Portfolio analysis & market intelligence for Claude Code & OpenClaw. Deterministic Python math + Claude/OpenClaw synthesis. Educational guardrails, no invest…
Healthiest
// sorted by health — what's thriving right now
// observatory (5535)
Assistant vocal français pour Windows : la Galaxie (ton cerveau en étoiles), Jarvis OS, cerveau local, mémoire, second cerveau (Claude Code), Gmail. Édition…
Web console and diagnostic workbench for AI coding agents — omp by default, with Claude Code, Codex, OpenCode and any ACP agent beside it. Elysia + Preact on…
🏭 Dead simple, lightweight engine for 24/7 background AI agents. Works with your Claude, Codex or any other subscription. Comes with remote control, UI and…
Claude (or any LLM) acts as the whole app instead of writing it: try an idea by hand in minutes, then turn it into a spec and a build plan.
The MacBook notch, finally behaving like the Dynamic Island: a liquid island for music, AirPods, Claude Code and more.
One window for all your Claude Code and Codex sessions, with Git Changes, diffs and worktrees for each, sessions on your own servers, and agents that can mes…
iOS Simulator on Linux: a full macOS VM in Docker with GPU acceleration (Metal via Reims vGPU), Xcode and a pool of iOS Simulators for AI coding agents (Clau…
Meridian — the open-source Arc browser alternative for macOS, Windows and Linux, built for AI agents (MCP server, Claude, coding-agent workbench)
NFS-e pelo Emissor Nacional (nfse.gov.br) para agentes de IA: skill, CLI e biblioteca Python para consultar, emitir e cancelar notas fiscais de serviço. Inst…
A living desktop notch: music with synced lyrics, tasks, reminders, calendar, AI agents (Hermes, Claude Code, Codex, OMP), a built-in MCP server, AI router a…
Copy the last shell command and its output to the clipboard as a paste-ready block, or let Claude Code read it
The Dynamic Island for your AI agents. Claude Code, Codex and more in your Mac's notch, plus a full menu bar toolkit.
Your team votes on how its AI coding agents behave. Correct Claude Code once, and PeerHarness turns it into a one-sentence rule (an Agent Skill) that a major…
An interactive desktop pet with exaggerated cartoon physics & real-time AI coding agent integration (Claude Code, Codex, DeepSeek, Antigravity).
필요할 때만 켜는 Claude Code 입력 개인정보 가림 모드 (schift-ko-pii-v5, 로컬 검사)
+62 Mode & Anti-Yapping Layer for Coding Agents. Langsung to-the-point ke baris bug, zero basa-basi korporat, dan anti-reasoning dump. (Claude Code, Antigrav…
Claude Code plugin that turns the podcasts you listen to on Spotify into a cited LLM wiki: one page per topic, every claim linked to its episode.
Claude Code you talk to. Hold ⌃⌥ and it sees your Mac screen, answers out loud, sketches explanations, and runs Claude Code agents for you.
Claude Code skill: make Claude the Head of a multi-AI team (DeepSeek, Nemotron, Qwen, any OpenAI-compatible API) with maker/reviewer flow, safety boundary an…
A Claude Code skill that turns a product's repo and running app into a 2-5 minute explainer video: the real app recorded, what happens behind each screen, El…
Prompt-rewriting skill with model and effort recommendations, for Claude and ChatGPT/Codex
A Claude Code mod that draws the spinner line in colour styles switched with /spinner
Claude Code skill: reverse engineer how a company, agency or creator does its marketing, from public evidence or an ads account you can read.
Free Claude skill for viral Roblox story shorts ("In this town, ..."): the foundation, measured rules, a style menu and ~75 solved pitfalls.
Running coach for Claude: season plans, HRV check-ins, session analysis and research-backed load rules, from TrainingPeaks, Strava or a conversation.
Local search over your code and documents for AI agents. One binary that indexes your repositories, PDFs and Office files and serves them over MCP.
Free Claude Code / OpenCode skill that fixes AI-slop SEO: one command, one commit per change
50 free SEO, AEO, LLM SEO, GEO and parasite SEO skills for Claude Code, Codex and AI agents. MIT.
Cut Claude Code token usage and cost with a one-line output style. Shorter replies than Concise on every Claude model: 29% fewer output tokens and 23% lower…