小白也能上手的 Claude Code / Codex 上游配置切换桌面应用 | A cross-platform, site-driven desktop app for switching Claude Code & Codex providers. Only official website: xiaoba…

Turn a YouTube video or a web article into didactic study notes, rendered as a self-contained HTML page. Agent skill for Claude Code, Codex, Cursor, OpenCode…

专门为本地模型玩家开发的code agent! 纯rust,极致简约的系统提示词 30tokens的速度也可以流畅使用。完美兼容claude skill。

Official MCP server for Consensus. Search 220M+ peer-reviewed research papers from Claude, ChatGPT, Cursor, and any MCP client.

Claude Code plugin that rewrites each assistant message into plain language on screen only. Local ollama by default; also codex CLI, Anthropic, or any OpenAI…

A Claude Code skill (/debuzz) that pipes Claude's answers through Gemini to remove the BuzzFeed voice

Watch a Claude Code session as a live flow graph, in your terminal or your browser.

YC (S26) | Open Computer History | Record your screen continuously locally and provide context to your agents (Claude, Codex, Openclaw, Hermes, Runner...)

A self-contained, reliability-first agent development flow — grill, spec, build under deterministic gates. Claude Code plugin.

A Stream Deck Neo cockpit for Claude Code and OpenAI Codex sessions.

Output style do Claude Code: 10 zasad ADHD-friendly (akcja najpierw, zero preambuł) - jako output style, który zostaje włączony między sesjami. Bazuje na ayg…

Design intelligence for websites local businesses pay for. A Claude Code plugin by AI Chris Lee.

Countbean plugin for Claude Code — hosted plain-text (Beancount) accounting. Published from the countbean monorepo; do not edit here.

A Claude Code starter for one design pattern: your own code runs on every prompt, before the model reads it, and tells the model how to answer.

A reference software factory for Claude Code and Codex

An agent skill that plays ARC-AGI-3. One rule: say what an action will do before you spend it. Claude Code on Opus 5 finished all 25 public games at 100.00 R…

Keep ai from adding unneeded modules, subagents, dependencies, and hashes to small tasks. 别再造史了，用于阻止ai过度工程，如在不必要的时候过度哈希，增加不要的全量测试等，基于hook和skill给ai划定边界 -for c…

Skill não oficial da API Banco Inter para ChatGPT, Codex e Claude Code — Pix, boleto, Banking, webhooks, OAuth 2.0 + mTLS.

Scheduled, unattended Claude Code CLI jobs — runs on your Claude subscription via the local CLI, no ANTHROPIC_API_KEY.

Steers Cursor and Claude Code agents with gates → follow-up → handoff → policy.

The Open Analytics design language as an agent skill: component recipes with type-checked source, token CSS, and a CLI. Works with Claude Code, Cursor, or an…

Find the conversation you forgot you started — a self-hosted dashboard that groups your Claude Code sessions by topic.

Ask your agent what happened in a run — it answers in your terminal and lights up the exact nodes on an open graph. Claude Code, Codex, Hermes.

Local audio transcription for Claude Code and any agent — batch, fully offline, no API key

An eraser against LLM-induced code & document entropy — clone/duplication/deadcode/structure judgment (Haskell core, Rust frontend) with Claude Code guard ho…

Use your Neovim like using Cursor AI IDE!

A minimal, evidence-gated harness for Codex and Claude Code: reuse what works, add only what is missing, verify before evolving.

AI-native HL7 v2 toolkit with generation, validation, HL7→FHIR conversion, MCP & Claude Code integration. Bringing healthcare interoperability into the AI-n…

Open-source adversarial verification Agent Skill for Claude Code, OpenAI Codex, and Cursor. Make AI coding agents prove bug fixes, CI, logs, and deployments.

Local video analyzer skill for Claude Code: yt-dlp + ffmpeg + Whisper + vision. Transcript, hook breakdown, and topic research in a dated folder. No API key.