Claude to Codex

Converts any Claude skill into a Codex-compatible skill. Searches the Claude skill marketplace by name, fetches the SKILL.md, rewrites Claude-specific tool references, generates agents/openai.yaml, and writes output to .codex/skills/. Use when asked to convert, port, or transform a Claude skill for use in Codex. Invoke with $claude-to-codex <skill-name>.

15 stars 4 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add padmilkhandelwal/convert-claude-to-codex-skill --skill claude-to-codex

Manual install

git clone --depth 1 https://github.com/padmilkhandelwal/convert-claude-to-codex-skill.git /tmp/convert-claude-to-codex-skill
mkdir -p ~/.claude/skills
cp -r /tmp/convert-claude-to-codex-skill/. ~/.claude/skills/claude-to-codex

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# claude-to-codex

Transform any Claude skill into a Codex-compatible skill in one command.

---

## Usage

```
$claude-to-codex <skill-name> [flags]
```

### Flags

| Flag | Effect |
|---|---|
| `--global` | Install to `~/.codex/skills/` instead of `.codex/skills/` |
| `--dry-run` | Print the transformed SKILL.md without writing any files |
| `--no-yaml` | Skip generating `agents/openai.yaml` |
| `--overwrite` | Replace an existing skill without prompting |
| `--multi-agent` | Use explorer + worker sub-agents for Steps 3–6 (see below) |
| `--test` | After writing files, run skill-creator validation on the output |

### Examples

```bash
$claude-to-codex git-commit
$claude-to-codex docx --global
$claude-to-codex "write commit" --dry-run
$claude-to-codex docx --multi-agent
$claude-to-codex docx --test              # convert + validate output
$claude-to-codex docx --dry-run --test    # preview + validate without writing
```

---

## Execution mode

**Default (single agent):** You run all 8 steps yourself, in order.
Fast, simple, best for most single conversions.

**`--multi-agent`:** Steps 3–4 go to an explorer agent, Steps 5–6 to a
worker agent. Use for large skills (500+ lines) or bulk conversions.

**`--test`:** Adds Step 7b validation after writing. Inline by default.

**`--test --multi-agent`:** Step 7b spawns an independent tester sub-agent
that reads the output cold — no context of how it was written. Strictest
validation mode.

Read the full skill on GitHub

Details

Skill name: claude-to-codex
Repository: padmilkhandelwal/convert-claude-to-codex-skill
License: MIT
Repo updated: 5 May 2026

FAQ

What does the Claude to Codex skill do?

How do I install the Claude to Codex skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add padmilkhandelwal/convert-claude-to-codex-skill --skill claude-to-codex. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Claude to Codex popular?

It lives in padmilkhandelwal/convert-claude-to-codex-skill, which has 15 GitHub stars and 4 forks.

Related skills

Rss Agent

shiquda/rss-agent

A powerful RSS subscription manager and reader. Use it to (1) Import/export OPML files, (2) Manage RSS feeds (add, remove, categorize), (3) Validate feed connectivity, (4) Schedule periodic updates via cron, (5) Fetch and summarize articles with a progressive disclosure approach.

AI, LLMs & Agents

Agents Md Generator

Eriemon/agents-md-generator

Use when creating, updating, compressing, reviewing, or verifying AGENTS.md and other AI coding-agent rules; when a managed root AGENTS.md is missing, malformed, stale, or version-incompatible; when the user explicitly mentions AGENTS.md, agent rules, or scoped AGENTS.md; when a managed skill README needs a functional illustration set; or when a request about the current workspace, repository, or work folder is a planning request and therefore requires a root AGENTS.md check first.

AI, LLMs & Agents

Math Modeling

Y-love-han/math-modeling-skill

Execute and audit complete mathematical modeling competition workflows with the evidence-first mmflow runtime as the single source of truth, plus adaptive data analysis, model selection, validation, publication, presentation, privacy, reproducibility, and compliance templates. Use for 数学建模、数模、赛题、CUMCM、MCM/ICM、GMCM、MathorCup、APMCM、深圳杯 or any contest task involving problem selection, data analysis, model construction, validation, paper writing, review, packaging, defense preparation, auditing, or workflow recovery.

AI, LLMs & Agents

Poggioai Msc Claude

PoggioAI/PoggioAI_MSc-claude

pAI/MSc research pipeline: hypothesis to paper in ≤10 steers. Runs persona debate, adversarial lit review, parallel theory+experiment tracks, and editorial quality gates.

AI, LLMs & Agents

Math Modeling Single

Yoki-cmd/math-modeling-single

数学建模论文生成器。给一道数学建模竞赛题，按国赛标准四阶段流程（策略→求解→写作→审查）端到端生成完整论文（LaTeX），含摘要/问题重述/问题分析/模型假设/符号说明/模型建立与求解/模型检验/评价改进推广；用 mermaid-cli/Python 作矢量流程图、MATLAB MCP（不可用回退 Python）跑真实数据，自带国赛标准 LaTeX 模板。Triggers on "数学建模", "数模", "建模论文", "math modeling", "国赛", "美赛", "CUMCM", "MCM"，或用户显式调用 /math-modeling-single。

AI, LLMs & Agents

Korean Humanizer

dotoricode/korean-humanizer

한국어로 작성된 AI 생성 텍스트에서 "AI 티"가 나는 표현을 걷어내 사람이 쓴 것처럼 자연스럽게 다듬는 skill. 사용자가 "한국어 humanizer", "AI 티 빼줘", "사람처럼 써줘", "자연스럽게 다듬어줘", "번역체 고쳐줘", "한국어 AI 냄새 제거", "humanize Korean", "AI 티 제거" 등을 언급할 때 반드시 사용. 외부(이메일, LinkedIn, 블로그, YouTube 스크립트, 뉴스레터, 마케팅 카피)로 나가는 한국어 AI 생성 텍스트 전반에 사용한다. 의미를 바꾸지 않고 표현만 다듬는 것이 목적. 호출 결과는 `Humanized` 교정문과 `주요 변경 (최대 5개)` 두 섹션의 Markdown 문서로 반환한다. 영어 텍스트, 단순 오탈자 교정, 내부 메모 / 기술 문서 / 법률 문서에는 사용하지 않는다.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.