Code-review Skills for OpenClaw Agents

Adversarial Code Review

@chpomob

Multi-perspective adversarial code review with git-isolated worktrees. Two reviewers (Architect + Inspector), cross-validation, and synthesis report. The synthesis is the final arbiter — its verdict takes priority over individual reviewer outputs.

code-polish

@tenequm

Pre-release code review - lint and type checks, parallel review agents (cleanliness, design, efficiency, side-effect gating), findings validated, fixes on approval. Reviews a GitHub PR when given one. Run before committing, pushing, or on a PR.

Software Concept Architect · Review — Find Design Gaps and Code Drift

@agenticweb4

Find Design Gaps and Code Drift

review-github-pr

@tenequm

Reviews a GitHub pull request end to end - fetches the diff, runs checks, analyzes with three parallel agents (correctness, conventions, efficiency), validates every finding against the code, drafts inline comments with a recommended action.

adversarial-code-loop

@chpomob

BUILD → REVIEW → (FIX → VERIFY)^N → ARBITER on isolated git branches. Git-native: each loop runs on its own branch, changes are committed, reviews inspect git diffs.

buildwright

@raunakkathuria

Apply agent-led software development workflows for planning, implementation, TDD, verification, security review, code review, shipping, repository analysis, and cleanup. Use when developing or maintaining a software project with Buildwright.

TRAECNclaw MCP

@luckycat133

Operate TraeCN through TRAECNclaw's focused stdio MCP tools. Use when an MCP-capable agent must send or stop work, choose a workspace/model/mode/conversation, inspect or change Trae settings through its UI, manage conversations, or resolve an exceptional question or command approval. Queueing, waiting, recovery, notifications, routine non-command questions, and keep/revert gates are gateway-managed.

smart-git

@yexinjia

Use the smart-commit-host-agent CLI for local code review, creating a PR/MR, reviewing an existing PR/MR, listing my open PRs/MRs, or batch-reviewing my PRs/MRs. Triggers: create MR / create PR / create pull request / open a PR / submit and create MR; review MR / review PR plus a PR/MR URL; list my MRs / list my open PRs / my MR list / my-pull-request list; batch review my MRs / batch-review my PRs / my-pull-request batch-review; local code review / local review of changes / local review diff / smart-git local review. Do not use for ordinary code review / review code without the word local. Must read this SKILL.md first. CLI task flow plus Host-Agent turn loop only; do not use gh for GitLab; no manual commit/push/API; do not edit business source based on review.

人虾协作开发工作流

@muippt

软件开发工作流+通用方案输出自检，融合Superpowers方法论，强制设计先行→批判性三问自检→计划分解→子Agent执行→双阶段Review。触发词：开发、写代码、新功能、新skill、重构、修bug、实现、build、implement、帮我做一个、方案自检、三问自检。即使用户没有明说'走流程'，只要涉及新...

Argus Design Review

@cgartlab

Use when reviewing frontend code for design quality — checking design token usage, hardcoded values, dark mode coverage, accessibility compliance, CSS consistency, semantic HTML, or framework API usage. Use when auditing a component, page, or design system for issues. Trigger phrases: '帮我 review 这段代

gitlab-work-stats

@endcy

生成 GitLab 用户工作统计报告（仅限只读分析）。分析指定用户在指定时间段内的合并请求、代码提交、代码审查活动。不修改服务器数据，不提供加密功能。

polish-new

@tenequm

Pre-release code review that converges - parallel review agents sized to the diff, findings validated against evidence in a run ledger, fixes on approval, then re-reviews its own fixes until a round warrants no edits. Run on /polish-new.

Delegated Code Review

@wufei-png

Single delegated review with verified fixes

Structured PR Review

@ggettert

Layered PR code review with severity tiers (MUST FIX/SHOULD FIX/SUGGESTION) and addressing-mode. Default: gh CLI only; optional Lobster pipeline.

Review Loop

@wufei-png

Bounded delegated review and fix loop

Code Craftsmanship

@chaocai2001

Senior Staff Engineer skill for AI coding agents. Enforces simplicity, reuse-first, minimal-diff changes, testability, and Clean Code discipline. Use this sk...

Hubo

@h0ngcha0

Implement code; reconcile every review finding

Vibe Codebase Audit

@43622283

Comprehensive automated and multi-model AI security audits for AI-generated codebases, checking vulnerabilities, secrets, dependency risks, and config issues.

Verificate

@verificate-dev

The trust layer for OpenClaw. Verify AI-written code, tool calls and research answers before you trust them — 17 deterministic reality gates + a frontier-model review with veto power. Free to try, no signup.

Verificate Cn

@verificate-dev

OpenClaw 的信任层。在信任之前，先验证 AI 编写的代码、工具调用与研究答复——17 道确定性现实闸门 + 前沿模型评审，拥有一票否决权。免费试用，无需注册。

Code Handover Assistant

@chenxyzcyxpp

Use when receiving a handed-over codebase and needing to systematically understand it for handover. Performs 7-phase structured analysis: business positionin...

元开 yotta-dev-mcp

@yottameta

元开（yotta-dev-mcp）—— 一个 stdio MCP server 提供 18 个确定性开发工具：repo_map（代码库地图）、system_model（系统模型与 .yotta/architecture.json 契约分层）、architecture_review（契约评审）、impact_analysis（变更影响锥）、verify_change（L0-L5 验证账本）、self_test（完整性检查与 seeded defect / mutation 反证）、run_adapter（显式运行 import-linter / dependency-cruiser / Repomix）、find_code（符号定位）、compress_output（长输出压缩）、review_code / review_diff（规则化评审）、scan_secrets（密钥脱敏扫描）、scan_dependencies（依赖与 typosquat 启发式）、check_publish_readiness（发布前守门）、run_checks（白名单检查，默认关闭执行）、scaffold_skill（技能脚手架，默认 dry-run）、workflow_state（.workflow 状态读取与安全追加）。Python 3.8+ 标准库、默认离线、默认只读、输出带文件行号与规则证据；缺工具或配置一律 UNKNOWN，不自动安装、不联网。

tldr-write

@surefirestudios

Write messages people actually read: the ask first, the padding gone. For email, Slack, PR descriptions, review comments, commit messages and issue replies. Short is not the same as curt — the ask, the deadline, the blocker, the bad news and the credit always survive. Invoke with /tldr-write, or name the medium.

structure-check

@return054

Stop trusting "done." Structure Check mechanically verifies that everything the task required actually exists in the code — symbols defined, exports wired, functions actually called, no stub shells hiding behind a TODO. The agent writes a requirement checklist from the user's task, the tool checks every item, and the exit code decides (0 all pass / 1 something missing / 2 bad checklist). The agent may only quote the verdict, never overrule it. Zero dependencies, Node >= 18, comment-aware; full JS/TS support plus Python exists/notStub. Use after completing any coding task (trigger phrases - structure check, feature implemented, 触发词 - 结构检查, 功能是否实现, 实现核对, 检查代码结构, 交付核对).

Address Review Comments

@arunjeetsingh

Fix the latest reviewer batch, self-audit, commit, and reply

Open Pull Request

@arunjeetsingh

Build, validate, and open a review-ready PR

Review Pull Request

@arunjeetsingh

Review a PR, reconcile prior feedback, and watch for the author's fix

RDK Model Zoo Demo Review

@maxma615

Review demos for standards and delivery completeness

Clean Code 审计法 · 第一性原理

@elisabeth15501

第一性原理 clean code 审计法。从单根前提「代码是写给人看的」推导出两根判据—— A. 理解成本（读起来费不费劲）/ B. 修改风险（改起来怕不怕），用红/黄/绿三档给代码打分， 并明确允许「有意的、注释了的、范围可控的技术债」暂时存在。专用于审计你自己的 WorkBuddy Skill 脚本或其他 Python 代码，产出带证据(文件:行)的可勾选报告。 触发词：「用第一性原理审代码」「理解成本/修改风险」「clean code 审计」「审计我的 Skill 脚本」 「按红黄绿审代码」「clean code 审计样例」。注意：本 skill 只做可读性/可维护性的第一性原理审计， 不做通用 PR/MR 审查（那用 code-review-assistant 或 critical-code-reviewer）， 不替代 clean-code 的写代码规范手册，也不做 lint/格式化（那用 project-code-standard）。 First-Principles Clean Code Audit. Derives two criteria from one root premise — "code is written for humans": A. Comprehension cost (how hard to read) / B. Change risk (how scary to modify) — scored red/amber/green, explicitly permitting intentional, documented, scoped tech debt. Audits your own WorkBuddy skill scripts or Python code, emitting an evidence-backed (file:line) checklist report. Triggers: "audit code with first principles", "comprehension/change risk", "clean code audit", "audit my skill scripts". Read-only: emits findings, never edits. Note: this skill does first-principles readability/maintainability audit only — not generic PR/MR review (use code-review-assistant / critical-code-reviewer), not a style handbook (use clean-code), and not lint/format (use project-code-standard).

Grokified code review

@imfaisii

Review a git diff for bugs, security issues and missing tests with the grok-build-0.1 model through the Grokified API.

TrailMark

@edelmarschneider

Collaborate with the developer through TrailMark's desktop Markdown IDE—inspect what document and passage they are currently reading, search tagged specs, read shared notes, and resolve inline review comments via MCP.

Security Best Practices

@return054

Security reviews and secure-by-default guidance