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.
MarcusJellinghaus/mcp-tools-sql
MCP server Claude CodeCodexCursor +2
One of 3 in .mcp.json
MCP server "mcp-workspace" as configured in MarcusJellinghaus/mcp-tools-sql. Launched with ${MCP_CODER_VENV_PATH}\mcp-workspace.exe --project-dir ${MCP_CODER_PROJECT_DIR} . Needs 1 environment variable to run.
gonzalo-cordova-pou/food_delivery_mcp
MCP server Claude CodeCodexCursor +2
MCP server "food-delivery-mcp" as configured in gonzalo-cordova-pou/fooddeliverymcp. Runs locally from the food-delivery-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server for LPC language server. Runs locally from the @gesslar/lpc-mcp npm package.
Skill Claude CodeCodex
Guides the user in discovering a better model structure (e.g. from feature transformations in logistic regression to equation terms within PDEs to neural network layer compositions) out of data. Use when the user asks to create or improve an existing model. Uses an iterative meta/inner agent loop to explore structural…
Skill Claude CodeCodex
Helps discover and install agent skills when looking for functionality that might exist as an installable skill.
jiachengwang-punch/small-sample-analysis
Skill Claude CodeCodex
End-to-end methodology for supervised machine learning on small datasets (typically 30-200 samples) where standard "throw XGBoost at it" approaches fail. Use this skill whenever the user is building a predictive model on a small dataset, especially when sample-to-feature ratios are tight, when interpretability matters…
Skill Claude CodeCodex
Generate personalized, unconventional side quests for solo adventures or group hangouts through an adaptive quiz. Use when user says "quest", "side quest", "bored", "drop a quest", "what should I do", "/quest-drop", or wants activity ideas that are genuinely exciting and non-generic.
Aidress-ai/aidress-skill-find-verified-deployment-automation-agent
Skill Claude CodeCodex
Find a Verified Deployment Automation Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for software agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).
MinistaJazz/diasporic-intelligence
Skill Codex
Use when writing, reviewing, citing, or implementing Diasporic Intelligence, a source-credited framework also described as Afrotemporalism in Action. Preserves source credit, consent governance, provenance, revocation, lineage boundaries, and the distinction from generic cultural AI, biometric extraction, and ancestor…
Skill Claude CodeCodex needs its repo
Humanize AI-flagged academic/professional text in Spanish and English so it passes stylometric AI detectors (Compilatio Magister+, GPTZero, Turnitin, Originality.ai) while keeping the original meaning, data, and citations intact. Use when the user says "humanize", "humanizar", "bajar el porcentaje de IA", "pasar…
miracorhan/OpenGoogleImageGeneratorMCP
MCP server Claude CodeCodexCursor +2
MCP server "open-google-image-mcp" as configured in miracorhan/OpenGoogleImageGeneratorMCP. Runs locally from the open-google-image-mcp Python package.
MCP server Claude CodeCodexCursor +2
Intelligent tool-call review system for AI agents. Runs locally from the superego-mcp Python package.
movebrickschi/harness-engineering-mcp
Skill Claude CodeCodex
A workflow for writing Chinese-language technology articles for WeChat, a messaging and publishing platform widely used in China, from recent news or a chosen topic.
promobase/facebook-business-mcp
MCP server Claude CodeCodexCursor +2
unofficial MCP server implementation for Facebook Business API. Runs locally from the facebook-business-mcp Python package.
MCP server Claude CodeCodexCursor +2
Git-backed multi-user wiki MCP server — LTM for any AI. Runs locally from the wikimcp Python package.
Skill Claude CodeCodex
Use when an approver agent wakes to clear pending approvals and needs a structured review workflow covering each item before deciding to approve, reject, or escalate.
MCP server Claude CodeCodexCursor +2
Tushare MCP Server with HTTP transport for financial data. Runs locally from the tushare-mcp-http Python package.
Skill Claude CodeCodex
Replace this with one to three sentences describing what this skill does, when to use it, and what it produces. Aim for at least 50 characters.
jackterror/social-demand-signal-agent
Skill Codex
Operates a human-reviewed social listening workflow that finds public customer pain, buying intent, product questions, competitor frustration, and unmet demand; routes risk; drafts governed A/B responses; and learns from observed outcomes. Use for social listening, demand-signal monitoring, public conversation…
Skill Claude CodeCodex
Challenges decisions, plans, and code by systematically arguing the opposing side. Surfaces risks, pokes holes in assumptions, and stress-tests thinking before committing. Supports intensity levels (gentle, balanced, ruthless, linus) and works with conversation context or a specific file reference. Trigger on requests…
lelephi/marketing-agent-skills-for-founders
Skill Claude CodeCodex
Review a company website or landing page the way a head of design, a CMO, and the actual customer would. Scores it out of 50, ranks the gaps by revenue damage, and rewrites the hero. Use whenever someone shares a homepage, landing page, marketing site, or URL, or screenshots, or pasted hero copy, and wants feedback, a…
jneaimi/evaluate-before-you-build
Skill Claude CodeCodex
Solution design skill based on Bloom's AI Collaboration model. Use when the user says /design, wants to design a solution, compare architectural options, evaluate tradeoffs, or produce a solution design document before building. Also trigger on phrases like "design the solution", "how should we architect this"…
MCP server Claude CodeCodexCursor +2
MCP server "chess" as configured in alegerber/stockfish-lc0-mcp. Runs dist/index.js with node. Needs 3 environment variables to run.
Skill Claude CodeCodex
LLM-driven epistemic reasoning engine. Evaluates claims against evidence, outputs calibrated confidence and structured belief state (VERIFIED/CONTESTED/UNCERTAIN). v2 adds 4-way constraint system, parameterized configuration, and formula-based confidence intervals. Use when the agent needs to assess whether…
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: