Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 273,364 indexed, measured the same four ways as everything else here.
Write Markdown files that pass markdownlint with zero warnings. Use when creating or editing .md, .mdc, or .mdx files, writing documentation, updating README files, or creating Cursor rules and skills.
Add persistent, interactive task plan management to your agent. Wingman tracks plans and tasks across a long conversation — Claude creates plans, ticks tasks after completing work, and a live panel renders inline in the chat. Install the MCP server first, then use these tools to manage plans and tasks throughout any…
Token-efficient web research for AI agents. Fetches, indexes, and queries web content locally via hybrid BM25 + embeddings, returning only the chunks that fit a token budget. Replaces raw webfetch for any task involving more than one source. Use when the user asks you to research, compare, summarize, or fact-check…
Manage your LinkedIn and Twitter presence with Reepl -- create drafts, publish and schedule posts, manage contacts and collections, generate AI images, create carousels, post to Twitter/X, and maintain your voice profile. Requires a Reepl account (reepl.io).
Use when creating Juhuo AI event promotion copy from an activity plan, Word/WPS document, or structured event brief for WeChat Official Account, Xiaohongshu, QQ channel/group/campus-wall reposts, or a full campus AI community promo package.
Use when the user wants AI project memory, task documentation, decision records, bug history, feature notes, context recovery, or "document everything" behavior without forcing a project structure. This skill keeps engineering context recoverable and only creates project files when the user explicitly asks to…
36 behavioral rules that cut AI output tokens 59% while maintaining quality. Always-on rules: no filler, no echo, act first, proportional responses, diffs over rewrites, cheapest tool first, parallelize calls, compact early. Drop-in for any project. Based on benchmark results across 15 tasks, 7 categories, 3-run…
Convene the board ON THE SYSTEM ITSELF - inventory the harness's own recent failures and weaknesses, attack them from eight adversarial angles, and leave with a prioritized determinism backlog and a scaling plan. USE WHEN the same class of mistake keeps recurring, before scaling the system up, quarterly as a health…
MCP server "windows-computer-use" as configured in GrimFandango42/Claude-MCP-tools. Runs C:\AI_Projects\Claude-MCP-tools\servers\windows-computer-use\server_mcp_framework.py with python. Needs 1 environment variable to run.
It allows AI agents to securely use a user’s wallet within the approved scope. Capabilities: x402 payments, USDC transfers, agent to agent transfers, payment links for receiving payments, discovering and calling x402 resources (paid APIs, Oneshot APIs), issue credit cards for agents, and using credit cards to complete…
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
An analysis guide for Pandadata index valuations and Chinese A-share industry rotation. It covers valuation percentiles, market temperature, fixed-investment references, and industry momentum.
Disciplined methodology for AI agents executing large, multi-step software tasks reliably. Covers context engineering, separated evaluation, and multi-session handoffs. Use when working on complex refactors, feature development, optimization, migration, or any task spanning many files or requiring sustained focus.…
★not rated 4 6mo agoA81 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: