3.4K skills · sorted by relevance
Launches and manages the local OpenAI Codex CLI as a non-interactive coding sub-agent via ChatGPT OAuth, never API keys. Use to delegate coding tasks to Codex, run codex exec, generate or refactor code, or get a Codex code review; phrases like 'codex', 'run codex', 'codex exec', 'delegate to codex'.
The English summary is being prepared. Showing the original description.
codex:codex-rescueエージェントを起動する各スキル(codex-review-loop・codex-consult等)が共有する、ハング防止付きの起動・監視・再試行契約の正本。内部専用でユーザーが直接使うものではない。
The English summary is being prepared. Showing the original description.
Codex が設計・実装を担い、Claude が要件確定・成果物の検証・反復・commit/push を管理する。「codex に書かせて」「codex メインで実装」「codex-drive」で発火。大きめの機能・移植・プロトコル実装向け。余剰トークンを厚く使う運用も選べる。
The English summary is being prepared. Showing the original description.
Add one optional Codex critique to a decision draft produced by council. With explicit consent to send the draft to OpenAI, examine weak conclusions, missing failure scenarios, and overlooked dissent before the user makes the final decision.
Help Codex respond to automatic warnings about comments after code edits. It explains when the checker runs and directs Codex to fix the flagged comment or explain it before continuing with other work.
View and configure status displays for Codex CLI and OMX workflows. Show the model, context usage, active modes, worker counts, and turns, with compact or detailed presets, live updates, and JSON output for scripts.
Diagnose oh-my-codex installation and skill discovery problems by checking configuration, hooks, plugin caches, and optional Team runtime checks. Produce an evidence-based report and carry out confirmed repairs with user approval, then verify the results.
Install or refresh oh-my-codex for a user or a specific project. Choose installation settings, preview file changes, manage how existing instructions are updated, and check the resulting files and configuration with diagnostic commands.
Create a saved plan for multiple goals in a repository, then execute it step by step with Codex goal mode. Track progress, verification evidence, review results, and blockers before marking the plan complete.
Find available Codex skills and install selected ones from a curated list or a GitHub repository. Supports public and private repositories, marks skills already installed, and lets you specify source paths and installation destinations.
Investigate stalled, retrying, or failed Symphony runs by connecting Linear issue identifiers with Codex sessions. Trace log events in time order, identify the failing stage, and collect evidence for the probable cause.
Guide a macOS app release through versioning, signing, Apple notarization, update feed checks, and Homebrew updates. Includes CodexBar release scripts, published asset verification, and preparation of the next unreleased version.
Set up or run repeated verification in Codex with explicit checking commands and stopping conditions. This alias corresponds to Claude Code’s `/pua:loop` command and requires command output as evidence before reporting completion.
Check active PUA agents and teams from Codex CLI using an alias for the Claude Code status command. Review process IDs and record lifetimes when available, alongside stale records.
Style materials to match the OpenAI and Codex look using specified colors and fonts. Apply distinct formatting to headings, body text, code, and shapes, with fallback fonts when the preferred ones are unavailable.
Reviews recent Codex conversations to identify coding habits, strengths, and recurring challenges. Produces a prioritized growth report with practical next steps and relevant HackerNews reading, then delivers it to your Slack direct messages.
Generate and edit transparent PNG ornaments, game sprites, emblems, and interface graphics with built-in Codex image generation. Includes transparency checks, saved prompts, and optional integration into an existing project with verified asset copies.
Turn five collected UI references into five original landing pages with distinct brands, copy, and imagery. Each page gets its own Codex task and workspace, with build checks, a source commit, and private deployment through Sites.
Compare five Codex execution setups on Terminal-Bench 4.0 under matching conditions. The skill covers benchmark configuration, separate verification environments, image preparation, and result interpretation to help identify misleading scores caused by setup errors.
Audit custom subagents, the specialized assistants used by Claude Code and Codex. Check whether definitions load, identify overlapping roles, review model choices and tool access, and receive scores with prioritized fixes and optional confirmed edits.
Retrieve the current Codex session ID so you can find its records in Weave Router logs and dashboards. The ID is returned in a copyable format for investigation or support.
Clear the model pin, a setting that holds a session to one model, in the current Codex session through Weave Router. The session continues within the same turn, and the router's response is reported.
Pin the current Codex session to a specific model through Weave Router by providing its model ID. The skill applies the pin, continues the same turn, and reports the router's response.
Understand how Codex Rules adds project instructions and file-specific rules to agent context. Check supported rule locations, when rules are applied, and environment settings for modes, sources, and text limits.