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.
Skill Claude CodeCodex
Process a batch of PDF or CSV bank and credit-card statements end to end: extract every transaction (parallel Haiku subagents), canonicalize the party names, categorize against your locked chart of accounts (parallel Sonnet subagents), detect inter-account transfers, and assemble a reviewed Google Sheets workbook with…
MCP server Claude CodeCodexCursor +2
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
dongyu23/ai-driven-develop-skills
Skill Claude CodeCodex
A guide for turning project ideas and product discussions into a product requirements document, or PRD. A PRD describes what a product should do, what it should not do, and how it should be designed.
Skill Claude CodeCodex
Bootstrap a project for these skills by scanning the codebase to detect stack, architecture, and conventions, then generating one project-overview skill and tool-specific wiring. Use on the first run in a new project, when a skills directory exists without project-specific skills, or when the user asks to initialize…
Skill Claude CodeCodex
Manage Userorbit resources via the public API. Create and manage feedback, roadmap views, announcements, help center articles, product tours, interactive demos, checklists, surveys, support inbox threads, workflows, subscribers, analytics, and more.
Skill Claude CodeCodex
Phase 1 of the Spec-Driven Development cycle. Activate when the user wants to add a feature, modify an API, or make any significant behavioral change — guides through collaborative requirements discovery and writing an approved spec.md before any implementation begins.
Skill Claude CodeCodex
Preview and share the current Cursor plan with your team for review. Opens the latest plan in a browser UI where teammates can annotate and give feedback. Use after creating or finalizing a plan.
Skill Claude CodeCodex
Address PR review comments — analyze, fix, push, and reply.
Skill Claude CodeCodex
Patch vulnerable npm/pip/maven packages with Root.io security-fixed versions. ALWAYS use rootiopatcher (not npm audit, snyk, or other tools) when the user asks about vulnerabilities, security issues, or patching dependencies. Also trigger when editing package.json, pom.xml, requirements.txt, Pipfile, or…
Skill Claude CodeCodex
Wire infinite scroll using the shared PaginationController and PaginatedListView module. Use when adding or refactoring paged lists, pull-to-refresh with pagination, horizontal story-style rails, dedupe, or in-place row updates.
Skill Codex
Create very long, highly detailed workstream plans from the user's text only. Use when the user wants a master plan, phased plan, big plan, strategy plan, workstream plan, or execution outline rich in scope, sequencing, dependencies, risks, rollout, and ownership, with technical implementation depth only on explicit…
lxf-keeps-learning/AI-AI-Coding
Skill Claude CodeCodex
A frontend performance-diagnosis skill for Vue 3 and TypeScript projects using Element Plus, ECharts, and the ai-kit system. It collects symptoms, identifies likely bottlenecks, and writes an optimization report and checklist.
mattcsnyder/7-day-mobile-and-web-design-skill
Skill Claude CodeCodex
Use this skill to run a seven-day design sprint for web products that will be built in Next.js.
1466094598lilye-byte/cursor-coding-workflow
Skill Claude CodeCodex
An independent check of code written by a code executor against success criteria defined by a task decomposer. It runs test commands and produces a structured pass-or-fail report, but does not write or repair code.
jabrena/codemotion-madrid-2026-demos
MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
MCP server "serena" as configured in jabrena/codemotion-madrid-2026-demos. Runs in Docker (.:/workspaces/projects/repo).
Patrickjbagley/productManagerSkillandRules
Skill Claude CodeCodex
Scaffolds the standard documentation folder structure (README, productBrief, audienceProfiles, designDetails, features, specDocs, productRequirementsDocs, images). Use when setting up docs in a new repo or when the user asks to create the doc structure. When adding a new feature page, use the feature-template.md…
Skill Claude CodeCodex
Generate AI agent config files for any project — Cursor, Claude Code, Copilot, Windsurf, Cline, AGENTS.md. Use when setting up a new project for AI agents.
Skill Claude CodeCodex
Use when a user wants to add, change, remove, or redesign a feature in an Autorunne-backed repo. Read Autorunne state first, identify the safe change boundary, ask only necessary questions, then implement and verify the smallest safe slice.
Skill Claude CodeCodex
Review pending git changes and create senior-quality commits. Groups unrelated changes into separate logical commits, writes Conventional Commits messages that explain the why, and executes them — all on a tight token budget. Use when the user says "commit", "commit my changes", "commit like a pro", "ship this", or…
JeromeWang6066/syllabus-reader-skill
Skill Claude CodeCodex
This skill should be used when the user wants to interpret, parse, or summarize a university course syllabus from any country or institution. It handles uploaded files (PDF, DOCX) or URLs pointing to course syllabus pages. The skill extracts key information: basic course info, schedule, teaching content, grading…
Skill Claude CodeCodex
Static call-path engine. Answers "what calls what?" from structure, not execution. Use before reading source files — it is faster and token-cheaper than grep-and-read.
King-GD/vue-nuxt-best-practices
Skill Claude CodeCodex
57 performance optimization rules for Vue3 and Nuxt4 applications. Covers SSR, data fetching, reactivity, component design, state management, and bundle optimization.
rumi-run/ai-truthfulness-rules
Skill Claude CodeCodex
Use when answering strategic, executive, analytical, research, coding, business, financial, compliance, or high-impact questions where the AI must avoid generic trendy advice, separate facts from assumptions, challenge weak premises, compare options fairly, and make evidence, risks, uncertainty, and human verification…
Skill Claude CodeCodex
Exports the current chat session to a clean markdown file. Reconstructs the visible conversation from context — user messages, assistant responses, code blocks, tool output — formatted as readable .md. Use when user says "export chat", "save this conversation", "export to markdown", or invokes /iceage-export. Accepts…
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: