Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 274,248 indexed, measured the same four ways as everything else here.
Make a person or brand the answer when Google or an AI assistant (ChatGPT search, Perplexity, Google AI Overviews, Microsoft Copilot, Gemini) is asked "who is X". An interactive, guided wizard: it asks the user for their name, positioning, real proof, products, and socials, then walks them step by step through writing…
Capture the entire current chat as a structured handoff document for the user to paste into Codex, Cursor, or another IDE-based AI coding agent. Use this skill whenever the user types /handoff, /export-context, /brief codex, /give to cursor, /dump, or says anything like "package this for codex", "export this chat"…
Build a structured Excel investor shortlist (M&A or fundraising mandate) by combining local investor databases, Outlook contacts, web search (Firecrawl) and email enrichment (Dropcontact). Output is a 2-tab .xlsx (branded cover page + 31-column investor table with full transaction pipeline). Trigger when the user says…
A structured review process in which several reviewers examine a claim, plan, or piece of work separately and compare their findings against evidence. It produces agreed conclusions along with objections and unresolved decisions.
A product-requirements writing guide that turns an idea into a detailed document an AI coding assistant can follow. PRD means product requirements document.
Turns rough input into structured Jira work. Two modes — single-ticket mode turns a bug description, meeting notes, Slack thread, incident writeup, or a few sentences into one fully-structured Jira ticket; decomposition mode turns a rough requirements doc or product brief with multiple asks and open questions into…
Create, update, or validate SKILL.md files and skill packages. Use this skill when users ask to "create a skill", "make a new skill", "add a skill", "write a skill", "update a skill", "validate skill", "check skill quality", "review skill", "audit skills", or work with .claude/skills/ directory contents. Supports…
Find a Verified Social Media Management Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for content agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).
MCP server "pubmed-evidence" as configured in Tianyu-Qu/mcp-pubmed-evidence. Runs mcp_pubmed_evidence.server with python. Needs 1 environment variable to run.
★not rated 2 3mo agoA
tokens not measured
originalMIT
Build or audit a reproducible official-conference census, then resolve identity-verified abstracts/full text for metadata-first screening, exact model/configuration evidence, and included/excluded/pending/duplicate dispositions. Use for conference-wide paper collection across ICLR, ASE, FSE, ISSTA, ICSE, ICML, AAAI…
MCP server "lean-mcp" as configured in misanthropic-ai/lean-docker-mcp. Runs locally from the python Python package. Needs 6 environment variables to run.
★not rated 2 1y agoA
tokens not measured
originalMIT
Add the gittools MCP server to a repository-local Codex config. Use when Codex needs to create or update .codex/config.toml in the current repository so the local config launches git-prompts-mcp-server via uvx with the repository root as an argument.
MCP server "smallcloud-mcp-server" as configured in SmallCloudCo/smallcloud-mcp-server. Launched with /opt/homebrew/bin/node ~/Git/smallcloud-mcp-server/index.js.
★not rated 2 1y agoA
tokens not measured
originalISC
Qualify or disqualify sales accounts for high inbound lead volume using Apollo CRM data, website intelligence, LinkedIn ads, funding signals, and job posting analysis. Automatically researches accounts, applies qualification rules, saves research notes to Apollo, and sorts accounts into Qualified or Not Qualified…
Decide API-vs-self-host LLM economics and fine-tuning ROI from any user context (code, PRDs, traffic logs, billing screenshots). Fetches live GPU prices from Runpod/Lambda/Modal, API prices from models.dev or vendor pages, and quality rank from lmarena.ai, then calls a deterministic local Python script for VRAM…
★not rated 2 4mo agoA152 tokens
originalMIT
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: