Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,788 indexed, measured the same four ways as everything else here.
A Chinese-language guide for writing, editing, checking, and finalising undergraduate, master’s, and doctoral theses. It covers academic structure, references, formatting, experiments, figures, consistency, and anonymous review requirements.
Use this skill for ANY financial market, investment, or macro-economic analysis. ALWAYS trigger this skill — do not skip it — when the user asks about: BTC, bitcoin, crypto, gold, silver, oil, stocks, forex, bonds, interest rates, Fed policy, inflation, deflation, stagflation, market structure, trading setups…
A writing and editing skill for Taiwanese Traditional Chinese and natural-sounding English, with modes for changing the assistant's voice or revising supplied text.
Turn a rough task or idea into a decision-closed, senior-reviewable requirement by asking structured questions grounded in the existing codebase. Only draft the final artifact after all key decisions are resolved and the user confirms.
Transform any user-uploaded photo into a vintage editorial print illustration—not a photo filter. Use for food, beverage, landscape, architecture, portrait, or product images that need Japanese archive print, mid-century graphic, risograph, specimen-sheet, or handmade editorial-art direction while preserving source…
Create beautiful, shareable HTML-based slide presentations styled to Red Hat brand standards. Generates single-file, self-contained HTML decks with click/keyboard navigation, story-arc-driven narrative structure, and cinematic dark-mode aesthetics. Supports embedded videos (YouTube, Vimeo, direct URLs) and linked…
When inferring character intent or behavioral patterns from video, validate inferences against cumulative observed actions rather than isolated moments or assumptions.
Verify that implementation and tests remain synchronized with specs after code changes. Use when code has been generated or modified from specs, after implementation is complete, or when reviewing a PR that touches spec-covered code. Reports mismatched targets, broken test links, and undocumented behavioral changes.…
Bootstrap AI coding assistance into ANY project. Supports 4 AI tools — Claude Code, Qoder, Codex, OpenCode. All tools share EXACTLY the same split-file architecture (rules/skills/agents/hooks/references loaded on-demand). Only the entry file name and config directory name differ.
Analyze WhatsApp Web data — contacts, groups, social graph, AND decrypt actual message content via live browser interception. Use when: 'WhatsApp contacts', 'WhatsApp groups', 'WhatsApp analysis', 'who do I talk to', 'WhatsApp messages', 'decrypt WhatsApp', 'read WhatsApp messages', 'WhatsApp network', 'social graph'…
Take over and control external devices (Android phones, Linux handhelds, Linux PCs) via network. Provides screen vision, touch/input control, voice I/O, and app management. Use when: controlling a remote device, playing games on a handheld, navigating a phone, taking screenshots of external devices, sending touch…
Iterative multi-round codebase audit with diminishing-returns detection. Run 5-20+ rounds, each focusing on one specific area. Built from 19 rounds of dogfooding pi-crew on itself. When NOT to use: one-shot review (use multi-perspective-review); investigation with single round (use read-only-explorer).
Invoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data…
Walk a client through a Responsible AI assessment questionnaire and score their answers 0-5 across eight RAI dimensions (Governance, Privacy & Security, Safety, Veracity & Robustness, Controllability, Fairness, Explainability, Transparency). Use when a user asks to run a Responsible AI assessment, RAI scorecard…
Run ambitious one-shot websites, web apps, games, simulations, clones, motion pieces, or benchmarks through fresh isolated subagents. Use for one-shot web artifacts, catalogue ideas, or parallel model/harness variants.
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: