Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 274,392 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex
Search the web using DuckDuckGo via the ddgr CLI tool. Use when the user asks to search the web, look something up online, find information on the internet, get instant answers, or needs current/real-time data. Also use for DuckDuckGo Bang searches (e.g., "!w" for Wikipedia, "!so" for StackOverflow).
Skill Codex
Marketing execution: campaign orchestration, copywriting, CRO, analytics, paid ads, email, and social content. Use to ship campaigns and improve conversions.
Skill Codex
Evaluate whether an existing project, service, subsystem, or migration RFC should adopt Rust. Compare staying, adopting an existing native tool, extracting a Rust kernel, replacing one component, and full migration through evidence-gated performance, safety, cost, compatibility, and delivery analysis. Produce a clear…
harshitsinghbhandari/domain-expansion
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Skill Claude CodeCodex
A note-making tool for turning YouTube videos, local media, or saved transcripts into detailed study notes. It is intended for requests that explicitly ask for notes or a study outline.
Skill Claude CodeCodex
Use when auditing whether a skill decomposition is evidence-grounded, over-inference-safe, and publishable.
Skill Claude CodeCodex
Use for AI-assisted code changes that must keep project living docs in sync. Triggers on feature work, bug fixes, refactors, API/schema/security/deployment changes, requirement updates, tests, guardrails, and change records. Do not use for general Q&A or non-project snippets.
Skill Codex
Use when a user wants a rough product, assistant, agent, chatbot, workflow, or business requirement converted into a visible expert-grade XML system prompt and immediately executed without waiting for approval.
MCP server Claude CodeCodexCursor +2
MCP server for the FRED (Federal Reserve Economic Data) API. Runs locally from the fred-mcp-server Python package.
MCP server Claude CodeCodexCursor +2
MCP server for daisyUI React components — search docs, props, and code examples from any AI coding assistant 🌼. Runs locally from the daisyui-mcp-server npm package.
MCP server Claude CodeCodexCursor +2
Flash Cast MCP Server - AI video production via Model Context Protocol. Runs locally from the flash-cast-mcp npm package.
Skill Claude CodeCodex
Android device control via raw ADB commands. Use for device/emulator discovery, USB or Wi-Fi connection, app launch/force-stop, tap/swipe/keyevent/text input, screenshots, UI hierarchy dump, and ADB troubleshooting.
Skill Codex
Create slides with the Prompt-as-Slide (PasS) protocol by defining each slide as one authoritative, self-contained Markdown prompt, generating one aligned slide image per prompt with an available image-generation capability, deriving synchronized speaker notes with target durations and bold visual anchors, and…
Skill Claude CodeCodex
CLI for bootstrapping and managing wordspace projects.
Skill Codex
Apply Feature-Sliced Design (FSD) v2.1 architectural methodology to frontend projects. Use when organizing code structure, decomposing features, creating new components or features, refactoring existing codebases, or when users mention "FSD", "Feature-Sliced", layers, slices, or frontend architecture patterns.
Jared13PG/ai-engineering-workflow
Skill Claude CodeCodex
Use this skill for complex coding, coursework, data analysis, notebook, research, or multi-file projects that need structured issue creation, context analysis, task breakdown, atomic execution, verification, status tracking, and final closure.
Skill Codex
Use when a natural-language task must be converted into a role-neutral, statically validated one-shot plan, workflow, or agent-loop specification before any user-task execution begins.
liu-wei-ai/douyin-video-summary
Skill Claude CodeCodex
Summarize Douyin (TikTok China) videos by extracting audio, transcribing with whisper.cpp, and generating structured summaries. Use when a user shares a Douyin link and wants a text summary of the video content. Supports optional sync to Feishu (Lark) docs. Triggers on Douyin URLs (v.douyin.com, douyin.com/video/).
Skill Claude CodeCodex
Saleor storefront data + UX playbook. Covers GraphQL query design, channel handling, data contracts per surface (PLP/PDP/nav/pricing/availability/media), variant-selection UX, and Saleor-specific correctness rules. Framework-agnostic — agent inspects repo and applies conventions locally.
soderlind/wordpress-agent-plugin
Skill Claude CodeCodex
Run mutation testing on WordPress plugins and themes to find weak tests — Pest --mutate or Infection for PHP, StrykerJS for JavaScript — then triage surviving mutants into concrete test improvements.
antonioc-cl/creative-ideas-council
Skill Claude CodeCodex
Expert experiences council with 6 advisors (Pine, Parker, Meyer, Sutherland, Godin, Gray) for events, experiences, space activation, and idea generation.
Skill Claude CodeCodex
Use Ghostpatch as an agent-native open-source contribution plugin for Codex, Claude Code, and other coding agents. Trigger when a user wants the agent to find repositories, discover GitHub issues, qualify candidates, solve issues locally, review diffs/tests, and raise approval-gated pull requests using the Ghostpatch…
yinguangyao/evidence-first-skill
Skill Claude CodeCodex
A work method for non-trivial tasks that produce conclusions or deliverables, such as research, analysis, troubleshooting, plans, documents, or code. It emphasizes checking evidence, especially when sources conflict or facts and numbers matter.
yihui-dev/linggan-talking-cards
Skill Codex
A tool for turning Chinese or English spoken scripts, with optional screenshots, into three to ten presentation-style PNG cards and an HTML preview page. It also produces a structured manifest and speaker notes for each card.
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: