Find Agent Skill tutorials, official repositories, marketplaces, and curated resources.
Project overview
Use this multilingual guide to understand skill structure, installation paths, marketplaces, and common management tools across agent ecosystems. It curates official skill repositories from model providers, cloud platforms, and developer-tool vendors, while comparing usage in apps, coding agents, and OpenClaw-style harnesses. The guide also highlights security review practices; its bundled creation and testing toolkit is currently limited to Claude Code.
Scaffold or starterSoftware developmentClaude Code
godogen
@htdt·Python
Generate a runnable Godot, Bevy, or Babylon.js game from a short description.
Project overview
Godogen publishes a thin, fresh game repository and lets Claude Code or Codex scaffold the project, generate assets, run the chosen engine, and iterate from a live game or recorded proof. It supports Godot 4, Bevy, and Babylon.js. Full runs require the matching engine toolchain plus API keys for the configured image, video, or 3D asset services.
Work with Mistral models through a conversational coding CLI
Project overview
Mistral Vibe is Mistral's open-source command-line coding assistant for exploring, searching, and editing projects through natural language while running shell commands when needed. It supports delegated subagent tasks, reusable skills, and selectable agent profiles; voice input is experimental, and Unix environments are the official target even though Windows can run it.
Generate self-contained technical diagrams with theme switching and high-resolution exports.
Project overview
Archify converts a plain-language system or process description into a self-contained HTML diagram. It supports architecture, workflow, sequence, data-flow, and lifecycle views, with dark and light themes plus PNG, JPEG, WebP, SVG, and clipboard export. A typed intermediate format, bundled validators, and post-render checks help keep targeted edits stable without requiring extra runtime dependencies.
Automate browser tasks in isolated sessions with human takeover when agents get stuck.
Project overview
BrowserAct gives AI agents commands for navigation, element inspection, clicking, form input, and data extraction while keeping parallel tasks and accounts in separate sessions. For protected pages, it can use stealth modes, CAPTCHA handling, or a remote-assist link for human takeover. Core browser automation is free, while managed proxies and more than five stealth browsers are paid.
Let Claude Code inspect and control charts in your local TradingView Desktop app.
Project overview
tradingview-mcp bridges Claude Code or a terminal CLI to a local TradingView Desktop session through Chrome DevTools Protocol. It supports Pine Script iteration, symbol and timeframe navigation, indicator reading, chart drawing, alerts, replay practice, screenshots, and JSONL monitoring. A valid TradingView subscription is required, and the desktop app must be launched with its debugging port enabled. The project is an interface for personal, educational, and research workflows rather than an autonomous trading bot, and users remain responsible for complying with TradingView's terms.
General agentSoftware developmentModel Context Protocol
gptme
@gptme·Python
Run an extensible personal agent with local tools from your terminal.
Project overview
gptme turns a terminal into an interactive or persistent agent workspace that can inspect and change local projects, run commands, and browse the web or process images when needed. It supports several hosted model providers as well as local llama.cpp models, and can be extended through plugins, skills, MCP tools, ACP editor integration, and templates for scheduled autonomous agents.
Write and review more modern, accessible SwiftUI code with an AI coding skill.
Project overview
SwiftUI Pro is an installable agent skill for Claude Code, Codex, Gemini, Cursor, and other coding assistants. It targets recurring model mistakes in SwiftUI API use, state management, layout, animation, performance, deprecated features, and VoiceOver accessibility, and can run as a broad review or focus on one concern. The documented guidance targets iOS 26 or later and Swift 6.2 or later, making it most relevant to projects adopting current Apple platform APIs.
Run a private skill registry with publishing, versioning, search, RBAC, and audit trails.
Project overview
SkillHub gives organizations a self-hosted place to publish, discover, install, and manage reusable agent skills. Packages can use semantic versions and release tags, while team namespaces define membership, roles, visibility, and publishing policies. Review gates and audit logs support governed internal sharing behind an organization's firewall.
Reuse Codex skills for Apple development, reviews, debugging, and refactoring.
Project overview
Add focused skills for App Store release notes, GitHub operations, iOS debugging, macOS packaging, SwiftUI and React improvements, and multi-agent review or bug-hunt workflows. Each skill is self-contained and installed under the Codex skills directory, so developers can invoke only the workflow relevant to the current project. The collection is especially useful for recurring Apple-platform and code-quality tasks.
Run a local Codex fork with browser tools and multiple agents
Project overview
Every Code is a community fork of OpenAI Codex for local terminal development. It extends the upstream tool with browser actions and multi-agent workflows, while Auto Drive and background Auto Review support longer execution and non-blocking checks. It supports ChatGPT sign-in or API-key use, can orchestrate external CLIs such as Claude and Gemini, and is not an official OpenAI product.
Coordinate multiple coding CLIs in one visual parallel workspace.
Project overview
Golutra turns existing coding CLIs such as Claude Code, Codex, Gemini, and OpenCode into a shared multi-agent workspace. Users can run agents in parallel, orchestrate longer workflows, import or export templates, inspect individual logs, inject prompts during execution, and track handoffs in a visual interface. It keeps the underlying CLI tools and project layout intact, making it useful for developers who want centralized oversight without migrating their work to a new agent runtime.
Prompt packImage generation and editingClaude Code
GPT-Image2-Skill
@wuyoscar·Python
Generate and edit GPT Image 2 visuals with curated prompts and a CLI.
Project overview
GPT-Image2-Skill combines a curated prompt gallery, an Agent Skill, and the `gpt-image` CLI for OpenAI image generation and editing. You can request gallery examples in natural language from Codex, Claude Code, OpenClaw, Hermes, and similar runtimes, or copy prompts into the command line and adapt them for posters, UI mockups, game interfaces, photography, maps, typography, or reference-image edits. The repository also explains prompt structure in English and Chinese. Scientific figures are framed as references or reproducible workflow targets, not unchecked final publication assets.
Collection or directoryWorkflow automationClaude Code
skills
@browserbase·JavaScript
Give Claude Code browser automation, site testing, tracing, and cloud function deployment.
Project overview
Browserbase Skills adds installable browser workflows to Claude Code through the official browse CLI. An agent can automate local or remote browsing, test websites, capture detailed browser traces, infer APIs from observed traffic, or deploy browser automation as cloud functions. It can start an isolated local browser or reuse an existing Chrome session when cookies and sign-in state are needed.
Turn agent-run learnings into readable, editable, reusable Skill files.
Project overview
Acontext is an open-source memory layer that captures reusable lessons from AI-agent runs and stores them as ordinary Markdown Skill files. Developers can read, edit, version, mount, or share those memories across models and frameworks without relying on embeddings or a closed memory format; agents retrieve the needed files through tools and reasoning. Users can connect to the hosted service with an API key or self-host the backend with Docker, which requires an OpenAI API key.
Turn approved specifications into long-running implementation tasks with independent review.
Project overview
cc-sdd installs a spec-driven development workflow as Agent Skills, moving from discovery, requirements, and design into task generation and long-running implementation. Each task can be handled by a fresh implementer using test-driven development, followed by an independent reviewer and an automatic debugging pass. The same seventeen skills target eight coding agents and thirteen languages; Claude Code and Codex are stable, while the other integrations remain beta.
Load local UI and native-feature tweaks into the Codex desktop app.
Project overview
Codex++ patches the locally installed Codex Desktop app so a small runtime can load tweaks from a user-owned folder. Those tweaks may alter the interface, add settings pages, run main-process code, or use OS-level features through its native bridge, while runtime files, configuration, logs, backups, and tweak data remain outside the app bundle. A watcher can reapply the patch after Codex updates. This is an unofficial modification that executes local extension code, so users should rely on its diagnostics, safe mode, repair, and uninstall controls.
MCP serverFinance, legal and complianceModel Context Protocol
tradingview-mcp
@atilaahmettaner·Python
Give AI clients market data, technical analysis, screeners, and backtests.
Project overview
tradingview-mcp exposes market quotes, screeners, technical indicators, sentiment, and strategy backtests for stocks, crypto, forex, and futures through MCP. It can be self-hosted for free or used through a managed connector. The server does not sign in to TradingView or place trades, and it is an independent project using third-party data that may be delayed or incomplete; its outputs are informational rather than financial advice.