All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 434,147 of them, each with its token cost per session, a security scan with the line that triggered it, and whether it is the original or one of the copies.
Skill Codex
Maintain and use a cross-channel collaboration map of rooms, people, agents, agent owners, relationships, expertise, ownership, roster, priority/VIP handling, and recent context. Trigger when a task or message carries room/channel/sender/member metadata; the user asks who is in a room, what it is for, who owns or…
Agent Claude CodeOpenCode
Senior code reviewer — reads diffs and surfaces bugs, security issues, and maintainability problems without modifying files.
Cursor rule Cursor
When executing shell commands in this codebase, use agentsh to run commands within a sandboxed session.
Skill Claude CodeCodex
Connect to 100+ APIs (Google Workspace, Microsoft 365, Notion, Slack, Airtable, HubSpot, etc.) with managed OAuth. Use this skill when users want to interact with external services. Security: The MATONAPIKEY authenticates with Maton.ai but grants NO access to third-party services by itself. Each service requires…
Agent Claude Code needs its repo
Generates printable exam papers with answer keys in PDF format. Searches for real exam examples online. Triggered by "/generate-exam" command.
Skill Claude Code
New screens, landing pages and redesigns that look generic or AI-made: visual direction, layout, type, color and a rendered build loop. Use for a new screen or page, a substantial restyle, typography or layout work, or UI that feels templated, and to write the design brief; small fixes keep the existing design without…
Skill Claude CodeCodex
Design, run, and analyze AI test suites on Rhesis — explore endpoints, build test foundations from a spec, create requirements and metrics, execute tests, and analyze results. Use when testing an AI endpoint, pasting a Product Requirements Document (PRD) or product spec, or working with Rhesis via MCP.
GongLingRui/screen-creative-skills
Skill Claude Code
A writing guide for creating and revising vertical short-drama scripts, where episodes are designed for phone screens and usually last one or two minutes.
Skill Claude Code
Analyze PMCC (Poor Man's Covered Call / diagonal spread) positions from IB portfolio. For each diagonal spread, reports short leg risk (delta, IV, assignment probability), daily P&L projections, top-3 roll candidates, and a side-by-side comparison table. Requires TWS or IB Gateway running locally.
AlpacaLabsLLC/skills-for-architects
Plugin Claude Code
Bundles 61 skills, 8 agents, 2 hooks · 2,908 tokens together
Arch Studio — governed AEC skills and portable studio workflows for Codex and Claude Code: initialize a studio workspace, create registered projects, maintain linked project records, or route work across NYC due diligence, site planning, zoning, programming, specifications, sustainability, FF&E, materials research…
yizhiyanhua-ai/media-downloader
Skill Claude CodeCodex
A media downloader that searches for and downloads images or video clips from a description, with support for automatically trimming videos. It can be triggered with media-download requests or the /media command.
Skill Claude Code
Use after the napkinmath pipeline has produced parameters/bounds/scenarios/montecarlo JSON to generate a plan assessment (assessment.md) — a thin interpretation layer over the intermediary artifacts. Emits a JSON manifest, a provenance map, gate verdicts (Critical / Fragile / Marginal / Robust), failure drivers…
zhongweili/nanobanana-mcp-server
MCP server Claude CodeCodexCursor +2
A production-ready MCP server for AI-powered image generation using Gemini 3.1 Flash Image (Nano Banana 2, default), Gemini 3 Pro Image, and Gemini 2.5 Flash Image with intelligent model selection. Runs locally from the nanobanana-mcp-server Python package. Needs 2 environment variables to run.
Skill Claude CodeCodex
AI-powered E2E testing for any app — Flutter, React Native, iOS, Android, Electron, Tauri, KMP, .NET MAUI. Connects via MCP to running apps so the agent can take screenshots, tap elements, enter text, scroll, inspect UI trees, and verify state with natural language. Use when the user wants to test an app's UI…
Skill Codex
Find, evaluate, and download low-level common standard CAD parts from step.parts, such as screws, bolts, nuts, washers, bearings, standoffs, electronics parts, motors, connectors, and other off-the-shelf components. Use when Codex needs to search the hosted step.parts catalog, resolve fuzzy part names, standards…
Plugin Cursor
Skills and MCP connection for Bagel: query rosbags, MCAP, CAN, MDF4, PX4/ArduPilot/Betaflight logs and live robot data in plain language; author event-windowed data-reduction pipelines; export to Rerun, Lichtblick, PlotJuggler, and LeRobot. Requires the Bagel server running locally (uvx bagel-mcp, or Docker for live.
Skill Claude CodeCodex
You are an AI agent working with the Windscribe Android app codebase. This skill defines HOW to perform common development, debugging, and maintenance tasks.
Skill Claude CodeCodex
Run an enterprise pre submission compliance audit on a mobile app project before uploading to the Apple App Store or Google Play. Use when the user is about to submit, ship, or release an iOS or Android app, when an app was rejected and needs a fix plan, when reviewing App Store Review Guidelines or Google Play policy…
Skill Claude CodeCodex
Explore and query Microsoft SQL Server, Azure SQL Database, or LocalDB through the microsoftsqlservermcp MCP server. Use when the user asks about data, tables, or schema in a SQL Server / Azure SQL / LocalDB database, wants to run T-SQL, or needs to set up or troubleshoot that MCP server.
Skill Codex
Adversarially pressure-test a draft or pending U.S. utility patent against technically credible, commercially plausible design-arounds that preserve its value proposition while avoiding the current proposed claims. Use fresh competitor subagents, then have the outer agent decide whether each workaround remains inside…
Plugin Claude Code
Bundles 1 skill, 12 hooks, 1 MCP server · 26 tokens together
memX: local-first semantic memory for coding agents. Native Claude Code lifecycle hooks.
Plugin Claude Code
Bundles 3 skills · 565 tokens together
Agent Skills for MARS-Curiosity, the Delphi REST library: scaffold new MARS server projects (also from OpenAPI documents, with MARSgen), develop REST APIs with resources and, as an addition, routes, attributes, JWT authentication, FireDAC and Devart UniDAC/MyDAC/IBDAC datasets, server-sent events, WebStencils, client…
Plugin Claude Code
Bundles 6 skills, 18 commands · 492 tokens together
LLM-powered knowledge base from Claude Code and Codex CLI sessions. Follows Karpathy's LLM Wiki pattern.
Plugin Claude Code
Bundles 2 skills, 5 commands, 1 agent, 3 hooks · 97 tokens together
A Claude Code plugin that's alive. Observes everything, learns instincts, evolves capabilities. Bound to one maker.
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: