Loading...
Loading...
Found 480 Skills
Turn the current Codex thread into a coordination thread that routes per-branch implementation work to durable reusable child threads without worktrees.
Spawn and manage multiple Codex CLI agents via tmux to work on tasks in parallel. Use whenever a task can be decomposed into independent subtasks (e.g. batch triage, parallel fixes, multi-file refactors). When codex and tmux are available, prefer this over the built-in Task tool for parallelism.
Use OpenAI's Codex CLI as an independent code reviewer to provide second opinions on code implementations, architectural decisions, code specifications, and pull requests. Trigger when users request code review, second opinion, independent review, architecture validation, or mention Codex review. Provides unbiased analysis using GPT-5-Codex model through the codex exec command for non-interactive reviews.
Have Codex CLI review uncommitted code changes. Claude Code then fixes valid issues and rebuts invalid ones. Codex re-reviews. Repeat until consensus. Codex never touches code — it only reviews.
Use when user wants to execute long-running tasks that require multiple sessions to complete. This skill manages task decomposition, progress tracking, and autonomous execution using Codex non-interactive mode with auto-continuation. Trigger phrases include autonomous, long-running task, multi-session, 自主执行, 长时任务, autonomous skill.
AI-powered code review via the OpenAI Codex CLI. This skill should be used when reviewing branch diffs before merging a PR, auditing uncommitted changes during development, inspecting a specific commit, performing custom-scoped reviews, or whenever changes touch security-sensitive paths or exhibit risky patterns.
Hand off a task to Codex CLI for autonomous execution. Use when a task would benefit from a capable subagent to implement, fix, investigate, or review code. Codex has full codebase access and can make changes.
Get a deep critical review of research from GPT via Codex MCP. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
Self-directed iterative research skill for Codex that continuously cycles through modify, verify, retain or discard, and repeat until a measurable goal is reached.
Run Codex code review against the current branch, fix only the review comments that are still valid for the current codebase, and leave invalid comments unchanged.
Use a persistent Codex sidecar thread from the local `codex-sidecar` CLI for design review, implementation advice, debugging, and context-preserving follow-up questions while keeping the current agent as the primary executor.
Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission. Codex designs ablations from a reviewer's perspective, CC reviews feasibility and implements.