Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 274,430 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex needs its repo
Turn notes (Notion, Google Docs, Markdown) into branded 1920×1080 HTML slide decks with PDF and PNG export. Pulls real brand tokens from any URL.
manke001-zhy/claude-code-skills
Skill Claude CodeCodex
A guide for creating or updating add-ons that extend an AI coding assistant with specialised knowledge, workflows, or tool connections.
Skill Codex
Build high-quality benchmark items, embedded scoring contracts, review examples, rubrics, evaluators, and release protocols for model and agent evaluation. Use when prompts mention benchmark construction, item writing, rubric design, score-boundary design, checker design, review examples, benchmark health…
Skill Claude CodeCodex
Guides agents through a 7-phase rigorous feature development workflow with 4 independent cross-verification passes: systematic self-review, cold-context code review (reviewer sees no design docs — finds design-level blind spots single reviewers miss), behavior-preservation diff, and cross-repo impact scan. Use this…
Skill Claude CodeCodex
A search tool for arXiv, a public website and API for sharing research preprints. It finds papers by keyword or author and returns their titles, authors, summaries, dates, and links.
Skill Claude CodeCodex
Comprehensive iOS development guidance covering SwiftUI, Swift Concurrency, Core Data, and Swift Testing.
Skill Claude CodeCodex
Comprehensive web interface guidelines for accessibility, interactions, animations, layout, content, forms, performance, and design.
Skill Claude CodeCodex
Complete reference for the Portkey AI Gateway Python SDK with unified API access to 200+ LLMs, automatic fallbacks, caching, and full observability. Use when building Python applications that need LLM integration with production-grade reliability.
Skill Claude CodeCodex
A senior product-management assistant for planning and reviewing products, including documents such as PRDs, which describe product requirements.
Skill Claude CodeCodex
Generates a complete AI-native service wiki from repository analysis for human onboarding and AI-agent long-term memory. Use when the user asks to generate a wiki, service documentation, repository documentation, ai-context.md, repository-map.md, onboarding docs, or LLM-native documentation for a codebase. Trigger on…
cuiyucheng0104-afk/q1-ai-workshop
Skill Claude CodeCodex
An AI judging workflow for student projects supplied as a folder, HTML file, or PowerPoint file. It reads the project, scores five areas, and creates an HTML report with a radar chart.
Skill Codex
Use when the user wants to deploy or manage content on a GitShelf site — a zero-cost GitHub Pages platform that turns PDFs into chapter books, renders Markdown as documents, and hosts ZIP archives as static sites. Provides CLI commands for uploading, inspecting, editing, deleting, reconverting, and checking failures.
marcbenito/claude_workshop_ensenyament
MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
Lets the agent inspect a PostgreSQL database schema and run read-only SQL queries against it. Runs locally from the @modelcontextprotocol/server-postgres npm package.
Skill Claude CodeCodex
Implementation guide for creating Jira epics with proper scope and parent linking in SRVKP project.
taimurijlal/Claude-Code-Security
Skill Claude CodeCodex
Creates a STRIDE threat model of the current project with ASCII diagrams and outputs a threat.md file. Use when analyzing system security, designing architectures, or identifying threats in applications.
Skill Claude CodeCodex
Converts a Figma frame into pixel-perfect code in whatever stack the project uses — by extracting EXACT values via the Figma MCP and reproducing every visual property (borders, gradients, shadows, blurs, opacity) instead of eyeballing them. Use whenever the user shares a figma.com/design URL or dev link and wants…
Skill Claude CodeCodex
Analyze your project and get personalized recommendations for Claude Code skills, MCP servers, and plugins.
Skill Claude CodeCodex
Product Office Hours — structured product thinking partner. Startup mode: six forcing questions on demand reality, status quo, specificity, narrowest wedge, observation, future-fit. Builder mode: design thinking for side projects, hackathons, learning, open source. Produces a design doc, never code. Use when asked to…
Skill Claude CodeCodex
Use Jujutsu (jj) for version control in jj-enabled projects. Covers command workflows, bookmark management, rebasing, conflict resolution, revsets, and common pitfalls. Triggers when: project has a .jj/ directory, README requires jj, or user explicitly requests jj commands. Do NOT use for regular git-only projects.
Skill Claude CodeCodex
Audit a repo for PII leakage, secrets, and sensitive data before commits or publishing. Runs gitleaks if available, scans git history, checks working tree for known and novel patterns, and optionally wires up a pre-commit hook. Use before making a private repo public, after importing external data into a project, or…
Skill Claude CodeCodex
Spin up a team of distinct AI personas that argue a topic via native inter-agent messaging, then deliver a moderated synthesis. Use when the user wants to debate, stress-test, pressure-test, red-team, or get a roundtable/panel on a decision, idea, plan, or product — e.g. "have customers debate this product"…
Skill Claude CodeCodex
This skill analyzes diagram, chart, or simulation specifications and returns a ranked list of the most suitable MicroSim generator skills to use. It compares the specification against capabilities of all available microsim generators (p5.js, ChartJS, Plotly, Mermaid, vis-network, timeline, map, Venn, bubble) and…
Skill Claude CodeCodex
Every amortized Bayesian analysis follows this sequence. Do not skip steps — especially simulator validation and model criticism.
Skill Claude CodeCodex
This skill should be used when the user asks to 'debug this failure', 'find root cause', 'compare passed vs failed', 'trace X values', 'analyze fmod vs vmod mismatch', or needs hardware simulation Root Cause Analysis methodology.
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: