Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,730 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex
Read this skill when you want to understand your affect reading, interpret what it means for your current work, or decide how to respond to elevated pressure. Covers the traditions that ground the instrument, what each dimension measures, the choices available to you, and what the instrument cannot see.
Skill Claude CodeCodex
Validate, fix, and publish skills as GitHub repos. Structures workflow skills for execution fidelity. Registers skills across platforms via symlinks and guides first-use onboarding. Use when the user says "create a skill", "forge a skill", "review this skill repo", "audit this skill", "audit all my skills", "audit…
martinholovsky/claude-skills-generator
Skill Claude CodeCodex
Skill "argo-expert" from martinholovsky/claude-skills-generator, covering 1. overview, 1.1 role & expertise, 1.2 core expertise, 2. core responsibilities and 2.1 design principles.
limelights-amsterdam/mckinsey-strategy-team
Skill Claude CodeCodex
Orchestrates a live agent team that pressure-tests a strategic question with McKinsey-style frameworks. A team lead runs intake, classifies the problem, then runs the team in waves: diagnose + map the market in parallel, generate competing strategic options from opposing mandates and filter them to a shortlist…
nexus9888/hermes-memory-skills
Skill Claude CodeCodex
Memory-agnostic background consolidation — reviews sessions, scores candidates, promotes durable insights to the active memory backend (built-in MEMORY.md or Holographic). Three-phase (Light/Deep/Condensation/REM). Run via cron or manually.
MCP server Claude CodeCodexCursor +2
MCP server "docuthinker-orchestrator" as configured in hoangsonww/DocuThinker-AI-App. Runs orchestrator/mcp/server.js with node. Needs 1 environment variable to run.
Skill Claude CodeCodex
Debug and trace C/C++/Rust programs with the GNU Debugger (GDB) without blocking the agent. Use when you need to set tracepoints, inspect variables, or monitor a running process while staying responsive to the user.
Skill Claude CodeCodex
A tool for retrieving current hot-search lists and popular topics from major Chinese platforms, including Weibo, Zhihu, Baidu, Douyin, Toutiao, and Bilibili. It uses their listed public endpoints.
markerikson/opencode-config-example
Skill Claude CodeCodex
Design patterns for data-dense dashboard UIs with dark themes. Use when building tables, charts, status panels, and data visualization components. Focuses on readability, information density, and consistent design systems.
delineas/astro-framework-agents
Skill Claude CodeCodex needs its repo
Astro framework specialist for building fast, content-driven websites with islands architecture. Use when creating Astro components, configuring hydration (client:load/idle/visible/media), using server:defer (server islands), Content Layer API (glob/file loaders, live loaders), sessions, astro:env, i18n routing…
Skill Claude CodeCodex
A command-line connection to a user’s T-Invest brokerage account, providing portfolio data, market information, calculations, and explicitly requested trades.
Skill Claude CodeCodex needs its repo
Bootstraps a deep-sky object (DSO) astrophotography project from raw acquisition frames (own rig, not a smart telescope), AND generates a complete, polished HTML documentation page, a processing checklist, an AstroBin post JSON, a PixInsight process icon set (XPSM), and a ready-to-paste PixInsight project Description…
MCP server Claude CodeCodexCursor +2
Persistent code indexing for AI assistants. 50x less context than grep. 11 languages. Runs locally from the aidex-mcp npm package.
Skill Claude CodeCodex
Get code reviews, plan evaluations, and second opinions using OpenAI Codex CLI (GPT-6 Astra). Use for reviewing code changes, evaluating implementation plans, getting alternative perspectives, or validating approaches with another AI model.
Skill Claude CodeCodex
Writing engine that audits and rewrites prose for AI-resistance, fidelity, and mechanical tell removal.
syzkillall/comprehensive-thinking-skill
Skill Codex
A structured method for making careful judgments about difficult or uncertain problems, including technical and non-technical decisions.
Skill Claude CodeCodex
Google Ads data analysis and reporting via google-ads-open-cli. Use when the user wants to check Google Ads performance, pull campaign/ad group/keyword stats, explore account structure, audit conversions, or run custom GAQL queries. Triggers: "Google Ads", "ad performance", "campaign stats", "GAQL", "ad spend"…
Skill Claude CodeCodex
Provide expert guidance on backend and database services. Advises on database design, APIs, authentication, and deployment.
MCP server Claude CodeCodexCursor +2
Lean Theorem Prover MCP. Runs locally from the lean-lsp-mcp Python package.
MCP server Claude CodeCodexCursor +2
63 semantic Java analysis tools via Eclipse JDT: navigation, refactoring, code intelligence. Runs locally from the javalens-mcp npm package. Needs 3 environment variables to run.
KingJing1/podcast-transcript-txt-skill
Skill Codex
A workflow for finding and exporting cleaned podcast or video transcripts as TXT files. It accepts sources such as YouTube, episode webpages, podcast searches, social-media links, audio URLs, and episode titles.
Skill Claude CodeCodex
Generate a high-level TLA+ model from source code (C, C++, Rust, etc.). Analyzes code to understand its purpose, creates abstractions, writes TLA+ specification, and proposes invariants and properties. Use when the user wants to model source code in TLA+, create a formal specification from implementation, or verify…
MCP server Claude CodeCodexCursor +2
MCP server "trends-mcp", hosted remotely at api.trendsmcp.ai, as configured in trendsmcp-ai/Trends-MCP.
pingchesu/hermes-curator-evolver
Skill Claude CodeCodex
Use when interpreting Hermes Curator Evolver evidence reports, historical session backfill, proposals, verifier results, candidate search, auto-run output, timer installs, or guarded apply manifests.
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: