Agent skills for Codex CLI

Configure human-in-the-loop gating for AI agent review actions in Claude Code.

Detect AI-generated writing patterns in developer text — docs, docstrings, commit messages, PR descriptions, and code comments.

Review the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR.

Convene a multi-perspective review board on a deliverable - specialist lens(es) plus a business/commercial lens plus QA, chaired by a…

Mandatory before code edits on implementation tasks.

Reviews a contract in plain English, surfaces red flags with severity ratings, and produces a marked-up docx/PDF with suggested redlines.

Use when an evaluation run needs review-driven documentation updates and a structured documentation summary.

Reviews uncommitted, commit, or merge-base firmware diffs.

Schema for tracking code review outcomes to enable feedback-driven skill improvement.

Addresses and fixes findings from a QA code review.

Use before an agent-produced diff is committed, pushed, opened as a PR, merged, landed, or applied to user files when explicit…

Use when targeting Review of Economics and Statistics (REStat) or deciding whether an applied econometrics manuscript fits this venue.

Use when auditing Review of Finance empirical or theoretical analysis: sample construction, identification, asset-pricing tests…

Use when targeting Review of Finance or deciding whether a finance manuscript fits this venue.

Use when running a Review of Finance submission preflight for Editorial Express, regular versus Fast-Track fee choice, 60-page cap…

Use when designing Review of Finance tables and figures under the 60-page total cap, including empirical-finance exhibits, theory figures…

Use when revising a Review of Finance manuscript for a 150-word abstract, double-blind wording, Chicago-style references, first-order…

PR review using parallel specialized agents for code quality, security, testing, architecture, and performance analysis.

Reviews PR comments from GitHub (Copilot, reviewers), evaluates against actual code, replies with reasoning, and resolves threads.

Use to understand how Agricultural Systems (AgSy) evaluates a manuscript — single-anonymized peer review with a minimum of two reviewers…

Use to understand how The Art Bulletin evaluates a submission — double-blind peer review, what referees and the editor look for in…