Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 282,341 indexed, measured the same four ways as everything else here.
Build agents that generate rich, interactive UIs using Google's A2UI (Agent-to-User Interface) format with Google ADK (Agent Development Kit). Use when building ADK agents that need to render dynamic UI components, forms, cards, lists, or interactive elements via the A2UI declarative JSON format. Includes a Tailwind…
Interactively create a new Grok skill (SKILL.md + optional scripts/references). Use when the user wants to create a skill, scaffold a skill, or runs /create-skill.
Default Runpod workflow for user-managed Pods. Ask the human to create a Pod with the desired GPU, get the podid and SSH access details, save a manual Pod profile, and use opencolab gpu ssh sessions as the default control path. Use OpenColab gpu server and gpu job only when the user explicitly wants managed…
GitHub Actions best practices — current action versions, caching, security, and common patterns. Activate when writing or modifying GitHub Actions workflows.
Comprehensive SaaS security skill covering code auditing, checklist generation, and vulnerability reporting. TRIGGER this skill whenever the user asks to: audit code for security issues, review a codebase for vulnerabilities, generate a security checklist, check for OWASP compliance, review authentication or…
Query GMX GM pools and GLV vaults with GmxApiSdk, and provide or withdraw liquidity through current contracts. Use for pool discovery, APY and earnings, GM/GLV deposits and withdrawals, and GM pool shifts on Arbitrum, Avalanche, and MegaETH.
Guide a user through a choice-first video production workflow, convert the answers into a structured director plan, generate clips with the Seedance API, run technical and semantic audits, and assemble deliverables. Use when the user invokes $seedance-video-workflow or asks for a guided Seedance video workflow…
Codex-only skill administration for auditing, enabling, disabling, restoring, and verifying local Codex skills. Use when the user asks to manage Codex skills, reduce skill token load, close unused skills without uninstalling them, restore disabled skills, inspect current skill visibility, or automate skill enablement…
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Discover Outcomes and their disclosed recipes, then prepare a complete starting brief for a fresh agent. Also author and validate source-owned Outcomes for Possible.
A toolkit for AI-assisted user-research phone calls, covering interview preparation, prompt creation, and call review. It guides researchers in Chinese or English and supports methods such as Laddering, SCQA, Five Whys, and Jobs to Be Done.
Coordinate durable or cross-process work with local JSON mailboxes and vc teams commands. Use when messages must persist beyond one Codex session; prefer built-in Codex subagents for normal in-session delegation.
MCP server "financial-analyst" as configured in mahak867/ai-projects-hub. Runs /FULL/PATH/TO/server.py with python. Needs 1 environment variable to run.
★not rated 11 7mo agoA
tokens not measured
originalMIT
A writing aid for creating Xiaohongshu, also called RedBook, posts from images, videos, or text. Xiaohongshu is a Chinese social platform where people publish short lifestyle and product posts.
Build reusable agent-readable frameworks from any domain expertise. Use when someone says "systematize this," "turn this into a repeatable process," "build a framework for," "create a skill for," "I keep doing the same thing," or "make this predictable." Produces a complete five-layer framework in markdown that agents…
A rule set for turning book content into interactive HTML reading pages, topic pages, comparison pages, or a book hub. It applies only when someone explicitly asks for a page to be created or updated.
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: