Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 282,343 indexed, measured the same four ways as everything else here.
Stackshift — Claude Code Optimizer. Periodic audit of a user's Claude Code setup. Confirms use case and tech level, inspects installed plugins/skills/MCP servers/marketplaces (flags broken ones), researches new tools from high-signal sources, checks overlap against native Claude Code features, and outputs a dated PDF…
Use x402-proxy CLI for consuming and debugging x402 and MPP paid APIs. Use this skill when testing x402/MPP endpoints, configuring MCP payment proxies for AI agents, managing wallets, or scripting paid HTTP requests. Triggers on x402-proxy, npx x402-proxy, x402 endpoint testing, MPP streaming payments, paid API…
Use when the user shares an image that Claude can't natively see, or when the user asks to analyze/describe/understand an image. Route every image through this skill — send the image path to eyes.py, which calls a vision model (default qwen3.7-plus) via 百炼 DashScope and returns a Chinese text description. Then answer…
A tool for creating same-length patches to Claude Code’s bundled or npm-installed JavaScript. It helps change how Claude Code behaves, including checks and limits.
Planificador de citas para parejas. Genera calendarios ficticios semanales para dos personas, encuentra huecos libres en común y sugiere planes de cita específicos por Telegram.
A guide for designing single-image covers for Xiaohongshu, a Chinese social media platform. It can analyse reference covers and turn content into visual layouts and image-generation prompts.
Especialista no MCP do Ekyte para gerenciar tarefas, projetos, usuarios, workspaces, fases e apontamentos de horas. Use quando o usuario quiser criar tarefa/projeto, atualizar fase, completar task, comentar tarefa, listar usuarios/workspaces/projetos ou registrar horas.
Adversarial verification agent that tests implementations by running builds, tests, and probing edge cases. Returns a structured VERDICT (PASS/FAIL/PARTIAL) with evidence.
Giúp đánh giá một ý tưởng có đáng thử hay không cho mục đích kinh doanh hoặc học tập, dựa trên bằng chứng, nguồn lực thực tế và một bước thử có giới hạn. Dùng khi cần xem nhanh, phân tích đầy đủ, so sánh ý tưởng hoặc xem lại báo cáo cũ.
Analyze, design, write, revise, translate, and review empirical or technical research papers through an evidence-bounded dialectical workflow. Use when Codex must develop a research question, integrate reference papers with a user's ideas, build phenomenon-mechanism-conditions reasoning, design methods or experiments…
A Chinese-language assistant for expanding an outline into doctoral engineering thesis paragraphs. It keeps the stated facts, methods, evidence, and limits of the outline.
A skill for collecting and analysing a Weibo blogger's posts, then generating text that imitates that blogger's writing style. Weibo is a Chinese social-media platform; the skill supports automated and agent-assisted workflows.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
MCP Server for Zotero SQLite Database - collection, tagging, PDF reading and more. Runs locally from the zotero-bridge npm package.
★not rated 10 6mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: