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. 273,985 indexed, measured the same four ways as everything else here.

job-description-writer

21217

Uhudsavasindankacanokcu2/recruiting-skills-for-claude

Skill Claude CodeCodex

Write clear, inclusive, conversion-optimized job descriptions from a short role brief. Produces a structured JD with must-have vs nice-to-have split, inclusive language, salary-band guidance, and a screening scorecard. Use when the user needs to write/improve a job posting, hire for a role, or asks for a job…

not rated 4 3mo ago A 75 tokens

design-libera

21218

liberastudio-mx/skill-web-design

Skill Claude CodeCodex

Visual and aesthetic design direction for web and UI. LIBERA Studio synthesis of impeccable design laws + high-end-visual-design pattern catalog. Self-contained for first-pass direction; optional deep-dive references if skill-web-design repository is available. Covers brand and product registers, OKLCH color strategy…

not rated 4 4mo ago A 92 tokens

claude-design-brand

21219

erenisci/claude-design-prompter

Skill Claude CodeCodex

DEPRECATED — use Acta (acta-design) at https://github.com/erenisci/acta. Detect the project's character from its repo (project type, audience, voice) and produce a complete brand foundation — palette, typography, mood, motion, voice, accessibility — with type-specific recommendations the user can accept or override.…

not rated 4 2mo ago A 120 tokens original MIT

aeo-kr

21220

gugdongbag-eng/korean-marketing-skills

Skill Claude CodeCodex

A Korean-language guide to answer engine optimization, the practice of helping AI services such as ChatGPT, Gemini, Perplexity, and Google AI mention or recommend a business in their answers.

not rated 4 3mo ago A 236 tokens

git

21221

RealTapeL/SkillPilot

Skill Claude CodeCodex

Version control with Git - commit, branch, merge, push, pull.

not rated 4 +1 6mo ago A 16 tokens

101-index

21222

101-group/101-ai-plugin

Skill Claude CodeCodex

Use when the user asks to read or change data in 101; routes every 101 goal to one available primary workflow while preserving the current chat context.

not rated 4 1mo ago A 34 tokens

hydro-plugin-handler

21223

gtn1024/hydro-dev-skills

Skill Claude CodeCodex

Comprehensive guide to HTTP request handling and WebSocket connections in Hydro plugins. Covers route registration, handler lifecycle, parameter decorators, response building, operations, the @requireSudo security decorator, WebSocket handlers, and inheritance patterns.

not rated 4 1mo ago A 51 tokens

Lancetnik/evidence-based-fitness-coach

Skill Claude CodeCodex

Use when the user asks about strength training, building a training program, hypertrophy, fat loss, gaining mass, nutrition plans, protein/macros, supplements (creatine, BCAA), recovery, cardio + lifting, training at home, or choosing a coach — any strength training or nutrition question. Triggers on "I want to lose…

not rated 4 3mo ago A 152 tokens original MIT

arcanea-image-gen

21226

frankxai/awesome-hermes-agents

Skill Claude CodeCodex

Purpose: Enable Hermes Agents to generate high-quality images, video, lipsync, and cinema content using Arcanea Studio's multi-model router (200+ models, provider-agnostic).

not rated 4 +1 4d ago A 0 tokens original MIT

gpt-5-6-prompt-engine

21227

wp-a/gpt-5.6-prompt-engine

Skill Codex

Use when creating, auditing, rewriting, debugging, migrating, or evaluating GPT-5.6 Sol, Terra, or Luna prompt layers, tool descriptions, agent briefs, or prompt stacks; choosing runtime configuration; or comparing controlled prompt candidates.

not rated 4 2mo ago A 58 tokens original MIT

creating-figures

21228

ai4paper/apaper-plugin

Skill Claude CodeCodex

Creates publication-quality scientific figures for academic papers. Backend is chosen by host paper extension — .tex papers get TikZ figures, .typ papers get CeTZ figures; the two are never mixed. Use when creating block diagrams, system architectures, flowcharts, or technical illustrations for papers and theses.…

not rated 4 13d ago A 86 tokens original MIT

engineering-discipline

21229

mukilankarthik/self-awareness

Skill Claude CodeCodex

Behavioral guidelines to reduce common agent coding mistakes — thinking before coding, simplicity, surgical changes, goal-driven execution, and mandatory verification for data/BI work. Adapted from andrej-karpathy-skills (MIT), with a data/BI engineering layer added. Use this skill whenever writing, editing, or…

not rated 4 1mo ago A 86 tokens original MIT

abacatepay

21230

AbacatePay/skills

Skill Claude CodeCodex

Integrate AbacatePay in code or interact directly with the API (list customers, create checkouts, check balance, etc.).

not rated 4 +1 5mo ago A 32 tokens

task-hypergraph

21231

VibeCodingNights/loop-engineering

Skill Claude CodeCodex

Crystallize a one-line objective into a sub-4k GOAL, scaffold a resumable task-hypergraph workspace on disk, and drive it to completion via PARALLEL map->do->review cycles run as Workflow fan-outs, with adversarial review gates, worktree isolation, and honest pass/fail gates. Use when decomposing a repo / refactor /…

not rated 4 3mo ago A 221 tokens

rhyean88/apple-platform-build-tools-claude-code-plugin

Skill Claude CodeCodex

Builds, tests, and archives Swift packages and Xcode projects for Apple platforms. Use when running xcodebuild, swift build, or swift test commands, discovering schemes and targets, or selecting simulator destinations for iOS, macOS, tvOS, watchOS, or visionOS.

not rated 4 2d ago A 64 tokens original MIT

crtvrffnrt/skills

Skill Claude CodeCodex

Static malware reverse-engineering and threat-intelligence triage for unknown files, Windows EXE/PE binaries, scripts, archives, ISOs, JavaScript, PowerShell, documents, and unpacked payloads. Use when a user provides a sample path, hash, filename, or file and asks whether it is malicious, benign, suspicious, contains…

not rated 4 16d ago A 104 tokens

agent-flow

21234

kanghelyu/agent-flow

Skill Codex

Design, validate, edit, visualize, and execute AgentFlow Markdown-first workflows with deterministic Boolean gates. Use when a task benefits from explicit boxes, arrows, branching, parallel work, resumable progress, or when the user asks to create/modify/run a workflow graph in AgentFlow.

not rated 4 1mo ago A 60 tokens original MIT

daily-work-log

21235

MasonSRE/debrief

Skill Claude CodeCodex

A daily report generator that summarizes local activity from Claude Code, Codex, Gemini CLI, and Git, with optional Chinese output.

not rated 4 3mo ago A 116 tokens original MIT

ai-security-review

21236

karthikrshet/aiskills

Skill Claude CodeCodex

Use this skill to audit an AI system for security vulnerabilities including prompt injection, sensitive data exposure, excessive agent permissions, unsafe tool calls, and insecure output handling. Grounded in OWASP GenAI LLM Top 10 (2026). Activates before production deployment of any LLM-based application, agent, or…

not rated 4 7d ago A 74 tokens

wanghao-io/it-infrastructure-equipment-selection-skill

Skill Codex

Portable IT infrastructure solution architect skill for selecting, sizing, validating and budgeting physical infrastructure equipment. Use for guided requirement discovery, scenario-based planning, equipment selection, BOM generation, tender/RFQ compliance and specification generation, project infrastructure planning…

not rated 4 changed 1mo ago A 111 tokens original MIT

continue-later

21238

dhruv-anand-aintech/continue-later-skill

Skill Claude CodeCodex

Generate a structured continuation.md for handoffs—project context, state, tasks, gotchas, and deploy steps. Use when the user wants to save state or hand off work (not for quick raw git dumps; use continue-later-fast for that).

not rated 4 4mo ago A 55 tokens original MIT

selective-intelligence

21239

infotradescout/Selective-Intelligence

Skill Codex

Use Selective Intelligence for corrections, failures, dissatisfaction, or exact trigger. Activate directly for any user correction, dissatisfaction, failure feedback, the exact words Selective Intelligence, or an unmistakable request for a named responsibility—even when unnamed and in any conversation domain. Use…

not rated 4 changed 13d ago A 179 tokens

redteam

21240

Baba01hacker666/gemini-redteam

Skill Claude CodeCodex

Expertise in offensive security research, vulnerability analysis, CMS-focused application testing, and red team operations.

not rated 4 3mo ago A 23 tokens

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: