Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 280,912 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex
Write type-safe @axiosleo/koapp code in TypeScript - typed contexts (KoaContext, ContextFromSpec, RequiredContext, SocketContext, WebSocketContext), Router generics, ContextHandler middlewares, module augmentation, typed file uploads with @koa/multer, response helper generics, and typed application configs. Use when a…
Skill Claude CodeCodex ✓ vendor
SAP Fiori for iOS Design Skill — Converts Figma designs from the Fiori iOS UI Kit into SwiftUI prototypes with animations and interactions. Use this skill when a designer provides a Figma node ID or component name and wants working SwiftUI code, when asking which Fiori iOS component to use, when mapping Figma variants…
MCP server Claude CodeCodexCursor +2
A job search and crawling tool built with Model Context Protocol. Runs locally from the mcp-jobs npm package.
Skill Claude CodeCodex
Run and benchmark BPU/NPU inference on an RDK board (X5/S100) over SSH — load a .bin model, verify it loads, measure latency and FPS with hrtmodelexec.
DottedSign-Official/dottedsign-mcp
MCP server Claude CodeCodexCursor +2
Automate eSignature workflows and signing tasks via natural language commands. Remote server at mcp.dottedsign.com.
Skill Claude CodeCodex
Helps users discover agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. Always ask the user for permission before installing any skill, and flag security risks.
microsoft/vscode-chat-customizations-evaluation
Skill Claude CodeCodex ✓ vendor
Fixes diagnostics reported by the Chat Customizations Evaluations extension on the active prompt file. Reads the current diagnostics from the editor and applies suggested improvements.
alima-max/prototype-to-figma-skill
Skill Claude CodeCodex
Converts a working Claude Code prototype into a structured Figma design file — exploding each interaction flow into separate frames, using the target file's design system components, and annotating interaction details natively in Figma. Use this skill whenever the user asks to turn a prototype into Figma frames…
Skill Claude CodeCodex needs its repo
Use when the user asks to batch-download academic PDFs with ref-downloader — either ALL references of one paper (Mode A: DOI or PDF input), OR a custom batch of papers (Mode B: DOI/title/arXiv-PMID list, or abstract query like "Author X's recent papers"). Not for one-off PDFs, paper search, or Zotero import.
Skill Claude CodeCodex
A scheduled review process that studies past coding-agent sessions and proposes improvements to project instructions and memory.
Skill Claude CodeCodex
A guided advisory discussion in which several chosen business perspectives ask questions and give feedback on a major decision, using current information from Baidu Search and Baidu Baike.
TanShilongMario/PromptSkill4image
Skill Claude CodeCodex
Advanced image prompt engineering assistant for Chinese-first users. Turns any input into high-quality image-generation prompts: reverse-engineers prompts from images, expands rough prompts into structured prompts, translates/transwrites prompts, extracts reusable variables, suggests phrase banks, supports minimal…
Skill Claude CodeCodex
Applies the frameworks of Aristotle (ancient Greek philosopher, logic, ethics, metaphysics, 384-322 BCE) to decision-making, ethics, and analysis. Use this skill whenever the user is grappling with moral dilemmas, character development, habit formation, finding balance (the Golden Mean), persuasive communication…
wpgaurav/generateblocks-skills
Skill Claude CodeCodex
Convert Elementor layouts to clean GenerateBlocks V2 format, eliminating DIVception.
markfulton/claude-antigravity-agents
Skill Claude CodeCodex
Delegate coding, code review, analysis, and research jobs to Google Antigravity CLI (agy) sub-agents that run alongside your own work. Use this whenever the user asks to spin off, offload, or delegate a task to Antigravity, agy, Gemini, or an "external agent"; wants a second opinion or independent review from a…
Skill Codex
A runbook for replaying past data through Dagster pipelines, which are scheduled workflows for processing data. It describes how to use the project’s `dg launch` commands and shared backfill jobs.
Skill Claude CodeCodex
Manage octo's agent profiles through conversation — create, modify, delete, list, and bind agents to IM chats by calling REST APIs. This skill is exclusive to the Default Agent (full-access). Use when the user wants to manage agents conversationally, e.g. "create a code review agent", "list all agents", "bind agent X…
Skill Codex
End-to-end, Chinese-first academic research and publication workflow for reading papers, literature reviews, research framing, manuscript planning and writing, the eight-step paper-system workflow, Chinese-English translation, LaTeX, figures, citation verification, reporting-guideline checks, journal selection, peer…
Skill Codex
A workflow for creating a personalized fitness plan from a person’s current condition, goals, available equipment, safety information, and training history.
Skill Claude CodeCodex
Use whenever an agent needs structured human input. Public HITL contract is question-only: ask questions, inspect pending questions, submit partial answers, and wait on caller-scope progress.
Skill Claude CodeCodex
Greet the user warmly and demonstrate the minimal shape of a valid Agent Skill.
Skill Claude CodeCodex
Drive a macOS app through the computer tool — read its accessibility tree, act on elements, and use real input only when the tree cannot reach the target.
Skill Codex
Work with OpenKakao CLI (openkakao-cli 1.18.0+) for KakaoTalk on macOS: send text, photos and files, reply to, edit or delete a message, read a chat, open a chat window, sign a logged-out KakaoTalk back in (ax-login), set the tool up (init, doctor), detect incoming messages (notif-watch), list friends' birthdays…
Skill Codex
Analyze, benchmark, diagnose, and optimize large-model inference deployments from hardware inventory, model details, workload traces, and latency or throughput SLOs. Use when Codex needs to tune SGLang launch parameters, run bounded single-host GPU experiments, plan deployment topology, inspect GPU or CPU profiles…
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: