Agent skills for Cursor

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.

Use when reviewing SQL migrations, queries, RLS/policy changes, schema modifications, or ORM access patterns for safety, performance, or…

Review uncommitted changes using impact analysis.

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…

Get comprehensive review of a GitLab merge request

Run the Julia code review protocol on Julia scripts.

Use when targeting Review of Economic Studies (REStud) or deciding whether an economics manuscript fits this venue.

Use when preparing the Review of Finance (RoF) replication package — code, data, pseudo-datasets for proprietary sources such as…

Review Playwright tests for quality. Use when user says "review tests", "check test quality", "audit tests", "improve tests", "test code…

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

Reviews a pull request from a PR URL by directly fetching the URL content (no `gh` dependency) and verifies compliance with CONTRIBUTING.md.

Use when understanding or planning around the Review of Economic Dynamics (RED) editorial process — the editor desk/suitability screen…

Use when understanding how Journal of Marketing (JM) review and decisions work — the double-anonymized process, the Coeditor structure…

Use when you need to understand how the Journal of Monetary Economics (JME) review process actually works — single anonymized…

Use to understand how MIS Quarterly's editorial process works and to read a decision letter — the double-anonymous model, the…

Use when you want to understand how Organization Science review and decisions work before or after submitting — the decentralized…

Use when you need to understand how Public Administration Review (PAR) evaluates a manuscript — double-blind review, desk screening for…