3.4K skills · sorted by relevance
Diagnose Codex behavior within BB, including question cards, MCP requests for user input or approval, Computer Use app access, model availability, service tiers, session options, and persistent goals, using thread and provider controls.
List available Codex skills and install selected ones from a curated collection, experimental listings, or a specified GitHub location. It also supports private repositories and marks skills that are already installed.
SUPERSEDED by /claudex-loop (formerly /crucible; adds a Phase 0 research/recon pass + rebuilt interview) — prefer that skill unless you explicitly want this one. Two-act plan hardening. ACT 1 (you ↔ Claude) — Claude interviews you relentlessly about a plan or design, one question at a time, recommending an answer for each and exploring the codebase when it can answer itself, until every branch of the decision tree is resolved. ACT 2 (Claude ↔ Codex) — Claude writes the locked plan to PLAN.md and OpenAI Codex adversarially reviews it in a read-only sandbox (VERDICT:APPROVED/REVISE), Claude revises and re-submits to the SAME Codex session until APPROVED or a MAX_ROUNDS cap, then you sign off before any code. Use when the user says "/grill-me-codex", "grill me then have codex review", "grill me and stress-test the plan", "interview me about this plan then get a second model on it", or is about to build something high-stakes (auth, schema, concurrency, migrations, payments) and wants both alignment AND a cross-model sanity check before implementation. Builds on Matt Pocock's grill-me (MIT). For the docs-aware variant use /grill-with-docs-codex; if you already have a plan and want only the Codex review use /codex-review. NOT for reviewing already-written code (use /codex:review) and NOT for trivial changes.
The English summary is being prepared. Showing the original description.
Delegate a coding task to the OpenAI Codex CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Codex — phrasings like "have Codex do X", "delegate this to Codex", "run it through Codex", or "use Codex to implement/fix/refactor" — or to run a queue of coding tasks through Codex while staying the reviewer. Prefer it over a one-shot Codex forwarder (such as the codex-rescue agent) when the user will review the diff and commit it themselves. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
The English summary is being prepared. Showing the original description.
Run an automated codex⇄Claude debate to consensus — no round cap, no deadlock exit. Two explicit subcommands. `review` (also the bare/back-compat default) — codex (reviewer) critiques the current diff and a Claude subagent (author) fixes/disputes, looping until they agree. `answer` — Claude and codex each answer a freeform prompt in parallel, then cross-check until they agree, and a unified answer is returned. Use when the user types `/codex-debate`, asks to "have codex review this", "run the codex debate", "review this PR with codex", "argue this with codex until you agree", or passes a question to "have Claude and codex debate/answer until they agree".
The English summary is being prepared. Showing the original description.
Provides Codex CLI delegation workflows for complex code generation and development tasks using OpenAI's GPT-5.3-codex models, including English prompt formulation, execution flags, sandbox modes, and safe result handling. Use when the user explicitly asks to use Codex for complex programming tasks such as code generation, refactoring, or architectural analysis. Triggers on "use codex", "delegate to codex", "run codex cli", "ask codex", "codex exec", "codex review".
The English summary is being prepared. Showing the original description.
Delegate feature development, large code refactors, and pull request reviews to Codex, Claude Code, or OpenCode as background workers. Use isolated project checkouts, monitor progress, and arrange completion or failure notifications.
Delegate feature development, code refactoring, and pull request reviews to OpenAI Codex CLI. The skill also covers monitoring long tasks and fixing multiple issues in parallel using separate Git working directories.
Analyze Claude Code and Codex usage logs to identify spending drivers, including cache usage, model choices, reasoning, and long sessions. Receive evidence-backed recommendations and hypothetical savings estimates to help decide which changes to try.
Update Codex's pinned V8 and rusty_v8 versions, synchronize build settings and checksums, and validate a release candidate. If validation fails, investigate upstream changes and adjust the affected build files to restore a working build.
Find and install Codex skills from a curated catalog or a GitHub path. Check which skills are already installed, explore experimental options, and add skills from private repositories when credentials are available.
Launch the @remotion/player example app locally and open it in the Codex in-app browser. The workflow prepares dependencies, builds the project, starts the development server, and reports its URL and whether it was newly started or already running.
Launch the local Remotion Convert app and open it in the Codex in-app browser to inspect its interface. The workflow prepares dependencies, builds the project, starts the development server, and reports the actual local URL.
Cancel an active PUA loop from Codex CLI using an alias for the corresponding Claude Code command. The workflow cleans loop state and worktree references, records the cancellation, and requires execution evidence before claiming completion.
Use Codex to define strategic direction, organizational structure, and P9 management boundaries through the P10/CTO protocol. This alias provides a Codex entry point corresponding to the Claude Code command `/pua:p10`.
Turn specialized knowledge and repeatable workflows into Codex skills. Follow guidance for defining usage examples, writing SKILL.md, organizing scripts and reference materials, validating the package, and improving existing skills through practical use.
Create clickable links that open conversations, files, folders, or settings directly in apps such as Codex, Cursor, and VS Code. Check supported formats, format links for Slack, and provide alternatives when direct links are unavailable.
Check a project's Codex infrastructure, fix missing dependencies, script permissions, and configuration errors, then repeat the check until failures are resolved. Receive a summary of repairs and any remaining optional-feature warnings.
Get independent code reviews of uncommitted changes, branch differences, or individual commits using Codex or Antigravity. Receive findings with severity, locations, impact, and suggested corrections, and compare where the two reviewers agree or differ.
Turn an idea, existing code, or a previous Codex conversation into a runnable OpenAI Agents SDK app. Supports local verification, focused evaluations of agent behavior, and local deployment through the Deployment Manager.
Turn API documentation, SDKs, or existing scripts into reusable command-line tools for Codex. Build focused read and write commands, stable JSON output, authentication checks, and a companion skill explaining how future sessions should use the tool.
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.
Bridge `/speckit.*` commands to `/vibe` execution guidance in Codex. A PowerShell router preserves the familiar command model and leaves official spec-kit prompts unchanged, helping carry existing workflows into `/vibe-first` execution.
Launches and manages the local OpenAI Codex CLI as a non-interactive coding sub-agent via ChatGPT Pro 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.