Find the open-source solution that fits.

Project overview

Atom is a self-hosted platform for running business workflows from text or voice requests. Specialized agents plan and execute work across connected services, while visual workflows, memory, and governance levels help operators control how tasks progress. Workflow data, agent state, and memory remain on infrastructure controlled by the operator. Prompts still go to a configured cloud model when bring-your-own API keys are used, unless local models such as Ollama or Llama.cpp are selected. Deployment requires operating the backend, frontend, database, and model configuration.

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.

Project overview

video-editing-skill gives OpenClaw and Codex a local workflow for talking-head, interview, and vlog footage. It can transcribe speech, split sentences, choose and merge clips, burn subtitles, and prepare plans for short-form batches, hook variants, jump-cut fades, picture-in-picture overlays, and vertical reframing. Optional YOLO analysis can identify scenes or subjects, while a lighter mode produces sampled frames for review. It suits creators who want a script-driven process with JSON and Markdown artifacts, not a fully graphical one-click editor.

Project overview

Cangjie Skill turns books, courses, long videos, podcasts, interviews, and other transcripts with reusable methods into modular agent skill packages rather than ordinary summaries. Its workflow maps the source, extracts frameworks, principles, examples, counterexamples, and terminology in parallel, filters weak candidates, and stress-tests the remaining skills. Deliverables can include an overview, skill index, reader digest, glossary, individual SKILL.md modules, and test prompts, making it best suited to structured reuse instead of simple content compression.

Project overview

Serenity.skill guides an agent through supply-chain research for themes such as AI, semiconductors, and robotics. It maps demand and industry layers, looks for bottlenecks with limited suppliers, difficult capacity expansion, or long qualification cycles, then checks filings, financial reports, customers, capacity, and risks. The output is a prioritized list of companies or fund directions with an evidence trail and follow-up checks. It is strictly a research aid: it does not execute trades, promise returns, or replace the user's final investment decision.

Project overview

Agent Skill Creator converts prose, PDFs, links, scripts, or transcripts into a reusable skill with a SKILL.md, working code, an evaluation specification, and an installer. It validates and security-scans the generated package, then adapts it for Claude Code, Codex, Cursor, Gemini, and other supported tools. This is aimed at teams that want to package repeatable internal workflows without hand-writing each skill.

Project overview

MathLens is a Cursor Agent Skill that accepts a math problem as text or an image and carries it through analysis, visual explanation, storyboarding, voiceover generation, and Manim animation. Its workflow validates audio timing and writes synchronization details back into the storyboard before rendering. The repository includes initialization, TTS, structure-checking, validation, and rendering scripts for producing step-by-step teaching videos.

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.

Project overview

Give a capable coding agent an article, argument, or product brief and this skill guides it through an editorial-magazine or Swiss-grid presentation workflow. It can produce a horizontal single-file HTML deck, supporting imagery, and matching social covers, with a low-power static mode for presentation. The format suits talks and opinion-led storytelling more than dense tables or collaborative editing, and its primary deliverable is HTML rather than native PPTX.

Project overview

She Love Me is an agent skill that extracts WeChat or QQ conversations and applies frameworks such as attachment styles, Gottman, and Sternberg to produce relationship-pattern analysis, risk signals, and practical suggestions. The results are guidance, not a definitive judgment. Its agent workflow emphasizes local processing; the traditional path exports messages.json and an analysis prompt, and whether those files leave the device depends on the chat model selected. Windows supports both platforms, macOS WeChat support is experimental, and Linux currently relies mainly on QQ.

Project overview

Comet organizes coding work into guarded phases from specification through build, verification, and archive, recording state so an interrupted task can resume without reconstructing its history. It also helps create, compose, distribute, and evaluate reusable skills across many coding agents. The CLI requires Node.js 20 or newer.

Project overview

AstronRPA provides a low-code and no-code desktop designer for automating Windows applications, browsers, office files, data processing, image recognition, and system operations through prebuilt workflow components. Processes can run directly, on schedules, through APIs or MCP, and can exchange capabilities with the separate Astron Agent platform. It primarily targets Windows 10 and 11 and is designed for team or enterprise deployments that normally include a Docker-based server and a configured desktop client.

Project overview

Spine Animation AI helps Claude turn separated character images and a reference pose into Spine 2D skeletal animation assets. It can position parts with image matching, build skeleton JSON and draw order, generate common motions such as idle or walk, and create interactive HTML5 previews. It can also refine an existing Spine skeleton, but users still need well-prepared artwork and a specific animation goal.

Project overview

YouTube Automation Agent links topic planning, script writing, thumbnail and SEO work, media production, publishing, and analytics into a scheduled self-hosted workflow with a local dashboard. Real uploads require YouTube Data API OAuth, assembly requires FFmpeg, and generated text, speech, images, or video depend on configured providers. Without the relevant keys, some stages use templates or simulations; placeholder media is refused by the uploader, and publishing defaults to private.

Project overview

karpathy-llm-wiki turns incoming sources into durable, cross-linked Markdown pages instead of reprocessing raw documents for every question. Its ingest, query, and lint operations update the wiki, answer from existing pages with citations, and check link or index health. It follows the Agent Skills standard for use across several coding agents.

Project overview

SurfSense gives competitive-intelligence agents live connectors for social platforms, search, maps, and the open web through REST APIs or MCP. Scheduled and event-triggered agents can combine sources into cited briefs and alerts, then keep findings in a searchable knowledge base. The platform, including connectors, automations, and the MCP server, can be self-hosted with Docker, but the project states that it is still under active development and not yet production-ready.

Project overview

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.

Project overview

Narrator AI CLI Skill teaches compatible agents how to operate narrator-ai-cli for complete movie narration production. From a natural-language request, the workflow can search titles, choose templates, background music and voices, generate a script, compose the video, and return a download link. The skill is an instruction layer rather than a standalone tool: narrator-ai-cli, Python 3.10+, an API key, and the bundled references directory are required.