codex
Codex skills are built for OpenAI's coding-agent workflow across the terminal, repository context, and tool-driven implementation tasks. Expect software engineering, debugging, refactoring, and research helpers that pair well with an agent editing files and running commands.
Skills compatible with codex
agent-md-refactor
by softaworks/agent-toolkit
Refactor bloated agent instruction files (AGENTS.md, CLAUDE.md, COPILOT.md, etc.) to follow progressive disclosure principles - keeping essentials at root and organizing the rest into linked, categorized files.
read-arxiv-paper
by karpathy/nanochat
Source details, install context, and public review data are available on the full page.
swiftdata-pro
by twostraws/swiftdata-agent-skill
Write and review SwiftData code for correctness, modern API usage, and adherence to project conventions. Report only genuine problems - do not nitpick or invent issues.
writing-clearly-and-concisely
by softaworks/agent-toolkit
Write with clarity and force. This skill covers what to do (Strunk) and what not to do (AI patterns).
commit-work
by softaworks/agent-toolkit
Source details, install context, and public review data are available on the full page.
crafting-effective-readmes
by softaworks/agent-toolkit
READMEs answer questions your audience will have. Different audiences need different information - a contributor to an OSS project needs different context than future-you opening a config folder.
gemini
by softaworks/agent-toolkit
NEVER use --approval-mode default in background or non-interactive shells (like Claude Code tool calls). It will hang indefinitely waiting for approval prompts that cannot be provided.
humanizer
by softaworks/agent-toolkit
Source details, install context, and public review data are available on the full page.
m01-ownership
by zhanghandong/rust-skills
Source details, install context, and public review data are available on the full page.
qa-test-planner
by softaworks/agent-toolkit
A comprehensive skill for QA engineers to create test plans, generate manual test cases, build regression test suites, validate designs against Figma, and document bugs effectively.
session-handoff
by softaworks/agent-toolkit
Creates comprehensive handoff documents that enable fresh AI agents to seamlessly continue work with zero ambiguity. Solves the long-running agent context exhaustion problem.
c4-architecture
by softaworks/agent-toolkit
Generate software architecture documentation using C4 model diagrams in Mermaid syntax.
codex
by softaworks/agent-toolkit
GPT-5.2 Advantages : 76.3% SWE-bench (vs 72.8% GPT-5), 30% faster on average tasks, better tool handling, reduced hallucinations, improved code quality. Knowledge cutoff: September 30, 2024.
command-creator
by softaworks/agent-toolkit
This skill guides the creation of Claude Code slash commands - reusable workflows that can be invoked with /command-name in Claude Code conversations.
daily-meeting-update
by softaworks/agent-toolkit
Generate a daily standup/meeting update through an interactive interview . Never assume tools are configured—ask first.
dependency-updater
by softaworks/agent-toolkit
Smart dependency management for any language with automatic detection and safe updates.
domain-name-brainstormer
by softaworks/agent-toolkit
This skill helps you find the perfect domain name for your project by generating creative options and checking what's actually available to register.
m05-type-driven
by zhanghandong/rust-skills
Source details, install context, and public review data are available on the full page.
marp-slide
by softaworks/agent-toolkit
Create professional, visually appealing Marp presentation slides with 7 pre-designed themes and built-in best practices.
meme-factory
by softaworks/agent-toolkit
Create memes using the free memegen.link API and textual meme formats.
professional-communication
by softaworks/agent-toolkit
This skill provides frameworks and guidance for effective professional communication in software development contexts. Whether you're writing an email to stakeholders, crafting a team chat message, or preparing meeting agendas, these principles help you communicate clearly and build professional credibility.
reducing-entropy
by softaworks/agent-toolkit
More code begets more code. Entropy accumulates. This skill biases toward the smallest possible codebase.
ship-learn-next
by softaworks/agent-toolkit
This skill helps transform passive learning content into actionable Ship-Learn-Next cycles - turning advice and lessons into concrete, shippable iterations.
skill-judge
by softaworks/agent-toolkit
Evaluate Agent Skills against official specifications and patterns derived from 17+ official examples.