Build synchronized AI agents visually or through a TypeScript SDK.
Project overview
Inkeep Agents lets non-technical teams design agents on a drag-and-drop canvas while engineers define the same agents in a TypeScript SDK, with two-way synchronization between both formats. It supports customer assistants, internal copilots, and multi-agent workflow automation, along with MCP credential handling, embeddable chat components, tracing, and Vercel or Docker deployment. The platform can be self-hosted, but it uses Elastic License 2.0 with supplemental terms rather than a permissive open-source license.
Collection or directoryDevOps and deploymentClaude Code
agent-skills
@hashicorp·Shell
Add HashiCorp skills for Terraform and Packer development.
Project overview
Equip supported coding agents with guidance for writing Terraform HCL, building modules, developing providers, running tests, and creating Packer machine images for AWS, Azure, or Windows with HCP Packer integration. Skills can be installed individually through the skills CLI or as Claude Code plugins.
Tailor truthful resumes to job descriptions using an existing Markdown resume library.
Project overview
Install this Claude skill to tailor a resume for one role or a small batch of job descriptions using material already stored in Markdown. The workflow researches the role and company, identifies relevant real experience, scores the fit, and assembles a targeted resume without inventing qualifications. It assumes you have an existing Markdown resume library and is packaged for installation through Claude's skill interface or skills directory.
Host scalable browser-based video meetings and collaboration on your own server.
Project overview
MiroTalk SFU lets organizations run browser-based video conferencing and real-time collaboration on infrastructure they control. Its mediasoup-based selective forwarding architecture is designed for multi-participant rooms and streaming-oriented use cases, while a REST API supports integration with other systems. The self-hosted model keeps meeting data and deployment choices under the operator's control. It is therefore best suited to teams prepared to configure, secure, monitor, and scale their own server rather than those seeking a fully managed meeting service.
Read RSS locally and let AI agents triage feeds from the command line.
Project overview
Papr combines an offline-first desktop RSS reader with an agent-facing CLI over the same local database, so subscriptions, articles, and reading state stay aligned. The app manages feeds, folders, tags, rules, full-text extraction, and saved views, while the CLI lets agents search, read, mark, refresh, and sync items from the shell. No Papr account or cloud is required by default; optional summaries, article Q&A, and digests use your own API key.
Collection or directorySoftware developmentClaude Code
swift-ios-skills
@dpearson2699·Python
Install focused agent skills for modern Swift and iOS development.
Project overview
This collection gives Claude Code, Codex, Cursor, and other compatible agents focused guidance for building Apple-platform apps. Its 86 self-contained skills cover SwiftUI, concurrency, data, system frameworks, testing, performance, and other iOS engineering topics, with examples aimed at iOS 26+ and Swift 6.3. Users upgrading from older releases should note that some skill paths were renamed.
Desktop appDesign and creative workModel Context Protocol
LichtFeld-Studio
@MrNeRF·C++
Train, edit, automate, and export Gaussian Splatting scenes in one workstation.
Project overview
LichtFeld Studio combines 3D Gaussian Splatting training, real-time inspection, selection editing, and export in one native workstation. Users can train from COLMAP datasets, resume checkpoints, transform Gaussian subsets with history support, and deliver PLY, SOG, SPZ, or a standalone HTML viewer. Python plugins, embedded scripts, and MCP tools support extension and automation. Prebuilt distribution focuses on Windows and NVIDIA GPUs. Source builds use C++23 and CUDA 12.8 or newer, while current Windows builds also require a recent NVIDIA driver.
Install, run, route, and inspect multiple local coding agents from one desktop workspace.
Project overview
WeSight brings local coding agents such as Claude Code, Codex, OpenClaw, and Hermes Agent into a graphical desktop workspace. Users can reuse existing CLI accounts and configuration, or install supported engines through a macOS setup flow, then inspect commands, file changes, permission prompts, tool results, and generated artifacts inside a chat interface. Model routing covers official providers, Ollama, and custom OpenAI-compatible endpoints. The app also tracks token and runtime metrics, manages skills and scheduled tasks, and can route work through IM channels such as Feishu.
Collection or directoryMarketing, growth and sales
marketingskills
@mysticaltech
Add conversion, copywriting, SEO, analytics, and growth workflows to compatible AI agents.
Project overview
This marketing skill collection packages repeatable workflows for A/B testing, analytics tracking, competitor pages, content strategy, copy editing, landing-page conversion, email sequences, and SEO audits. It is a fork of coreyhaines31/marketingskills that adds prebuilt `.skill` files for easier installation in Claude Code and other Agent Skills-compatible tools.
Collection or directoryResearch and knowledgeClaude Code
qinyan-academic-skills
@LeonChaoX·Python
Add research, paper-writing, literature-search, and grant-proposal skills to AI agents.
Project overview
Qinyan Academic Skills is a broad collection for literature search, scientific writing, reviews, research planning, Chinese national grant applications, bioinformatics, drug discovery, clinical research, machine learning, and data analysis. Researchers can install the full library or deploy a category or individual skill to Claude Code, Cursor, Codex, Gemini CLI, OpenClaw, and other supported tools.
Create, send, fill, and sign PDF forms on a self-hosted platform.
Project overview
DocuSeal lets teams turn PDFs into online forms with a visual field builder, assign multiple submitters, and collect completed documents and electronic signatures from phones or desktops. The self-hosted platform also supports automated email, signature verification, user management, local or cloud object storage, plus APIs and webhooks for integration. Its base application can be deployed quickly with Docker. Advanced capabilities such as white-labeling, SSO, SMS identity verification, bulk sending, and embedded builders or signing forms are listed as Pro features.
Control and troubleshoot Android devices through a desktop interface for ADB.
Project overview
AYA provides a graphical desktop interface for common Android Debug Bridge workflows. After connecting a device, developers can mirror its screen, browse files, manage applications, inspect layouts, view Logcat, open a shell, and monitor processes or performance. Release packages are available for Windows, Intel and Apple Silicon Macs, and x86-64 Linux, making it useful for teams that prefer visual device management over repeated ADB commands.
Turn videos, audio, and podcasts into summaries, transcripts, articles, and notes.
Project overview
BibiGPT Skill routes video and audio tasks through a desktop CLI, remote MCP server, OpenAPI, or Codex plugin. Its workflows cover quick summaries, chapter-level deep dives, transcript extraction, article rewrites, batch processing, multi-source research, and exports to Notion, Obsidian, or local files. The remote MCP option uses OAuth without a local install, while other modes require the BibiGPT client or service endpoints.
Host a multi-user RSS reader that organizes feeds and syncs with native clients.
Project overview
FreshRSS brings RSS, Atom, and selected feedless websites into a self-hosted reader with per-user organization and custom tags. It can receive WebSub updates, expose APIs to mobile and desktop clients, and scrape basic website content; hosting requires a web server, PHP 8.1 or later, and a supported database.
Scan disk images or raw devices and recover lost or deleted files.
Project overview
Digler analyzes disk images and physical devices through either a command-line interface or desktop application. Its scan-first workflow creates a DFXML report, which can then guide selective file recovery; on Linux, results can also be mounted as a browsable FUSE filesystem. File carving is designed to work independently of the original filesystem, and plugins can add scanners for new formats. Prebuilt binaries cover macOS, Windows, and Linux, but the project remains at an early v0.1.0 stage.
Turn Markdown notes into a searchable semantic knowledge graph.
Project overview
Automatically chunk, embed, tag, and connect Markdown notes by semantic similarity, then search them by meaning, explore them on a graph canvas, or synthesize cited wiki articles and recurring reports. Atomic runs as a desktop app or self-hosted server and exposes MCP tools for other assistants; semantic and generative features require Ollama, OpenRouter, or another OpenAI-compatible provider.
Turn video ideas into timed, production-ready prompts for Seedance on Higgsfield.
Project overview
This set of Claude skills expands a simple video concept into a detailed Seedance 2.0 prompt with second-by-second timing, camera direction, lighting, sound layers, source-media references, and opening hooks. It covers formats such as SaaS launches, faceless channels, personal brands, and short-form social clips. The skills create prompts for Higgsfield rather than rendering the final video themselves.
Manage Claude Code projects, sessions, and custom agents from a desktop interface.
Project overview
opcode provides a desktop command center for Claude Code, combining project and session management with custom or background agents, usage tracking, MCP server controls, checkpoints, and CLAUDE.md editing. On first launch it detects the existing ~/.claude directory, so users can keep their native Claude Code configuration while working visually. The Claude Code CLI must still be installed and available on the system.