Automated code review with quality checks, security audit, and best practices. Analyzes code for bugs, performance issues, and convention violations. Triggers: code review, review code, check code, analyze code, PR review, 코드 리뷰, 코드 검사, 코드 분석, コードレビュー, コード分析, 代码审查, 代码分析, revision de codigo, revue de code, Code-Review, revisione Do NOT use for: architecture review (use $phase-8-review), deployment (use $phase-9-deployment).
Run a local pre-push AI code review of the current branch with the OpenAI `codex` CLI, the same way ClickHouse CI does, and optionally iterate fix and re-review until clean. Use when asked to review the current branch before pushing, run "the codex review" / "the AI review" locally, or get an independent second opinion on a diff. Not for reviewing someone else's PR on GitHub (CI already does that).
Review a pull request, diff, or set of proposed changes in microsoft/mssql-rs — from a GitHub PR link, a PR number, or local staged/unstaged changes. Use whenever the user asks to review a PR, asks for feedback on a diff, or asks whether changes are ready to merge. Covers correctness, security, tests, readability, performance, API/breaking changes, and mssql-rs repo conventions.
Review committed or uncommitted changes along two axes — repository standards and the originating capability contract or change spec. Use for a branch, PR, or work-in-progress review.
Deep code audit that finds dead wiring, silent failures, unfinished features, placeholder stubs, bloated files, and unnecessary complexity. Produces an actionable report with file:line references grouped by severity. Think of it as a senior dev doing a thorough PR review of the entire codebase. Triggers on: "code review", "audit the code", "review the code", "find dead code", "find placeholders", "check for stubs", "prune the code", "code cleanup", "implementation review", "completeness check", "find unused code".
Use before opening a pull request to this repo. Reviews the working diff for correctness bugs and repo conventions, runs the test/lint gates, and can post findings directly on the PR. Triggers on "review my changes", "review this PR", "pre-PR review".
Skill: CodeReview
## Purpose
Provide concrete and actionable code-review feedback to surface bugs, risks, and testing gaps.
## Trigger conditions
- Tasks that explicitly request a codereview or quality audit
Reviews code changes and codebases for real defects and unnecessary complexity. Use this skill when asked to review a diff, branch, codebase, or completed implementation, or to check work against its plan. Do not use for an HTML walkthrough of a pull request (use pr-review) or for planning.
(alamops) Performs a thorough, read-only code review on any source of changes — a pull request, a git diff, uncommitted edits in the working tree, recent commits on the current branch, or code that was just produced or discussed in the conversation. Flags bugs, security issues (tenant isolation, authz gaps, atomicity, retry safety, multi-step flow completeness, RLS / row-policy self-recursion), performance issues (in-memory aggregation, sequential fan-out, partial-period comparisons), consistency issues (including schema ↔ code column-reference drift), and blast-radius gaps. Returns structured findings (category, severity, file, line, suggestion) without modifying any code. Use whenever the user asks for a code review, PR review, diff review, feedback on pending or recent changes, or a critique of code just written in this session.
Adversarially verified multi-dimensional review of a code diff. Runs independent reviewers across language, architecture, QA, technical-lead and regression, the review depth deciding which of them always run, plus devops, security, domain and blast radius (who outside the diff observes the change, from the codebase graph) only when the diff calls for them, then makes two skeptics try to refute every blocker and warning before it reaches you. Use after implementing a change, before opening a PR, or when a diff is high-stakes enough that false positives would waste real time.
5011d agoReviewMountCreate a free account to mount
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
ww-w-aiSkill
