Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,768 indexed, measured the same four ways as everything else here.
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
Default path for any cloud training work in Dat. Use this skill whenever a task needs cloud training, GPU training, model fine-tuning, training evaluation, long-running training compute, or hosted training job orchestration. Also use it to submit prepared packages, handle approval/session handoff, track jobs, cancel…
Capture browser console logs and dev server output to files with agent-tail. Use when debugging runtime errors, checking console output, tailing or diagnosing logs, or setting up Vite/Next.js log capture.
Authors, reviews, and hardens Bash scripts for the stability and security properties a linter cannot verify on its own, including strict-mode semantics and the cases errexit ignores, cleanup and locking on every exit path, injection-safe handling of untrusted input and filenames, PATH and environment control…
★not rated 93 yesterdayA✓ AI review158 tokens
originalApache-2.0
A skill that turns a supplied photograph into a minimalist printed poster or zine-style artwork using hand-written HTML, CSS, and SVG, then exports a PNG. It does not use an image-generation model.
Use when recreating a reference website or brand hub in this Hydrogen plus Weaverse repo, especially when deciding whether to reuse sections, add global styles, update theme schema, or resolve conflicts between the live site and project brand guidelines.
Read a research paper end to end and produce a single Heilmeier-style analysis that doubles as both summary and critique. Use this skill whenever the user shares a research paper (PDF upload, arXiv link, arXiv ID, DOI, or pasted paper text) and asks anything that resembles "read this", "summarize this paper", "what…
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
Write rigorous, gap-free mathematical proofs for academic research. Use when asked to prove, derive, justify analytically, expand a proof sketch, check a theorem statement, or turn economic or game-theoretic reasoning into a complete proof with explicit algebra, signs, edge cases, and no hand-waving.
Automated optical design agent for Ansys Zemax OpticStudio 2024 R1 through ZOS-API. Use when Codex should automatically turn optical requirements or an existing .zmx/.zos/.zar file into an executable Zemax design loop: parse requirements, create or load a lens model, run baseline analyses, choose variables and…
An on-chain trading-research guide for examining token activity across Binance Alpha and several Ethereum-compatible blockchain networks. It covers trader or insider distribution, confirmed selling, wallet categories, unusual activity waves, and monitoring exports.
The governed client for Proxmox (PVE, PBS, PMG, PDM): plans, keeps the receipts, puts things back. Runs locally from the proximo-proxmox Python package.
★not rated 93▲
+29 2d agoA
tokens not measured
originalAGPL-3.0
Jarvis MCP – Browser-based voice input/output for AI Assistant conversations via MCP (Model Context Protocol). Runs locally from the @shantur/jarvis-mcp npm package.
Use when three or more AI agents are available and a task needs coordinated execution, or when work must be handed to another agent, session or tool. It ships the coordination rules as ENFORCED invariants rather than advice: one writer per resource (a conflicting claim is refused and names the holder), a verifier that…
Connect warehouses, BI tools (Tableau, Looker, Power BI) and custom connectors to Monte Carlo with API v2 tools: show what exists, reference credentials, create, validate and fix connections. Use to onboard platforms or generate Terraform or scripts.
Walk a contributor through shipping a new feature or fix in catalyst-core — tracking issue, branch, design proposal, implementation, docs, PR. Use when a contributor says a feature/fix is ready to start or is asking "what do I do next" for new work.
Reverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or…
Analyze whether TikTok or Instagram search traffic is a viable growth channel for your business. Uses ScaleBrick's framework to evaluate demand, competition, content fit, and intent categories. Ends with a go/no-go recommendation.
★not rated 92▲
+3 6mo agoA45 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: