Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 272,006 indexed, measured the same four ways as everything else here.
Ryder-MHumble/Youtube-KOL-Transcripts
Skill Codex
Retrieve evidence-backed viewpoints from the kol-transcripts repository. Use when a user wants to compare a thesis with KOL opinions, find who expressed a similar or opposing view, recover exact original wording from transcript Markdown files, or cite a video URL and timestamp. Especially useful for strategy research…
Skill Claude CodeCodex
Activate when an agent must parse high-throughput screening plate-reader data, reconcile plate maps, detect row/column/edge artifacts, normalize inhibition or activation assays, calculate Z-prime or robust Z-prime, compute robust z-scores or B-scores, assess replicate concordance, control false discoveries, call…
Skill Claude CodeCodex
Pre-commit/ship code review: Codex default; optional Claude or Pi.
Pavel-Kravchenko/Bioinformatics
Skill Claude CodeCodex
ColPali-style Vision RAG: embed rendered PDF pages, retrieve via ColBERT MaxSim, feed top-k pages to Qwen2-VL, no OCR. Use for PDF/document QA over figures and tables, multimodal retrieval, or Recall@k/MRR eval.
Skill Claude CodeCodex
Use when a command needs API keys or environment secrets. Inject only named variables through envskill without reading or printing values.
LevyBytes/AI-SKILL-adobe-products
Skill Claude CodeCodex
Use when a task specifically concerns Adobe InDesign: InDesign documents, layouts, pages, spreads, frames, styles, publishing, UXP, or layout scripting; this is the product subskill routed from adobe-products.
Skill Claude CodeCodex
Generate a custom checklist for the current feature based on user requirements.
Skill Claude CodeCodex
Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a verdict. MANDATORY TRIGGERS (always invoke on these exact phrases) 'council this', 'run the council', 'convene the council', 'war-room this', 'pressure-test this'…
Skill Codex
Run an isolated persona-based UX test through the real desktop or browser UI. Creates a precise non-developer user persona, gives the tester only an approved product introduction, prevents source-code and design-document leakage, and produces an evidence-based Chinese evaluation report. Use when the user asks for…
Skill Codex
Evidence-first opportunity discovery — finds novel, defensible product/startup/project opportunities by researching before ideating, and mechanically rejects generic "AI-powered X" slop with deterministic validators. Use whenever the user asks for startup ideas, product or business opportunities, "what should I…
Skill Claude CodeCodex
Use when generating documentation from a codebase, creating architecture docs, building an Obsidian vault from code, or when someone asks to document or explain a project's structure.
Skill Claude CodeCodex
Advanced narrative agent that engineers human-resonant stories using neurochemical pacing, Jungian archetypes, structural paradigm selection, and automated pathology diagnostics. Use when asked to "write a story", "create a narrative", "develop characters", "build a world bible", "expand a novel", "batch revise", or…
Skill Claude CodeCodex
Use this skill for ANY coding task — writing new code, fixing bugs, refactoring, reviewing code, or implementing features. It makes Claude code like an experienced senior software engineer instead of a code generator: understanding context before writing, matching existing conventions, handling edge cases and errors…
Skill Claude CodeCodex
Pre-execution planning and priority-scored task list before running tools.
MCP server Claude CodeCodexCursor +2
MCP server "openbaud" as configured in Leonezz/openbaud. Runs ./launcher.mjs with node.
yihefeikong-rgb/ai-plc-integration-public
MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
MCP server "tiacommander" as configured in yihefeikong-rgb/ai-plc-integration-public. Launched with D:\claude code xiangmu\AI 接入PLC\mcp-servers\tiacommander-mcp\TiaCommander.exe.
Skill Codex
Audit and optimize OpenAI Codex context locally, enforce reviewable context budgets, compile model and subagent profiles, detect capability drift, create redacted lockfiles, inspect model-visible prompt structure, and render honest token, credit, quota, or API-cost receipts. Use when the user explicitly invokes…
moVictor99/shopify-theme-builder
Skill Claude CodeCodex
Build a complete, clean, Online Store 2.0 Shopify theme from a guided requirements interview. Use when a user wants to build, generate, scaffold, or design a Shopify theme, Shopify sections, JSON templates, Liquid, section groups, or a fully theme-editor-controllable storefront (including bilingual / RTL Arabic…
Skill Claude CodeCodex
Web platform design and accessibility guidelines. Use when building web interfaces, auditing accessibility, implementing responsive layouts, or reviewing web UI code. Triggers on tasks involving HTML, CSS, web components, WCAG compliance, responsive design, or web performance.
HenriqueCotta/ownership-driven-ai-customization-architecture
Skill Claude CodeCodex
Assess likely downstream impact, decide what should be reconciled now versus carried forward explicitly, and keep the repository coherent without sweeping every related surface.
MCP server Claude CodeCodexCursor +2
A simple MCP server to fetch the content of ArXiv papers. Runs locally from the arxiv-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server "netlab-mcp" as configured in steinzi/netlab-mcp. Runs locally from the netlab-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server to search the web and fetch page contents. Runs locally from the @guhcostan/web-search-mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server for SSH operations with built-in diagnostics. Runs locally from the @yawlabs/ssh-mcp npm package.
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: