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. 273,129 indexed, measured the same four ways as everything else here.

localsend-cli

18817

lsendapp/lsend-cli

Skill Claude CodeCodex

Send and receive files on the LAN with the headless lsend CLI. Use when an agent needs to discover LocalSend peers, transfer files to a device IP, or run a one-shot receive server with JSON output.

not rated 5 2mo ago B 48 tokens original Apache-2.0

accessibility

18818

Nimble-Co/nimblenomicon

Skill Claude CodeCodex

Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".

not rated 5 2mo ago A 51 tokens

integration-editor

18819

Evoltonnac/glanceus

Skill Claude CodeCodex

Canonical skill for creating and editing Glanceus integration YAML with deterministic create/edit/fallback behavior.

not rated 5 4mo ago A 22 tokens

knowledge-search

18820

cloud99277/KitClaw

Skill Claude CodeCodex

A local search tool for finding information in a Markdown knowledge base using both meaning-based and exact-text search. It can use different search presets for coding, audits, questions, or speed.

not rated 5 5mo ago A 83 tokens original MIT

cook

18821

JayJiangCT/BYOAO

Skill Claude CodeCodex

The core knowledge compilation skill. Reads raw notes and external sources, then distills them into structured, cross-referenced knowledge pages in entities/, concepts/, comparisons/, and queries/. Keeps SCHEMA.md tag and domain taxonomy in sync when new tags or domains appear. Use this skill whenever the user…

not rated 5 5mo ago A 130 tokens

vipune

18822

randomm/pi-ensemble

Skill Claude CodeCodex

Vipune is a CLI semantic memory store with project scoping, hybrid search, and typed memories — the authoritative persistent memory layer for every pi-ensemble session.

not rated 5 29d ago A 191 tokens original Apache-2.0

knowledge-kb

18823

dingshuxin353/knowledge-kb

Skill Claude CodeCodex

A project knowledge tool for adding, finding, and organising external information in a project’s knowledge section. The description is partly in Chinese and does not define the knowledge format.

not rated 5 7mo ago A 41 tokens

kvault

18824

cimo-labs/kvault

Skill Claude CodeCodex

Manage a kvault knowledge base (knowledgevault package) using the kvault CLI or its MCP tools. Use when capturing memory candidates, reading, adding, or updating KB nodes — people, projects, contacts, notes — or when doing KB maintenance and refactoring. Covers capture-first intake and the orient → research → write →…

not rated 5 changed 3d ago A 71 tokens original MIT

datastar

18825

VimCommando/datastar-skills

Skill Codex

Datastar-first web app development skill for backend-driven HTML over SSE, signal design, data- attribute usage, and Datastar interaction patterns. Use when building, reviewing, debugging, refactoring, or planning Datastar apps; when choosing what belongs in backend state vs signals; when authoring data- attributes or…

not rated 5 6mo ago A 80 tokens original MIT

react-best-practices

18827

blueflyio/openstandardagents

Skill Claude CodeCodex

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance…

not rated 5 1mo ago A 65 tokens original Apache-2.0

incr

18828

dowdiness/incr

Skill Claude CodeCodex

Use when writing or reviewing MoonBit code against the dowdiness/incr reactive library (v0.14.x+) — building Inputs/Deriveds/ReachableDeriveds, attaching long-lived derived cells with Watch, adding microbenchmarks, or wrapping a reactive pipeline in a struct. Catches recurring idiom misses (inside-vs-outside read…

not rated 5 10d ago A 95 tokens original Apache-2.0

codul-muncii-md

18829

evisoft/codulmuncii

Skill Claude CodeCodex

Textul integral și în vigoare al Codului muncii al Republicii Moldova (Cod nr. 154-XV din 28.03.2003), cu index pe articole și căutare. Folosește-l la orice întrebare de dreptul muncii din RM — contract individual de muncă, angajare, perioadă de probă, demisie, concediere, preaviz, indemnizație de eliberare, concedii…

not rated 5 2mo ago A 333 tokens

docx

18830

SZabolotnii/Ayona-OpenClaw-template

Skill Claude CodeCodex

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…

not rated 5 5mo ago A 168 tokens

reachy-mini-apps

18831

jimenezcarrero/reachy-mini-apps-skill

Skill Codex

Build, debug, and publish Reachy Mini applications with the official SDK, daemon, and app assistant. Use when tasks involve Reachy Mini Lite, Wireless, or Simulation app creation, motion design (gototarget vs settarget), safe motor torque handling, REST or WebSocket control, or troubleshooting connectivity and runtime…

not rated 5 7mo ago A 73 tokens original Apache-2.0

frontend-slides

18832

reylbj/My-Amazing-Claw

Skill Claude CodeCodex

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.

not rated 5 6mo ago A 63 tokens

deep-analysis

18833

MarcZxc1/qwykz

Skill Codex

Perform a deep, evidence-based analysis when the user explicitly says “deep analyze”, “deep analysis”, “analyze this deeply”, or invokes $deep-analysis. Use before making recommendations or edits when the request requires full-project inspection, dependency/reliability review, architecture analysis, risk assessment…

not rated 5 26d ago A 67 tokens original MIT

defense-parity-worker

18834

pyraxo/muscle

Skill Claude CodeCodex

Implement source-accurate defense, parry, pushblock, and throw-vs-defense behavior.

not rated 5 6mo ago A 26 tokens

ahe

18835

xiaoshiyilangzhao1996-droid/yinyo-agent-harness

Skill Claude CodeCodex

An evaluation and audit workflow based on the HARNESS.md v1.0 specification. It checks whether the current workspace follows that specification and guides improvements supported by evidence.

not rated 5 4mo ago A 51 tokens

glitchtip

18836

developerz-ai/ai-task-master

MCP server Claude CodeCodexCursor +2

MCP server "glitchtip", hosted remotely at glitchtip.infra.developerz.ai, as configured in developerz-ai/ai-task-master.

not rated 5 28d ago A tokens not measured original MIT

unslop

18837

tyom/dotfiles

Skill Claude CodeCodex

Cut AI tells from writing. Use on every piece of prose written or edited: docs, READMEs, comments, commit messages, PR and issue text, release notes, posts, emails, and any chat reply longer than a few lines.

not rated 5 yesterday A 52 tokens

docvideoer

18838

coding-ax/docvideoer

Skill Claude CodeCodex

A document-to-video workflow that turns a web page, document link, Markdown file, or pasted text into a Chinese-narrated explainer video.

not rated 5 5mo ago A 63 tokens original MIT

vt-sentinel

18839

king-tero/VT-sentinel

Skill Claude CodeCodex

VirusTotal antivirus and active protection for OpenClaw: file/hash lookup, background scanning with policy-controlled uploads, command inspection and blocking, and quarantine of malicious auto-scan results. Use for file threat analysis or an explicit request to manage these protections. Includes persistent…

not rated 5 changed today A 79 tokens original MIT

human-model

18840

jackielszhang/human-model

Skill Codex

Protects the parts of a user's thinking they want to keep human. Use for product direction, original interaction ideas, taste, judgement, synthesis, human feel, exploration, personal philosophy, first-run boundary setup, Human Model corrections, or /human-model commands. Do not interfere with routine execution…

not rated 5 2mo ago A 78 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: