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. 281,763 indexed, measured the same four ways as everything else here.

virtengine/bosun

Skill Claude CodeCodex

Use this plugin when the task involves native Windows desktop apps or browser surfaces that do not have a stronger structured integration available.

not rated 287 +2 7d ago A 0 tokens original Apache-2.0

bilibili-page-reader

3050

Misaka-Mikoto-Tech/agent-skills

Skill Codex

A tool for reading Bilibili videos, including subtitles, viewer messages, and comments. Bilibili is a Chinese video platform; viewer messages are timed comments that appear over the video.

not rated 287 +2 1mo ago A SkillSpector: warn 52 tokens original MIT

funplay-unity-mcp

3051

FunplayAI/funplay-unity-mcp

MCP server Claude CodeCodexCursor +2

MCP server "funplay-unity-mcp" as configured in FunplayAI/funplay-unity-mcp. Launched with funplay.unity.mcp.

not rated 287 +7 7d ago A tokens not measured original MIT

configure-quality-rule

3052

aliyun/alibabacloud-aiops-skills

Skill Claude CodeCodex

A manager for Dataphin data-quality rules on tables and fields. These rules check conditions such as required values, uniqueness, allowed values, or enumerations, and can run on a schedule.

not rated 287 +3 changed 1mo ago A 276 tokens

ida-pro-mcp

3053

namename333/idapromcp_333

MCP server Claude CodeCodexCursor +2

Vibe reversing with IDA Pro. Runs locally from the ida-pro-mcp Python package.

not rated 287 7mo ago A tokens not measured

wikiskill-proposer

3054

ashutoshsinghpr7/wikiskill

Skill Claude CodeCodex

Propose skills from wiki patterns and traces (WikiSkill).

not rated 286 +1 1mo ago A SkillSpector: pass 18 tokens original MIT

alfanous

3055

Alfanous-team/alfanous

MCP server Claude CodeCodexCursor +2

An MCP (Model Context Protocol) server that exposes the Alfanous Quranic search engine as tools and resources for AI assistants. Runs locally from the alfanous3-mcp Python package.

not rated 286 4mo ago A tokens not measured LGPL-3.0

Geeksfino/finskills

Skill Claude CodeCodex

A detailed financial review workflow for one company listed on China’s A-share stock markets. It examines profitability, cash flow, debt, operating efficiency, and signs that reported results may be unreliable.

not rated 286 +1 8mo ago A 100 tokens original Apache-2.0

kumo-cli

3058

ProjectKumo/KumoApp

Skill Claude CodeCodex

Drive Kumo from coding agents and automation through the kumo command-line interface. Use when starting, stopping, inspecting, configuring, or troubleshooting Kumo, Mihomo runtime state, profiles, proxies, system proxy, TUN, service mode, or Kumo agent skill installation.

not rated 286 5mo ago A 62 tokens AGPL-3.0

freecut

3059

Moh4696/freecut

Skill Claude CodeCodex

Edit any video by conversation. Transcribe (locally, free, by default), cut, color grade, generate overlay animations, burn subtitles — for talking heads, montages, tutorials, travel, interviews. No presets, no menus. Ask questions, confirm the plan, execute, iterate, persist. Production-correctness rules are hard…

not rated 286 +1 4mo ago A 78 tokens copy · 89% MIT

manage-gpt-image-cases

3060

xianyu110/awesome-gptimage2

Skill Codex

Build, validate, search, export, and maintain structured GPT image prompt case libraries with stable IDs, localized categories, prompt fingerprints, source attribution, and license metadata. Use when Codex needs to import prompt/image examples, deduplicate cases, query reusable prompts, update a case-library JSON…

not rated 286 +1 1mo ago A 73 tokens

yueyuan

3061

qianye-wuyu/yueyuan-bazi

Skill Claude CodeCodex

A specialised BaZi analysis system, where BaZi is a Chinese birth-chart method based on birth date and time. It is designed for structured analysis with explicit uncertainty and requires the user to check the chart before deeper interpretation.

not rated 286 +6 2mo ago A 263 tokens original MIT

andrej-karpathy-skill

3062

duolahypercho/andrej-karpathy-skills

Skill Claude CodeCodex

Apply Andrej Karpathy-inspired coding-agent guidelines in Codex. Use when writing, reviewing, debugging, or refactoring code to surface assumptions, avoid overengineering, keep edits surgical, and define verifiable success criteria.

not rated 286 +3 5mo ago A 51 tokens original MIT

add-example-agents

3063

microsoft/discovery

Skill Claude CodeCodex ✓ vendor

Add agents from the public microsoft/discovery GitHub repository to this workspace, either (a) locally for the Copilot app by emitting a .agent.md companion per agent (so each is invocable via runSubagent), (b) into a Microsoft Discovery project via UpsertAgent sourced fresh from upstream (binding pre-existing tool…

not rated 286 +4 3d ago A 622 tokens original MIT

mikemikeqqq/copyeditor-skill

Skill Codex

Comprehensive academic journal copyediting and manuscript review for Microsoft Word (.docx) files across disciplines and target journals. Use when the user asks to proofread, line-edit, polish, revise, redline, or prepare a manuscript with tracked changes, editor comments, a clean accepted copy, PDF review copy, and a…

not rated 285 +4 3mo ago A 144 tokens original MIT

dry-refactoring

3065

YYH211/Claude-meta-skill

Skill Claude CodeCodex

Guides systematic code refactoring following the DRY (Don't Repeat Yourself) principle. Use when user asks to eliminate code duplication, refactor repetitive code, apply DRY principle, or mentions code smells like copy-paste, magic numbers, or repeated logic. Implements a 4-step workflow from identifying repetition to…

not rated 285 +1 5mo ago A SkillSpector: pass 70 tokens original MIT

agile-pm-workflow

3066

chyxin071-sys/Agile-PM-Workflow

Skill Claude CodeCodex

Guides novice PMs through a 7-step agile workflow: dialogue-based requirement gathering, drafting PRD skeleton, HTML prototype creation (via frontend-design), mermaid flowcharts, and final PRD with iframe slices.

not rated 285 +2 7mo ago A 51 tokens

ads-strategy

3067

zubair-trabzada/ai-ads-claude

Skill Claude CodeCodex

Full Ad Strategy Orchestrator. Launches 5 parallel subagents to build a complete advertising strategy from a single URL — audience personas, creative concepts, funnel architecture, competitive intelligence, and budget allocation. Produces a composite Ad Readiness Score (0-100) with a unified, client-ready strategy…

not rated 285 7mo ago A 67 tokens original MIT

cx

3068

ind-igo/cx

Skill Claude CodeCodex

Semantic code navigation with cx CLI. Use when you need to understand code structure before reading files, find symbol definitions, trace references before refactoring, or explore large codebases efficiently. Triggers: 'cx overview', 'cx symbols', 'cx definition', 'cx references', 'code structure', 'find function'…

not rated 285 1mo ago A 82 tokens original MIT

besimple-oss/broccoli

Skill Claude CodeCodex

Non-interactive wrapper: plan-sketch -> auto-pick recommended options -> plan-write -> plan-critique-loop -> implement-from-plan -> claude-simplify-wrapper -> dedup -> code-review-loop. No PR creation and no Linear comments.

not rated 284 +1 6mo ago A 58 tokens original MIT

pmb-ai

3070

oleksiijko/pmb

MCP server Claude CodeCodexCursor +2

PMB (Personal Memory Brain) - local-first persistent memory for AI coding agents (MCP server, fully offline, no API keys). Runs locally from the pmb-ai Python package.

not rated 284 +5 1mo ago A tokens not measured original Apache-2.0

hooks

3071

get-vix/vix

Skill Claude CodeCodex

Create and manage lifecycle hooks that vixd fires automatically on agent-loop events (a tool about to run, a prompt submitted, a thread starting, a turn finishing). Use when the user wants to enforce a rule, block or rewrite a tool call, validate prompts, auto-format, notify, or react to what the agent does.

not rated 284 +3 1mo ago A 69 tokens AGPL-3.0

argue

3072

onevcat/argue

Skill Claude CodeCodex needs its repo

Run structured multi-agent debates using argue CLI for cross-examined, high-confidence answers. Use when facing strategic decisions, ambiguous trade-offs, architecture debates, or questions where multiple perspectives improve the answer. Triggers on: argue, debate, cross-examine, second opinion, multi-agent, 'Should…

not rated 284 3mo ago A SkillSpector: warn 84 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: