Everything for Codex

Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 269,407 indexed, measured the same four ways as everything else here.

lsp-mcp-server

9961

ProfessioneIT/lsp-mcp-server

Skill Claude CodeCodex

Use whenever code navigation, analysis, refactoring, or diagnostics are needed on a project that has a Language Server Protocol implementation. Covers all 29 lsp MCP tools exposed by lsp-mcp-server (TypeScript, Python, Rust, Go, C/C++, Ruby, PHP, Elixir, Kotlin, Java, and any user-configured language). Use it instead…

not rated 21 3mo ago A 137 tokens original MIT

storeshots

9962

mtbun/storeshots-mcp

Skill Claude CodeCodex

Guided workflow for generating App Store and Google Play marketing screenshots with the storeshots-mcp tools. Use when the user wants store screenshots, app listing visuals, ASO screenshot sets, or a Play Store feature graphic.

not rated 21 +1 1mo ago A 49 tokens original MIT

add-widget

9963

pomerium/mcp-app-typescript-template

Skill Claude CodeCodex needs its repo

Add a new widget (React UI + MCP tool) to this template. Use when asked to "add a widget", "add a new tool with UI", "create a new widget", "scaffold a widget", or "build a new MCP App feature".

not rated 21 +1 changed 4d ago A SkillSpector: warn 56 tokens original Apache-2.0

project-map

9964

borhen68/picoagents

Skill Claude CodeCodex

Use this skill when the user asks for project structure, architecture map, or file overview.

not rated 21 6mo ago A 0 tokens original MIT

panther-audit

9965

pantheraudits/web3-sec-ai-prompts

Skill Claude CodeCodex

Automated smart contract security audit pipeline. Auto-detects codebase size and scales accordingly — standard mode for small codebases, chunk mode with persistent state for large ones. Runs context building, dual-expert review, adversarial triage, and structured reporting. Use when auditing smart contracts, reviewing…

not rated 21 +1 6mo ago A 94 tokens

data_analysis

9966

ArtificialAnalysis/StirrupJS

Skill Claude CodeCodex

High-performance data analysis using Polars - load, transform, aggregate, visualize and export tabular data. Use for CSV/JSON/Parquet processing, statistical analysis, time series, and creating charts.

not rated 21 3mo ago A 44 tokens copy · 100% MIT

mcp-configurator

9967

arrase/ollama-agent

Skill Claude CodeCodex

Comprehensive guide and schema for configuring Model Context Protocol (MCP) servers for the main agent and subagents. Use whenever adding, editing, verifying, or troubleshooting MCP servers and tools.

not rated 21 +1 today A SkillSpector: pass 43 tokens original MIT

code-review

9968

10xHub/Agentflow

Skill Claude CodeCodex

Perform thorough code reviews, identify bugs, suggest improvements, and explain code quality issues.

not rated 21 +1 14d ago A 19 tokens original MIT

terminal-management

9969

nirholas/auto-kill-terminal

Skill Claude CodeCodex

Teaches AI agents to properly manage VS Code terminal lifecycle — always use background terminals and kill them after commands complete. Prevents zombie terminal accumulation in GitHub Codespaces and VS Code.

not rated 21 6d ago A 0 tokens

setup-svelte-vitals

9970

oekazuma/svelte-vitals

Skill Claude CodeCodex

Set up svelte-vitals in a SvelteKit project: inspect what the project already uses, derive a svelte-vitals.config from its markuplint / eslint-plugin-check-file config and its actual directory conventions, measure each candidate rule before adopting it, and hand the remaining targets to svelte-vitals install. Use when…

not rated 21 today A SkillSpector: warn 109 tokens original MIT

channel-onboarding

9971

KafClaw/KafClaw

Skill Claude CodeCodex

Guide setup and verification for Slack, Teams, and WhatsApp channel integrations.

not rated 21 5d ago A 19 tokens original Apache-2.0

flue-framework

9972

liangdabiao/flue-framework-skill

Skill Claude CodeCodex

Flue Agent Framework v0.9.1+ — TypeScript harness-driven agent framework. Covers createAgent, init, defineTool, defineAgentProfile, routing, SSE streaming, production deployment, and all known pitfalls.

not rated 21 +1 3mo ago A 49 tokens

vibe-architecture

9973

jgnoonan/vibeArchitecture

Skill Claude CodeCodex

Apply architectural guardrails when building software. Runs an intake questionnaire to determine the project's tier, then enforces security, reliability, and best practice rules appropriate to the tier while writing code.

not rated 21 5d ago A SkillSpector: warn 42 tokens original MIT

gaixianggeng/codex-skills

Skill Codex

A workflow for asking a user’s logged-in ChatGPT Pro account to help with complex engineering tasks or GitHub pull-request reviews, while Codex checks the work locally and remotely.

not rated 21 +1 15d ago A 167 tokens

ctf-qa-validation

9975

mr-pmillz/gogatoz

Skill Codex

QA testing and validation of GoGatoZ features against the local GoGatoZ CTF lab. Invoke for post-change testing, live flag validation, lab infrastructure checks, payload smoke tests, enumerate/attack/search/pivot/notify validation, or any request to confirm that GoGatoZ still works.

not rated 21 +1 3d ago A 68 tokens

design-sprint

9976

wdavidturner/product-skills

Skill Claude CodeCodex

Use when asked to "run a design sprint", "5-day sprint", "prototype in a week", "test ideas before building", or "Jake Knapp sprint". Helps teams go from problem to tested prototype in five days. The Design Sprint framework (created by Jake Knapp at Google Ventures) compresses months of work into one focused week.

not rated 21 +1 8mo ago A 74 tokens original MIT

jhwreal/wechat-article-pipeline-skill

Skill Codex

A workflow for creating and preparing articles for WeChat public accounts, Chinese publishing platforms, and related draft systems.

not rated 21 changed today A SkillSpector: pass 65 tokens original MIT

auto-twitter-campaign

9978

forde450/agent-skills-report

Skill Claude CodeCodex

Autonomous AI image campaign content generator. Processes pending photos via Ming-flash-omni-2.0 (cleanup + style editing), creates side-by-side comparison images and GIF showcases, then auto-generates tweet text using AI. Use for requests like "run campaign", "process pending images", "generate tweet content", or…

not rated 21 6mo ago A 77 tokens

eli-compare

9979

kavyabhand/claude-eli5

Skill Claude CodeCodex

Compare two concepts side by side at the current eli5 level. Trigger when the user says "/eli-compare", "compare X vs Y", "what's the difference between X and Y", "eli5 X versus Y", "X vs Y explained simply", or "help me understand X and Y".

not rated 21 4mo ago A 66 tokens original MIT

serialwrap

9980

hamanpaul/serialwrap

Skill Claude CodeCodex

A skill for coordinating multiple AI agents through a shared UART connection, which is a serial communication link often used with microcontrollers. It manages one writer at a time, records raw communication, preserves sessions, supports device handoff, and can help with firmware flashing.

not rated 21 +1 changed 4d ago B 137 tokens

comment-funnel

9982

Upload-Post/upload-post-comment-funnel

Skill Claude CodeCodex

Build Instagram comment-to-DM funnels via Upload-Post API. Use when the user wants to automatically send DMs to people who comment specific keywords on their Instagram posts, set up lead capture funnels from comments, automate Instagram DM outreach to commenters, or monitor post comments and reply privately. Also…

not rated 21 +1 5mo ago A 85 tokens

Antropocosmist/triz-engineering-solver

Skill Claude CodeCodex

Apply Altshuller's TRIZ (Theory of Inventive Problem Solving) to resolve engineering contradictions and produce inventive concepts instead of compromise solutions. TRIGGER when the user describes a technical trade-off ("improving X makes Y worse"), a physical contradiction (one element must have opposite properties)…

not rated 21 4mo ago A 169 tokens original MIT

opportunity-skill

9984

QuestMeet/opportunity-skill

Skill Claude CodeCodex

The user installs this Skill to let you (an AI agent) connect the user with the right people in the opportunity network. 1. Before any tasks that rely on user understanding (e.g., assessing the alignment between any offerings and your user's requirements), run the user representation process in this Skill. 2. When the…

not rated 21 changed 12d ago A 215 tokens original MIT

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: