Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 272,426 indexed, measured the same four ways as everything else here.
Diagnose and repair Claude Desktop Mac third-party inference / 3p / DeepSeek-style Claude Code setups for best-effort parity with first-party Claude Code. Use when users mention Claude Code Mac app developer mode, Claude Desktop 3p, third-party API providers, DeepSeek V4 Pro/Flash, bypassPermissions not working…
A method for reviewing code, bugs, diffs, branches, and pull requests. A diff is the set of changes between two versions of code, and a pull request is a proposed change submitted for review.
Full-cycle software development agent: plans, builds, tests, lints, fixes bugs, and writes production-grade README docs. ALWAYS use this skill when the user wants to: build or scaffold a new project, add features to existing code, fix bugs, improve code quality (lint, format, refactor), write or improve a README, add…
Drive IDA Pro through the IDA Pro MCP like a senior reverse engineer: don't just narrate decompiler output, transform the database. Use this whenever the user is reverse engineering, analyzing malware, working a crackme or CTF, or doing binary/firmware analysis with IDA Pro over an MCP connection (mrexodia/ida-pro-mcp…
Coordinate Supervisor, Worker, and Reviewer work through Auspex when a brief names an Auspex task, when handing work to another agent, or when reviewing shared task progress. Auspex remains the task state source; this skill is only the operating playbook.
A review tool for checking whether another coding-agent skill is well designed. It examines how the skill is triggered, how its instructions are organized, and which parts can be removed without changing its behavior.
Archive and export historical X/Twitter account timelines from a public handle using a bundled bird-search backend, browser/session cookies, and optional local proxy. Use when the user asks to collect, export, archive, or analyze tweets/posts from a specific X/Twitter account over a date range, especially when they…
Organize user-scoped CLEC episodes into traceable Traditional Chinese Obsidian pages. Use when Codex must group X, pCloud, Google Drive, Bilibili, Odysee, and RSS or Podcast sources by five-digit episode number; obtain and review transcripts through media-transcript; clean readable transcripts with the confirmed CLEC…
Use Chutes.ai from Hermes for model discovery, routing, account/API-key guidance, and OpenAI-compatible inference. Prefer the live models endpoint for current availability and capabilities.
Write, finalize, or clean up reader-facing marketing and long-form copy (landing pages, sales pages, e-books, reports, case studies, product and email copy, founder notes) so it reads like a specific human wrote it and says something worth reading. Use when asked to humanize, de-slop, make less AI-sounding, rewrite…
Use when the user asks to critique, peer-review, appraise, assess the credibility of, or evaluate the methodology, statistics, or bias of a single dental or oral-health research paper. Use for RCTs including split-mouth, cluster, and crossover designs; observational studies; diagnostic accuracy studies; systematic…
This skill should be used when the user asks to "upload to App Store", "manage App Store Connect", "update app metadata", "upload screenshots", "set app description", "set keywords", "manage TestFlight", "add beta testers", "check app reviews", "respond to reviews", "submit for review", "set app pricing", "create…
Turn a contested question, research brief, technical choice, or high-impact decision into a source-grounded interactive evidence map. Use when an agent must preserve support, contradiction, qualification, and missing evidence; make every evidence edge traceable to a dated source region; pressure-test a conclusion; or…
Create frontends, posters, dashboards, and web UIs rooted in Bauhaus and Swiss International Typographic Style (Internationale Typografische Stil) design principles. Use this skill when the user mentions Bauhaus, Swiss design, International Typographic Style, grid systems, Josef Müller-Brockmann, Max Bill, Jan…
Meta-skill that audits health of the entire product launch engine, identifies broken links between phases, and generates improvement roadmaps. Use when: system health, skill audit, launch engine health, are our skills working together, process audit, workflow health check.
When the user wants to apply to startup accelerators, incubators, or fellowship programs. Also use when the user mentions "YC application", "Techstars", "accelerator", or "apply to programs".
A music-playing skill that searches several online sources and controls playback through the mpv media player. It supports requests such as finding songs, pausing, continuing, skipping, changing volume, and repeating a track.
Create, improve, optimize, and port games for the Sega 32X (Sega Mars) using Chilly Willy's 32XDK toolchain and the DOOM 32X Resurrection (d32xr) codebase as reference. Use whenever the user wants to port a game (DOS, Genesis, PICO-8, HTML5, or any platform) to the 32X, build or debug a homebrew 32X ROM, or make a 32X…
Write Java microbenchmarks with JMH (Java Microbenchmark Harness) that produce trustworthy numbers — not numbers distorted by JIT dead-code elimination, constant folding, insufficient warmup, or single-fork JIT contamination. Use this skill whenever the user writes @Benchmark, mentions JMH, microbenchmark, throughput…
A manually triggered writing guide that turns notes, debugging records, design summaries, code snippets, or rough drafts into Chinese technical blog posts. It first identifies and evaluates possible article topics before writing.
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: