Skip to main content

code-review-personal

Perform a comprehensive branch code review using `git diff main...HEAD`, feature-plan context files, and project conventions.

来源信息

仓库
sunpar/agentic_coding_tools
最近来源活动
2026年2月13日 13:40
检测到的 SKILL.md 语言
英语
星标
1
分支
0

安装方式

默认使用会先检查来源的 Prompt;你也可以切换为直接命令,或下载本地副本。

检查来源文件

决定是否安装前,请先阅读 SKILL.md,以及 SkillsMP 当前展示的配套文件。

正在显示 SKILL.md

SKILL.md
来源说明 · 只读预览
name
code-review-personal
description
Perform a comprehensive branch code review using `git diff main...HEAD`, feature-plan context files, and project conventions.
disable-model-invocation
true
# Code Review Personal ## Workflow 1. Run `git diff main...HEAD` to inspect all branch changes. 2. Load context from `FEATURE_PLAN.md`, `feature_summary.md`, any `{git-root}/docs/feature-summary*.md` files, or task-prefixed `T*-feature-summary*.md` files if they exist (prefer the most recent summary). 3. Load context from `ORIGINAL_PLAN.md` if it exists. 4. Review all changes against the criteria below. ## Review Criteria ### Functionality - Verify code matches feature intent from plan files. - Check edge-case handling. - Check error handling appropriateness. - Flag obvious bugs or behavioral regressions. ### Code Quality - Check readability, consistency, and organization. - Prefer single-purpose functions. - Check naming clarity. - Enforce project conventions. ### Security and Privacy - Flag sensitive data logging (raw transactions, account numbers, CSV rows). - Check input validation where needed. - Flag hardcoded secrets or credential-like values. ### Performance - Flag inefficient algorithms or query patterns. - Flag potential N+1 access patterns. - Flag unnecessary recomputation or heavy work. ### Tests - Check whether tests cover new behavior and risk areas. - Prefer behavior-focused tests over brittle implementation-coupled tests. - If tests are missing, recommend `/write-tests`. ## Output Format Provide all sections in this order: 1. Executive Summary (1-2 paragraphs) 2. Findings by Severity (Critical > Major > Minor > Cosmetic) 3. Test Coverage Assessment 4. Final Verdict: `Ready to merge` | `Needs minor cleanup` | `Needs major revisions` ## Ground Rules - Prioritize findings and risks over praise. - Keep findings specific and actionable. - Reference concrete file paths and lines when possible. - If no findings exist, state that explicitly and note residual risk/testing gaps.
在 GitHub 查看