Perform an automated code review on recent changes. Checks for security issues, performance problems, error handling gaps, and code quality. Outputs a structured report with severity levels.
[omh] Pull request or changes to vet: bug-first review with evidence. Use when the user says: code-review, review, audit, find bugs, release gate, claim audit, evidence audit, README claim.
Review a diff or pull request for correctness first and quality second — logic bugs, edge cases, error handling, races, missing tests, API misuse, performance and readability. Use when reviewing someone else's PR, auditing a change before merge, or self-reviewing your own diff.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
Adversarially-verified multi-angle code review. Use when asked to review code — a working diff, branch, MR/PR, or commit range — or before merging or shipping changes. Fans ten review angles (five bug-hunting, five quality) out to cheap subagents, verifies every candidate finding adversarially, sweeps for coverage gaps, and reports only confirmed findings ranked by severity.
Reviews and audits existing Roblox/Luau code. Use whenever the user asks to review, check, or audit a file, diff, pull request, place, or system, asks whether their code is safe, good, or exploitable, or wants its architectural health or maturity scored - even when Roblox or Luau is never named but the code is a game script. Finds leaks, exploits, and data-loss risks, reports one severity per finding (Blocker / Correctness / Advisory) behind a confidence gate, and scores a whole project 1-5 across security, lifecycle, performance, and replication. Hand-offs: writing or refactoring code goes to the best-practices skill, chasing a reported symptom with no file named to the diagnose skill, Studio tooling, sync, or playtest questions to the studio-ops skill.
评审代码,不评审人:给可操作建议、提问而非命令、解释为什么、区分阻断与建议、肯定好的做法、知道何时收手。 Use when the user asks to review a PR, diff, or code change, or wants review feedback improved or responded to. 触发于「帮我评审这段代码/这个 PR」「回复 review 意见」。
Review code for correctness, edge cases, missing tests, maintainability, and merge risk. Use when the user asks for a code review, asks what could break, or wants a structured assessment before merging.
Perform thorough code reviews with security, performance, and maintainability analysis. Use when user asks to review code, check for bugs, or audit a codebase.
Review a diff the way a senior engineer does — design first, then spec conformance, correctness, complexity, and tests — reporting only findings with a demonstrated failure. Use when asked to review code, review a branch or PR, check changes before merging, audit a diff for bugs or security issues, or "is this safe to merge?".
Adversarial multi-persona code review. Use when the user says "review", "code review", "check this", "review before merge", or wants a second opinion on code quality. Reads all files once, then the full panel finds 3-10 specific issues across code quality, architecture, risk, and user impact.
Use for code, branch, diff, and pull-request reviews in any language, and for technical-plan or design reviews. Performs analysis-only review by default, prioritizes correctness and production risk, adds Kotlin-specific analysis through kotlin-code-reviewer, and uses PRFlow or TWG when remote PR state or company context is needed.
Review code for correctness, maintainability, and best practices. Uses a structured two-pass review (CRITICAL then INFORMATIONAL) with interactive issue resolution. Includes scope challenge, failure mode analysis, and TODOS.md cross-reference. Use this skill when a code review is requested on new or modified code.
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
How do I use one I find here?
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
What do the warnings mean?
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Which skills worked for people?
Open a skill to see its discussion. Reports from people and their agents are coming.