3.3K skills · sorted by relevance
Test omo Codex Light edition in an isolated environment using real Codex and a local mock model. Verify installation, plugin hooks, and terminal startup, with captured evidence and no calls to a real model API.
Reproduce and fix LazyCodex or Codex defects in a temporary workspace. Verify the change with regression tests and real usage, then deliver an upstream Codex pull request or a LazyCodex issue containing the tested patch.
Summarize local CodexBar cost logs for Codex or Claude by model. View a representative model from the latest daily entry or a full cost breakdown, with results available as text or JSON.
Forward tasks from Claude Code's rescue subagent to Codex through a helper script. This internal skill handles model and effort options, fresh or resumed runs, and write access, then returns the helper's output unchanged.
タスク着手時に codex にリードしてもらうワークフロー。codex に設計/方針を主導（リード）させ、その方針に沿って Claude が実装し、実装後は codex で設計適合・実装正当性・敵対的（red team）の 3 観点でレビューする。余っている codex トークンを積極的に消費したい時に使う。「codexにリードしてもらって」「設計から codex に任せて」「タスクを codex 主導で」「codex-lead」「/codex-lead」で発火。
The English summary is being prepared. Showing the original description.
Checks LazyCodex and Codex CLI installations against current source code, inspecting versions, settings, plugin files, and runtime behavior. Produces an evidence-backed health report with suggested fixes while leaving the installed setup unchanged.
Investigate LazyCodex and Codex bugs using reproduction results and source code. Identify the responsible repository, then prepare or submit an English GitHub report with evidence, likely causes, fix guidance, and a verification plan.
Add Codex as the agent that plans tasks and coordinates tools in NanoClaw. Choose it for individual groups alongside Claude, with conversation history and session resume using a ChatGPT subscription or OpenAI API key.
Connect an Expo project to the Codex app Run button by creating a local launch script and action configuration. Start the development server from the app, view its logs, and optionally add platform-specific launch buttons.
Get guidance on Codex, OpenAI APIs, and ChatGPT Work using official documentation with citations. Use it to investigate settings and errors, compare models, plan migrations, or work on prompts and API integrations.
Codex CLIと相談するスキル。 ユーザーが「codexと相談して」「codexに聞いて」「codexにレビューしてもらって」と言った時に使用する。 現在の会話コンテキストに基づいてCodex CLIにプロンプトを送り、結果を要約して報告する。 「codexはAstraで」「effortはhighで」のようにCodexのmodelやreasoning effortを指定された時は、そのmodelとeffortで実行する。
The English summary is being prepared. Showing the original description.
Find guidance on Codex settings, pricing, and OpenAI products and APIs using current official documentation. Get cited answers for setup, troubleshooting, model comparisons, migration planning, and prompt changes, with uncertainty stated when sources are inconclusive.
Configure Codex CLI to connect through OmniRoute on Linux, macOS, or Windows. The workflow detects the operating system and shell, creates configuration files and seven profiles, sets environment variables, and verifies the setup.
Get source-backed guidance on OpenAI products, APIs, and Codex from official documentation. Use it to compare models for a task, understand configuration options, or plan focused model and prompt updates while preserving an explicitly requested target model.
Generate a PUA KPI and performance report card from Codex CLI. This command alias loads pua-pro and provides a Codex equivalent of the Claude Code /pua:kpi command through $pua-kpi.
Claude Code（.claude）と Codex（.codex / .agents / AGENTS.md）に分裂したエージェント設定を、 実ファイル1つ + symlink と双方向変換で単一化・同期するスキル。 実ファイルをどちら側に置くか（symlink の向き）は共通設定 source で選べる。 プロジェクト単位の導入ウィザード、既に分裂しているリポジトリを危険度の低い順に解決する手順、 片方しか無いリポジトリへもう片方を生成する scaffold、書き換え前のバックアップと復元、常駐の管理を含む。 「エージェント設定を同期して」「.codex と .claude がずれている」「Codex でも同じスキルを使いたい」 「AGENTS.md と CLAUDE.md を一本化したい」「MCP を Codex でも使えるようにして」 「サブエージェントを Codex 側にも作って」「設定の分裂を解消して」「元に戻して」 「agents-sync」「同期デーモン」などと言われたら使う。 Keywords: agents-sync, エージェント設定同期, .claude, .codex, .agents, AGENTS.md, symlink 統合, symlink の向き, 実ファイルを置く側, 双方向同期, scaffold, 分裂解消, MCP 同期, hooks 同期, サブエージェント同期, バックアップ, 復元, fswatch, launchd, 常駐デーモン
The English summary is being prepared. Showing the original description.
Check skills before distributing them to Codex or Cursor. Identify unsupported metadata fields, Claude-specific variables in shell examples, and inconsistencies between source skills and their installation copies using the project's compatibility checker.
Present results returned by a Codex helper while preserving findings, severity, file references, and uncertainty. This internal guidance also covers reporting edited files, failed runs, and setup requirements, with user confirmation before fixing review findings.
Delegate coding, analysis, refactoring, or reviews from Claude Code to Codex CLI. The skill explains unattended execution, permission settings, output capture, parallel tasks, and independent checks of changed files and test results.
Complete the PUA survey through a guided flow in Codex CLI and save responses to a local JSON file. This alias provides the equivalent of Claude Code’s /pua:survey command without sending answers anywhere.
codex exec review を基本に、必要なら codex exec を使ってコード変更のレビューを依頼し、指摘事項を報告する。通常 / 厳しめ (--strict) / 敵対的 (--adversarial、実装を壊しにいく red team) の 3 モードを持つ。「codexでレビューして」「codex-review」「/codex-review」「敵対的にレビューして」で発火。Codex 単体での単独レビュー用途。複数エージェント並行レビューは cross-review、差分ではなくコードベース全体の監査は audit を使う。
The English summary is being prepared. Showing the original description.
Save project context and task handoffs as local Markdown documents that Claude, Codex, and other agents can share. The skill guides searching prior knowledge, recording evidence and remaining work, and checking the shared memory vault for structural problems.
Resume unfinished Codex work in Muse Code by reading a local session log selected by the user. Recover the latest request, decisions, and pending changes, then check current files and continue the task.
Delegate code analysis and implementation to Codex CLI without an interactive session. The skill reads ordered output events, extracts the final agent response, and reports errors, with a read-only sandbox used by default.