메뉴
Cross-model second opinion from OpenAI Codex — `codex-run advise --context` reviews the current session, or pipe a brief. Triggers on "ask codex", "codex review", "second opinion", or the "Cross-model review" rules.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Delegate a task's implementation wholesale to OpenAI Codex (`codex-run work`) — the whole requirements document in one long autonomous run — keeping policy, orchestration, and acceptance in the main loop. Use at the Implement step of the Orchestrator loop, for any multi-part build.
The mechanic-level evaluation toolkit — apply the 5-Component Framework (Clarity, Motivation, Response, Satisfaction, Fit) to any individual mechanic. Use when designing or evaluating a single mechanic, reviewing whether a feature pulls its weight, debugging why a specific action feels off, comparing alternative implementations of the same mechanic, or doing a first-pass critique on a player-facing feature. For session-level pacing or emotional arcs see experience-design; for moment-to-moment juice see game-feel; for system-of-systems interactions see systems-design. This skill is the per-mechanic lens.
Push the current branch and create a pull request with a title and description derived from the commit history. Use when the user asks to open a PR — the Ship step of the Orchestrator loop, always user-triggered.
Define requirements before implementation — clarify constraints and design policy, then write a requirements spec and task breakdown for the Implementer to a gitignored plan file. Use at the Plan step of the Orchestrator loop, or whenever a request's scope needs pinning down before building. Never implements; the plan file is its only write.
Run a PR's full review-fix cycle — wait for review and CI, fix failures, evaluate and reply to comments, then commit and push. Use whenever a PR was just opened or updated — the post-Ship phase of the Orchestrator loop.
Root-cause investigation — enumerate competing hypotheses, verify each with evidence, suggest a fix but never apply it. Use when an error, failing test, or anomaly needs diagnosing before any fix is written; implementation hands off to the Implementer.
| name | codex-advise |
| description | Cross-model second opinion from OpenAI Codex — `codex-run advise --context` reviews the current session, or pipe a brief. Triggers on "ask codex", "codex review", "second opinion", or the "Cross-model review" rules. |
Cross-model outside view from OpenAI Codex. The prompt is read from stdin. Flags: codex-run --help.
codex-run advise --context # review this session, no brief
codex-run advise --context < brief.md # session + a specific question
codex-run advise -C <repo> --log /tmp/codex.jsonl < brief.md # cold review of a repo, no session
codex-run advise --resume <id> < followup.md # continue a review (id in the banner; only after it exits)
--context sends the session transcript to OpenAI. Codex sees your actions, not your thinking — put load-bearing reasoning in the brief and name the files.~/.claude/rules/process.md) runs foreground; background only a non-gating opinion.-s workspace-write lets Codex run tests. stdout is the verdict.