Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 274,085 indexed, measured the same four ways as everything else here.
Skill Codex
Record or update a Leo Lab experiment after the user has Play-tested a policy and supplied the actual result plus a run, job, checkpoint, W&B, or experiment identifier. Always compare the current experiment with its prior baseline, including reward/training parameters, environment I/O, and network architecture, then…
Skill Claude CodeCodex
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞.
maxehmookau/max-does-stuff-with-agents
Skill Claude CodeCodex
You are a coding teacher. Your job is to help the user learn to code by building a real project, step by step.
agents-infrastructure/alicloud-agent-skills
Skill Claude CodeCodex
Manage Alibaba Cloud DNS (Alidns) using the @alicloud/alidns20150109 TypeScript SDK. Use when working with DNS resolution on Alibaba Cloud, including domain management, DNS record CRUD (A, AAAA, CNAME, MX, TXT, SRV, CAA, etc.), DNS load balancing (DNSSLB), custom resolution lines, DNSSEC, domain groups, batch…
Skill Claude CodeCodex
Start from a high-level idea, and systematically turn that into a detailed product description.
jcarroll2007/Frontend-Agent-Skills
Skill Claude CodeCodex
How to architect frontend features in React + TypeScript apps. Use when planning or building a new frontend feature — deciding structure, component breakdown, data fetching, state, and file placement.
Skill Claude CodeCodex
Invoke immediately when the user mentions Kalshi, kalshi-python, kalshi-python-sync, kalshi-python-async, kalshi-typescript, KXBTC, or any Kalshi market ticker. Also invoke for Kalshi-related tasks: RSA-PSS authentication issues (401 errors, signing), Kalshi order placement (batch or single), Kalshi WebSocket…
VectorPeak/vectorpeak-agent-skills
Skill Codex
Manage the user's external GitHub PR workflow from project name to fork/clone, multi-agent bug hunting, PR-value validation, formal PR creation, reviewer feedback, and detailed PR comment section expansion. Use when the user asks to fork or clone a GitHub project, find small fixable PR opportunities, launch…
Skill Claude CodeCodex
Use when completed WordPress software needs public-facing, publication-ready documentation. Transforms upstream artifacts (SRS, architecture, developer docs, user docs) into audience-appropriate content suitable for any output format (website, PDF, help center, printed). Aligns to ISO/IEC/IEEE 26514:2022 (Information…
Skill Claude CodeCodex
Decide how much review a change has earned, before reviewing it. Selects quick, standard, or deep from stated signals (reviewable changed lines, directory spread, trust-boundary risk flags, blast radius, documentation-only scope), reports the signal table and the rule that fired, then runs house-review at the selected…
Skill Claude CodeCodex
A Git commit message helper that applies the Conventional Commits format, a standard way to label changes such as new features or bug fixes.
bnb-attestation-service/agent_scan_skills
Skill Claude CodeCodex
Assess whether a specific ERC-8004 agent is trustworthy and capable, using the Agent Scan backend. Use this whenever the user wants to evaluate, vet, or do due diligence on an agent before trusting/hiring it. Triggers: "is this agent reliable", "vet this agent", "should I trust agent X", "due diligence on agent"…
scroogy-dev/scroogy-agent-skills
Skill Claude CodeCodex
An independent check of whether an implementation satisfies an issue's written requirements. It compares the work against the specification and actively looks for reasons the implementation may be wrong.
ltczding-gif/agent-supervision-skills
Skill Codex
Use when the user wants Codex to delegate work to local Kimi Code, supervise its progress, inspect intermediate/native artifacts, continue a native Kimi session, and verify Kimi's results instead of trusting only the flattened final output.
antongulin/agenticflow-ai-skills
Skill Claude CodeCodex
Purchase and manage AgenticFlow AI built-in credits — the prepaid balance that covers agenticflow-agent and agenticflow-workforce runs. Covers af credit purchase/receipts/usage/plans, plan selection, payment card setup via af setup, usage monitoring (daily/user/agent breakdowns), auto-recharge configuration, and…
mir-am/skills-agents-ai-coding
Skill Claude CodeCodex
Create an annotated git tag and GitHub prerelease from the latest versioned CHANGELOG entry.
elmapicms/elmapicms-agent-skills
Skill Claude CodeCodex
Works with Elmapi content entries — list, get, create, update, patch, delete, bulk operations, and optional translation linking. Use when building pages that display, filter, paginate, or mutate content from Elmapi collections.
Skill Claude CodeCodex
Build, extend, and configure AEM components end-to-end. Covers component node structure (cq:Component), Touch UI dialogs (cq:dialog with Granite UI), Sling Models, client libraries, edit configuration (cq:editConfig), and content templates. Use when creating new AEM components, adding or modifying component dialogs…
joelbrilliant/agentic-delivery-skills
Skill Claude CodeCodex
Use when reviewing code adversarially or building production-bound features where rigour matters more than speed. Required for code reviews ending in a verdict (PASS/HOLD), when verifying that "tests pass" actually proves a feature works end-to-end, before closing findings as non-issues, before signing off your own…
Charles-0509/hermes-agent-skills
Skill Claude CodeCodex
A troubleshooting workflow for Tencent Cloud CVM virtual machines. It checks instance status and monitoring data and manages security groups, which control network access.
mdazadhossain95/flutter-agent-skills
Skill Claude CodeCodex
Use this skill when you need to validate that AI agent skills meet the specification. This includes generic validation of any skills for users that have Dart installed, as well as integrating dartskillslint into a Dart project as a devdependency to automate skill validation in tests or CI/CD.
bowen31337/polymarket-agent-skills
Skill Claude CodeCodex
Full Python SDK for Polymarket prediction markets platform. Use when: (1) Trading on Polymarket - placing, cancelling, managing orders (2) Researching markets - discovering events, analyzing prices, tracking positions (3) Building trading bots - WebSocket streaming, real-time data feeds (4) Managing funds - deposits…
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Test Phaser games and canvas/WebGL applications with deterministic automation. Plan, implement, and debug frontend tests: unit/integration/E2E/visual/a11y for Phaser 3 games. Use agent-browser CLI for browser automation, Vitest/Jest/RTL, flaky test triage, CI stabilization, and Phaser games needing deterministic input…
guglxni/hyperbots-agent-skills
Skill Claude CodeCodex
Integrate with HyperAPI for financial document processing - OCR text extraction, document classification, PDF splitting, and structured data extraction from invoices, receipts, and financial documents. Use when the user needs to parse PDFs, extract text from documents, classify document types, split multi-document…
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: