Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,858 indexed, measured the same four ways as everything else here.
Générer un plan de lancement complet, semaine par semaine, pour tout lancement de produit, service ou fonctionnalité. Ce skill produit un plan tactique avec des modèles, checklists, séquences d'emails, publications sociales et suivi des métriques — tout le nécessaire pour exécuter un lancement réussi.
End-to-end statistical writing assistant for LaTeX - draft title/abstract/keywords, expand outlines into sections, audit manuscripts, write reviewer reports and response letters, and scaffold book manuscripts.
Comprehensive guidance for building and deploying static websites with the Astro framework. This skill should be used when asked to "create astro site", "deploy astro to firebase", "set up content collections", "add mermaid diagrams to astro", "configure astro i18n", "build static blog", or "astro markdown setup".…
Update project memory after completing a task, making a key decision, discovering a gotcha, or changing active goals. Use this skill at the end of any meaningful unit of work to write structured entries into .claude/memory/MEMORY.md following the project schema. Also use when the user asks to save memory, update…
Multi-agent iterative research pipeline using Eric Jang methodology. 10-18 specialized agents across 3 cycles produce consensus references, interaction maps, personalized syntheses, and action plans with domain-specific stress-testing, iterative deepening, and anti-pattern guards.
Reviews Magento 2 code for quality, security, performance, and compliance with PSR-12 and Magento coding standards. Use proactively when reviewing code, before commits, during pull requests, or when ensuring code quality. Enforces strict type declarations, proper dependency injection, security best practices, and…
Redis backends for Google's Agent Development Kit (ADK). Use this skill when the user wants to back an ADK agent with Redis: persistent sessions and long-term memory via Redis Agent Memory Server, RAG search tools over a RedisVL index (vector / hybrid / range / text / SQL), MCP toolsets for RedisVL or Agent Memory…
Model Context Protocol (MCP) server for SendGrid API v3 - manage email marketing, automations, templates, and analytics. Runs locally from the sendgrid-mcp npm package.
MCP server exposing JetBrains TeamCity CI/CD workflows to AI coding assistants. Runs locally from the @daghis/teamcity-mcp npm package. Needs 3 environment variables to run.
★not rated 32▲
+1 6d agoA
tokens not measured
originalMIT
A tool for reading web pages, videos, podcasts, links, and local audio recordings, then producing structured Chinese explanations and answering questions about the source material.
Creates a polished interactive web prototype previewer for new or existing products. Use when the user asks for an HTML prototype, a clickable multi-screen flow preview, a reviewable app mock, a screen-by-screen web prototype, or a Figma-ready capture page. Produces a three-panel reviewer with flow navigation, a…
Use when managing Google Play Developer Console metadata, graphics, tracks, app bundles, reviews, subscriptions, or in-app products with the local play CLI. Trigger this for Moshi Android Play Store work, especially when editing /Users/jyo/projects/ai/moshi/marketing/play assets or debugging…
An MCP server implementation for Kalshi prediction market endpoints. Runs locally from the mcp-server-kalshi Python package. Needs 4 environment variables to run.
★not rated 32 1mo agoA
tokens not measured
originalMIT
Use when the user asks to count, audit, compare, or report local Codex Desktop or CLI token usage, including daily token counts, total or net usage, cache hit rate, peak periods, or an offline HTML usage dashboard.
MCP server "lightcms" as configured in jonradoff/lightcms. Launched with https://github.com/jonradoff/lightcms/releases/download/v1.1.0/lightcms-darwin-a. Needs 2 environment variables to run.
★not rated 32 1mo agoA
tokens not measured
originalMIT
Cross-platform skill for Codex, Claude Code, and DeepSeek Harness (DSH) that creates, updates, compacts, rotates, repairs, and reviews durable repository handoffs. Use when bootstrapping cross-session memory; creating or maintaining AGENTHANDOFF.md and .agent-handoff files; adding AGENTS.md or .claude/CLAUDE.md rules…
A skill for creating academic presentations in Marp, a tool that turns Markdown text into slides, using a theme made for HFUT defenses, course reports, and thesis presentations.
★not rated 32 9mo agoA82 tokens
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: