Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 269,837 indexed, measured the same four ways as everything else here.
Specialist skill for mobile E2E testing with Appium 2.x + Python (pytest) for Android and iOS. Use this skill whenever the user asks about: setting up Appium with Python, writing mobile test cases, configuring Android/iOS drivers (UIAutomator2, XCUITest), implementing Page Object Model for mobile, running tests with…
Use when the user asks to research a problem, find solutions, compare approaches, or investigate a technical topic by searching the internet and organizing findings into structured directories.
Audits React and Next.js code for high-leverage runtime and rendering pitfalls, then routes to deep-dive references on useEffect anti-patterns, re-render causes, rendering model selection, React 19 APIs, and waterfall chains. Use when a .tsx or .jsx file is opened or reviewed, the user asks "is my React code good"…
Manage virtual Visa cards for AI agents with AgentCard. Fund a wallet with Apple Pay or Google Pay, create single-use or multi-use cards, check balances, view credentials, pay for things, shop and check out at merchants like DoorDash, close cards, manage plans, and get support. Use when the user wants to create or…
Turn technical evidence into clear, natural, audience-appropriate user-facing explanations without changing meaning, certainty, obligations, operational state, or exact technical tokens. Use for change summaries, status and error reports, walkthroughs, handoffs, release notes, how or why explanations, and requests to…
OSINT investigation toolkit. Use when the user wants to investigate or gather open-source intelligence on an indicator — a person's name, email, username, domain, IP address, phone number, company, coordinates, IBAN, or crypto address — and needs the right set of curated OSINT search links, or wants to validate an…
Retrieve and curate durable, project-aware knowledge through the Global Agent Memory MCP server. Use before substantial planning, implementation, refactoring, debugging, handoff preparation, or investigation when prior decisions, exact identifiers, recurring errors, verified solutions, preferences, or conventions may…
Enforce minimal, scoped, evidence-based work for software delivery and adjacent product, QA, security, analysis, database, architecture, content, statistics, and MCP tasks. Use for every non-trivial developer workflow, including work that produces no code.
Use when building a frontend and the user wants a distinctive / animated / "wow" UI element in React + Tailwind - e.g. a laptop-opening-on-scroll, 3D tilt card, spotlight hero, animated beams/background, marquee, bento grid, interactive globe, meteor/particle background, shimmer button, or scroll/reveal motion.…
A development guide for industrial software that uses open-source tools for computer-aided design, simulation, visualisation, electronics design, and related engineering work.
Run or resume the Sprint Loops Book v2 workflow when the user explicitly invokes $sprint-loops or directly asks to start, continue, resume, or run a sprint loop. Do not use it for ordinary documentation work or merely because a docs directory exists.
Test Minecraft mod changes in the running game - rebuild the mod, deploy the jar, restart the client via DebugBridge, and rejoin a server. Use when asked to "test this in game", restart Minecraft after a build, or run the build-deploy-relaunch-rejoin loop. Requires the mcdev-mcp MCP server and the DebugBridge mod with…
MCP server "sap-rfc-mcp-server" as configured in thupalo/sap-rfc-mcp-server. Runs locally from the sap-rfc-mcp-server Python package.
★not rated 14▲
+1 1y 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: