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.
Aesthetic-direction design skill: reads a brief, infers the right visual style and direction, and ships interfaces that do not look templated. Umbrella for concrete style variants — minimalist, brutalist, soft/premium-agency. Use when the user wants a particular vibe or aesthetic, or wants a landing page or portfolio…
Triages and prioritizes security vulnerabilities (CVEs) by combining CVSS base/temporal scores, real-world exploitability (EPSS, KEV, public PoCs), environmental exposure (internet-facing, network reachability, authentication), and business impact (data sensitivity, asset criticality) into a defensible, ranked…
Report on new stars, forks, and releases for watched repos — with profile enrichment (name, location, company, bio, follower count) for every new stargazer and forker, plus a one-line growth verdict.
VORTEX-OS is a Hierarchical Autonomous Orchestration Engine designed to treat AI agency as a high-stakes, closed-loop corporate operation. Built exclusively to maximize the native capabilities of the MiniMax ecosystem, VORTEX-OS decouples strategic planning from operational labor. It enables you to ship complex…
Judge performance or resource claims on real hardware, and design the test, replay, evaluation, benchmark, soak or watch before it runs: latency, throughput, memory or headroom numbers, and accept-or-reject decisions on optimizations. Not for refactors with no resource claim.
Run an agentic commerce chain under a signed Work Mandate, trip the escalation gate on purpose, and replay the gates on the ledger. Use when you want one run that shows the same tool returning the same answer through every AINumbers doorway. Written for the agentic commerce audience.
★not rated 12
changed 3d agoA64 tokens
originalMIT
Persistent, structured project memory for AI coding agents via the Knowit MCP server. Use before planning or editing code to load relevant rules, architecture, decisions, patterns, and conventions; use after finishing work to save durable learnings. Triggers on "remember this", "what are our conventions", "project…
Produce a publishable piano score and matching 1080p60 falling-notes video from a user-provided audio recording, including metadata research, cover art, PDF/MusicXML/MIDI exports, review-gated YouTube publication, and mymusic5 sheet-music listing. Use for piano transcription, sheet-music delivery, falling-notes video…
Create and edit a product, launch, demo, or social video from the current project with 21st video MCP tools. Open the editable project alongside the chat, apply small revision-aware edits, check rendered frames, offer visual variants, and export the result. Use when the user asks for a video, says "make a launch video…
An auditing and organizing skill for an AI project's instructions, rules, skills, and supporting context. It finds duplication, conflicts, outdated information, and prompt injection, then creates reviewable, reversible change proposals or applies approved changes.
Manage persistent wiki via the kb CLI or HTTP API. Use when storing, retrieving, updating, or searching knowledge that should persist across conversations. Triggers on remember, store, recall, look up, find in memory, organize knowledge.
Guide for creating content on ayokoding-web, a Next.js 16 fullstack content platform (ayokoding-web). Covers bilingual content strategy (default English), tRPC API, content workflow, and ayokoding-web specific patterns. Essential for content creation tasks on ayokoding-web.
Test mobile apps with MobiLoop MCP, collect device evidence, and fix and retest confirmed failures within the user's scope. Use for Flutter, React Native, Android, or iOS QA on an emulator, simulator, or device, including relevant mobile security checks.
Library of 670 proven prompt templates (1,007 originals, variants merged) for software work. Use whenever the user asks for "a prompt for X", wants a better prompt, or starts a coding, frontend, backend, full-stack, API, database, DevOps/CI/CD, cloud, AI/ML/LLM/RAG, debugging, code review, architecture/system design…
A command-line guide for managing MCP Apps in mcpcat. MCP Apps are hosted application resources that can include tools and other app content for connected AI systems.
Email infrastructure and authentication for developers: domains, inbox routes, auth apps, deploys. Runs locally from the @smbcloud/cli npm package. Needs 1 environment variable to run.
Use when reviewing an agent tool that reads or writes PostgreSQL, such as whether an agent could read another customer's rows, lose a user's requirements on a retry, or write the same business effect twice. Not for building a new agent.
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: