Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 267,937 indexed, measured the same four ways as everything else here.
GitHub work via gh CLI: PRs, review conversations, CI failures, repo state. Use when inspecting a PR, reading a review (bodies, comments, inline threads), debugging CI (finding which run failed, why a check or Actions run is red, reading job logs), or composing non-trivial gh commands. Scripts cover what raw gh can't…
Use when starting a new project. Genesis finds real production failures from similar GitHub repos, then builds a working MVP immediately - not just documents. Two modes: fast-mvp (5 min research cap, builds right after) and deep-research (full analysis). Success = user can run the project. Triggers on: "genesis init…
Build agent skills for Amazon Quick following skill construction best practices. Use when the user asks to 'build a skill', 'create a skill', 'make a new skill', 'author a skill', 'convert this to a skill', 'save this as a skill', 'test a skill', 'run evals on a skill', 'audit a skill', or wants to turn an agent…
An internal review skill named officer-inquisitor, described as a truth-seeking and adversarial reviewer. The description is partly in Chinese and mentions strict expert review and debate.
A skill for writing 30–40-second short-video scripts from supplied reference material and a topic. It uses common short-video structures and is aimed at platforms such as Xiaohongshu, a Chinese social-media app.
Analyze blockchain attack transactions end-to-end: pull chain-specific artifacts first (EVM: traces, contract source, opcodes, selectors; Solana: transaction/meta payloads, instructions, logs, accounts, invoked program metadata), then perform the full EVM-oriented 6-phase root cause analysis with deep trust boundary…
Use ProofFlow from Codex for Agent Work Ledger and maintainer workflows: wrap complex AI coding tasks in a Ledger, review diffs, export Proof Packets, triage issue text, and keep claims evidence-backed.
Use when pushing this repo's Common, Docs, Slides, Sheets, or Workspace projects to their remote Google Apps Script projects, especially when library linking, sidebar builds, or deployment/version confusion could cause a bad push.
A set of tools for understanding, creating, and editing images, video, and audio. It covers tasks such as image recognition, text-to-speech, speech-to-text, and turning images or text into video.
A stock-analysis tool that combines market data with technical indicators and interactive HTML charts. Technical indicators are calculations from price and trading-volume history, such as RSI, MACD, moving averages, and ATR.
A beginner-friendly Chinese tutor for China's 2026 CPA exam, covering accounting, auditing, finance, strategy, law, and tax. CPA is a professional accounting qualification.
Translate academic papers from arXiv to Chinese. Use when users want to (1) translate arXiv papers from English to Chinese, or (2) create technical reports summarizing academic papers. Works with arXiv paper IDs like "2206.04655".
Generate a cognitive coverage system for any project: a JSON manifest tracking understanding across files, concepts, and data flows; an interactive HTML teaching guide with quiz; and an HTML dashboard showing coverage status with gap analysis. Works for codebases, research paper collections, documentation wikis, and…
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: