. The skill is built specifically for Claude Code.

Secops is a desktop application that exposes selected Ubuntu security controls through a graphical interface. End users can download a release instead of working through command-line configuration, while contributors need the project’s CMake, frontend, and Rust development setup. The repository explicitly notes that more security settings still need to be added, so it should be treated as an evolving control panel rather than a complete security suite.

Kodo assigns a goal to coding backends such as Claude Code, Cursor, Codex, Gemini, or Kimi and coordinates repeated work cycles with independent verification. It can implement features, run improvement reviews, test software through realistic user workflows, and fix findings from earlier runs, with effort levels controlling how aggressively agents iterate. At least one supported coding-agent backend must be installed.

Modular Skills gives AI coding agents official, task-specific guidance for working with Mojo and the MAX platform. The collection can be installed all at once or skill by skill, with workflows for starting projects, handling Mojo–Python interoperability, importing model architectures, and debugging output divergence. It augments an existing coding agent rather than serving as a standalone development environment.

This kit converts text-layer PDFs from Traditional to Simplified Chinese while trying to retain page size, images, selectable text, and overall layout. An image-only cover can be replaced in a separate step, and the workflow is also packaged as a Codex skill. The included example PDFs and cover are not automatically relicensed under the code’s MIT license.

Riichi Mahjong Calculator analyzes hand efficiency, open-hand choices, winning hands, and scores from han and fu. Its default rules follow Mahjong Soul and Tenhou conventions with some customization. Tile inputs can be recognized from images or the clipboard, with the recognition model tuned for Mahjong Soul screenshots. Calculations run locally, and builds are available for web, Android, desktop, and self-signed iOS installation.

Oxide Lab provides a desktop chat interface that runs compatible language models entirely on the user's machine. It loads GGUF or SafeTensors models across several Llama, Qwen, Mistral, DeepSeek, and related architectures, with CPU, NVIDIA CUDA, or Apple Metal acceleration. Users must obtain a compatible model before chatting, and larger models require more memory than the stated 4 GB minimum.