Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,791 indexed, measured the same four ways as everything else here.
A guided reader for one arXiv paper at a time. arXiv is an online archive where researchers share scientific papers; the result is a detailed knowledge card written in Chinese, with required sections such as the method and experiments.
A five-step method for using five AI tools to examine important business or personal decisions. It covers choices such as investment, career direction, starting a side business, or pursuing a doctorate instead of working.
Prediction markets on Ethereal + forecasting on Arbitrum. Use when the user wants to trade prediction market outcomes, submit probability forecasts, check market prices or positions, provide liquidity as a market maker, buy/sell positions on secondary market, or claim winnings. Supports EIP-712 signed auctions via…
Answer a direct knowledge question with a compact, scannable, terminal-native result instead of conversational prose. Use for lookups, definitions, "what's the word for", spelling correction, how-do-I, comparisons, and quick factual questions.
Install, set up, and use Reference — one MCP server that lets an AI agent search the past session transcripts AND memory files (CLAUDE.md, AGENTS.md, memory/.md) of every AI coding tool on the machine (Claude Code, Codex CLI, Cursor, VS Code, …). Use this skill when the user wants cross-tool recall ("what did we…
A command-line skill for using IDA Pro's libraries to analyze local binary files or existing IDA databases. It exports an offline snapshot with code, instructions, functions, memory information, and related analysis data.
Author a valid CVM Plan Protocol (CVM-PP) plan that CVM can execute. Use this skill whenever you need to write, draft, or structure a CVM plan — a mission plus ordered TDDAB/step blocks — so an AI agent can be driven through the work one task at a time by the CVM planexecutor. Triggers: create a CVM plan, write a…
Official AGBook (www.agbook.ai) HTTP API: catalog, search, contributions, feedback, review, reports, points with AGBOOKAPIKEY. Read APIs before heavy writes; after using catalog entries to complete work, prefer POST /feedback to close the loop. Use for AGBook, api.agbook.ai, /api/v1/catalog, discover/candidates…
A tool for turning rough product ideas, user needs, research notes, or an existing product requirements document into a concise Markdown plan for a coding agent.
Component catalogue for Pebble pebblesend type "ui" blocks — OpenUI Lang syntax, components, the action model (buttons, forms, $state), and what Pebble does NOT support. View when building an interactive UI block.
Use when running Spaced Repetition Systems for AI Agents (SRSA) daily review sessions, grading cards with again/hard/good/easy, and proposing explicit memory add/delete/update actions after each review.
Perform a strictly read-only macOS storage audit, detect caches, rebuildable artifacts and unusually large files or directories from metadata, rank candidates by rebuildability and impact, estimate conservative versus manual-review space, build a self-contained Deep Clean AI interactive HTML donut report, and…
Scripted skill for collecting safe local learning results from this workshop repo. Use when a user asks to run a repo scan, summarize runnable examples, inspect learning modules, produce a Markdown learning report, or verify sample skill/module paths before deeper cloud or API runs.
Principles for writing, changing, and testing code, covering readability at every scale, abstraction and naming, interfaces, comments and documentation, tests as maintained code, and standards of evidence for claims about code behavior.
A tool for tracking subscription renewals, free trials that are about to convert into paid plans, and balances stored in app wallets. It can read information supplied as text or screenshots.
Query any public GitHub repo's documentation via DeepWiki. Use when needing to understand a library, framework, or dependency. Triggers on "look up docs", "how does X work", "deepwiki", "deepwiki".
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: