Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,002 indexed, measured the same four ways as everything else here.
Use when building, running, or testing an iOS app on a simulator — claims a leased simulator through simlease so parallel AI agents never collide, labels the simulator window with the task name, and releases it when done.
Fetch academic journal / blog RSS feeds, rank new items against the user's research interests, write a daily markdown digest (optionally into an Obsidian vault), and optionally email it. Use when the user says "/academic-journal-rss ...", asks to set up their RSS feeds, add a feed, or run today's digest.
Creating interactive data visualisations using d3.js. This skill should be used when creating custom charts, graphs, network diagrams, geographic visualisations, or any complex SVG-based data visualisation that requires fine-grained control over visual elements, transitions, or interactions. Use this for bespoke…
Build or update UI screens, dashboards, forms, modals, and tables. Use when the subtask is primarily a frontend implementation — page layout, component composition, responsive design, interaction polish, or UI state wiring to existing APIs.
Process learning materials into structured Obsidian atomic notes with roadmaps, MOCs, and double-links. Auto-generate study vaults from PDFs, Markdown, Word, PowerPoint, and more with AI-powered note-taking, knowledge linking, and deep research. Supports English and Chinese output. Use when the user wants to build a…
Force the laziest solution that actually works — the simplest, shortest, most minimal. Use on ANY coding task (writing, adding, refactoring, fixing, reviewing, designing code, choosing libraries or dependencies). Question whether the code needs to exist at all (YAGNI), reuse before writing, stdlib and native platform…
Autonomous Claude agent building MCP tools and infrastructure. Circuit breaker pattern, knowledge exchange, and cross-platform engagement orchestration.
Generate a minimal, effective project-level CLAUDE.md for the current repository. Use when initializing a new project, onboarding contributors, or auditing an existing project config — only includes what the agent cannot discover from the code.
Setup Sentry AI Agent Monitoring in any project. Use this when asked to add AI monitoring, track LLM calls, monitor AI agents, or instrument OpenAI/Anthropic/Vercel AI/LangChain/Google GenAI. Automatically detects installed AI SDKs and configures the appropriate Sentry integration.
Use when the user wants Agent Office to route work to the right employee, coordinate multiple employee roles, act like an office manager, or respond as a named employee. Triggers include requests to triage work, decide who should handle something, simulate the office team, delegate across roles, use the employee…
USE FOR: Verifying technical claims, comparing options, and investigating unfamiliar libraries/APIs/tools with cited, confidence-rated evidence. DO NOT USE FOR: implementation, opinion without evidence, or tasks better served by a narrower repo-specific skill (e.g. data-platform, dev-platform-workflow).
Fork and template gotchas (env import, routes, typegen, forms, D1, Turbo, HMR, new DO packages). Use when working on apps/web or durable-objects, or when behavior diverges from this stack’s conventions.
Design practical, production-grade editable vector icons and icon systems with clean geometry, strong recognition, scalable SVG structure, and restrained visual polish. Use when the user asks to create, improve, audit, or export app icons, product icons, system icons, feature icons, SVG icons, Figma-ready icons, icon…
Migrate and rewrite Hyprland configs from the old v0.54 hyprlang (.conf) syntax to the new v0.55 Lua (hyprland.lua) API. Use when converting an existing hyprland.conf, writing new Hyprland Lua config, explaining what changed between 0.54 and 0.55, or troubleshooting a config that broke after upgrading. Covers every…
Scans Android app projects for Google Play rejection and enforcement risk before submission. Reads source directly with no back-and-forth. Auto-detects vibe coder vs developer mode, supports Flutter/React Native/native Android, detects mid-build state and asks whether to run a submission audit or build checklist.…
Expert skill for developing TradingView Pine Script v6 indicators. Use this skill whenever the user asks to build, debug, refactor, or extend a Pine Script indicator — especially those involving SMT divergence, swing detection, multi-asset security calls, FVG/OB logic, session markers, ATR/ADR/CDR dashboards, or any…
★not rated 12 7mo agoA108 tokens
originalMIT
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: