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

SuperAgentX coordinates modular agents that can carry out multi-step workflows across browsers, APIs, databases, conventional tools, and MCP integrations. Sensitive actions can pause for human approval, while execution state, memory, and audit logs are retained. It is aimed at applications that need agents to take actions without giving up governance or operator control.

Medusa Agent Skills packages framework conventions into task-focused plugins for AI coding agents. The plugins cover backend, admin, and storefront development, an interactive tutorial, ecommerce storefront practices, and Medusa Cloud management through its CLI. Claude Code users can install from the plugin marketplace, while other agents can copy skill directories and optionally configure related MCP assets. The collection is specifically for Medusa and guides an agent toward established architecture; it does not replace the application runtime or cloud account.

Qdrant Skills gives coding agents decision-oriented guidance for vector-search engineering. It covers scaling, quantization, performance, search quality, monitoring, deployment, tenant isolation, embedding-model migration, upgrades, and SDK use across several languages. Users can install the Qdrant Advisor to load matching guidance dynamically or keep the full set locally for offline triggering. The material acts as a solutions-architecture handbook explaining when and why to choose an approach and pointing to relevant documentation, rather than teaching Qdrant from scratch.

Kimi Skills gives AI agents dedicated workflows for creating and editing DOCX, PDF, and XLSX files. The skills cover structured document layouts, native charts, tracked changes, formulas, PivotTables, PDF processing, and output validation rather than basic text export alone. They can be installed together through npx, but each workflow relies on its own local toolchain, including combinations of .NET, Node.js, Python, Playwright, and OpenXML libraries.

Bloom turns a topic, uploaded source, or project files into a guided learning experience with a syllabus, lessons, annotations, feedback, evaluation, and summaries. It can run as a portable Claude Code tutoring skill or as a self-hosted web app. The web mode requires an OpenAI-compatible model API key, while the CLI mode uses Claude Code directly.

any2pdf lets an AI coding assistant convert Markdown into a styled PDF through a conversational workflow. The agent can ask about themes, frontispieces, watermarks, and back covers, then produce documents with covers, a clickable table of contents, bookmarks, headers, and footers. Its main distinction is handling mixed CJK and Latin text, system font discovery, formulas, images, and Obsidian callouts across macOS, Windows, and Linux. It uses Python with reportlab and can also be run directly from the command line.

These skills let coding agents use context captured by Entire, including sessions, Checkpoints, prompts, and git history. Ask an agent to find earlier work, explain why code changed, review a branch, or prepare a session handoff without memorizing CLI commands. They are most useful in repositories with substantial captured history, and some indexed searches require the Entire CLI and login.

SSH Keys Manager replaces routine terminal edits with a native Mac interface for browsing, generating, renaming, duplicating, and removing key files. It also provides a form-based SSH config editor for Host blocks and IdentityFile mapping, plus menu-bar copying and reachability checks. A read-only mode blocks edits, overwrites, renames, and deletions when you only want to inspect a workspace. Current release builds are unsigned and not notarized, so macOS may require a manual quarantine workaround.

FFUF Skill for Claude Code connects the ffuf web fuzzer to natural-language requests for discovering hidden paths, files, subdomains, and API endpoints. It helps choose wordlists and analyzes results while using rate limits and other safer defaults. You must install ffuf and a supported Claude client, and only test systems you own or are explicitly authorized to assess.

This Agent Skills collection covers a video subtitle workflow from audio transcription to publishing support. It converts common audio formats into SRT files, can refine wording and proper nouns against an `origin.md` transcript without changing timestamps, adds card annotations, and generates platform-specific summaries for Facebook, Threads, and YouTube. Each stage can be invoked separately or combined into the provided workflow. Users need to prepare the expected files in the same working directory and install the dependencies required by the individual skills.

Listen to MP3, WAV, and FLAC files or M3U8 radio streams without leaving the terminal. The text-based player includes file browsing, playlists, lyrics, volume and progress controls, next-track actions, and a waveform animation when lyrics are unavailable. It supports macOS, Linux, and Windows, with installation options through Snap, the Arch User Repository, and prerelease binaries. The project remains under development, and some Linux audio-device configurations may require manual troubleshooting before sound output works correctly.

TanStack Agent Skills gives coding agents structured rules for Query, Router, and Start. The guidance covers cache keys and invalidation, mutations, error handling, type-safe routes, loaders, search parameters, navigation, server functions, middleware, authentication, SSR, and security. Install the skills into a project with the cross-agent command, then compatible assistants can load them for relevant development or review tasks. The repository is a best-practice reference; it does not install or run the TanStack libraries or application.

This documentation library packages agents, instructions, and skills for UI, API, end-to-end, regression, accessibility, and flaky-test work. Teams can embed the material into projects using GitHub Copilot, Claude, Cursor, or similar assistants, with guidance for Playwright TypeScript, Selenium Java, and ISTQB-aligned planning. The repository is a knowledge base and has no build, lint, or test system of its own.

Abu Cowork is a local-first desktop AI agent that can plan multi-step work, read and write files, run commands, control a real browser, and create documents or web pages from natural-language requests. Risky actions such as deletion, overwriting, sending, or installation can be placed behind a reviewable plan and explicit approval. Each conversation can use its own model and permission mode. The app also supports installable skills, MCP connectors, schedules, and team messaging channels for broader automation.

Give Image2 UI Skill a screenshot, design mockup, or app reference and it guides Codex to produce a working clickable demo. Text, buttons, navigation, forms, icons, and interaction states are implemented in code, while complex photography, textures, illustrations, or product imagery are generated with image2. Those assets are saved inside the project and wired into the interface, so the result is a usable prototype rather than a disconnected set of generated images.

Auto Screenshot saves full-screen captures at intervals ranging from one second to 24 hours. It supports multiple displays, configurable names and folders, inactivity pauses, startup capture, old-file cleanup, hotkeys, and commands that run before or after each screenshot. Images can be written in formats including PNG, JPEG, WebP, and AVIF, with installer or portable options for Windows and portable or DEB packages for Linux.

Pin multiple skill repositories as flake sources, recursively discover their SKILL.md directories, namespace duplicate IDs, and select exactly which skills enter a bundle. Home Manager integration can sync that bundle to global or project-local destinations for Codex, Claude, Cursor, OpenCode, and other agents. Targets are opt-in rather than automatically installed, making the project best suited to Nix users who want reproducible skill management.

OpenZeppelin Skills gives agents structured workflows for secure contract development using the OpenZeppelin Contracts ecosystem. The available skills cover project setup and contract upgrades across Solidity, Cairo, Stylus, and Stellar, while the secure-development workflow can use the OpenZeppelin Contracts CLI to generate reference implementations. Users can install the collection through the Skills CLI, a Claude Code plugin, or manual copying, making it most relevant to teams already building with OpenZeppelin libraries.