code-quality-review

Run a maintainability and structure review focused on abstraction quality, branching complexity, file growth, canonical ownership, duplication, and refactoring opportunities. Use when the user asks for code quality review, maintainability review, 代码质量审查, 可维护性审查, or comments about whether the change stays easy to understand, modify, test, and extend, including layering and ownership of the change / 改动的分层与归属. Not for generic PR review or independent diff review hunting regressions, concurrency, or test gaps; not for full-spectrum or 全维度代码审计; not for system architecture audits; not for applying refactors; not for pure security, formatting-only, or performance profiling.

Ir a la instalación

Repositorio: bahayonghang/my-ai-cli-toolkit
Última actividad en el origen: 21 de agosto de 2026 a las 07:08
Idioma detectado de SKILL.md: inglés
Estrellas: 16
Forks: 1

Opciones de instalación

De forma predeterminada está seleccionado el prompt que primero revisa el origen. Puedes cambiar a un comando directo o descargar una copia local.

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Un comando directo omite el prompt de revisión. Revisa el origen antes de ejecutarlo.

npx skills add https://github.com/bahayonghang/my-ai-cli-toolkit --skill code-quality-review

El comando permanece en una sola línea. Desplázate horizontalmente para revisarlo antes de copiarlo.

¿Prefieres una copia local? Descarga los archivos que SkillsMP tiene disponibles ahora.

Revisa los archivos de origen

Lee SKILL.md y los archivos complementarios que muestra SkillsMP antes de decidir si quieres instalarlo.

Explorador de archivos

4 archivos

SKILL.md

Instrucciones de origen · Vista previa de solo lectura

Volver a la búsqueda Volver a la instalación

trellis-plan-review

Independent review of Trellis task planning artifacts. Treats the selected task and its recursive current or archived children as one review scope, verifies repository claims and path:line citations against code, traces every acceptance-criterion clause to a requirement and design mechanism, rechecks arithmetic and units, writes one combined evidence-backed Markdown report under the reviewed project's .trellis/reviews directory, and returns one copyable handoff prompt. Compares the plan with the real diff after the task starts. Use when the user asks to 审阅 trellis 父子任务, 审阅规划, 审查 prd design implement, 检查验收标准有没有机制支撑, review a trellis plan or task tree, audit a plan another agent wrote, or verify plan claims before implementation. Not for a code-diff-only review, writing or repairing the plan, or running the task.

2026-08-26

job-application-kit

求职申请与面试准备套件：针对目标职位（JD/职位描述）量身定制简历与求职信，在诚实边界内修改与包装既有经历，生成阶段化面试准备包并支持模拟面试。触发词：写简历、改简历、简历定制、tailor resume、resume、CV、 resume writing、求职信、cover letter、投递、申请职位、job posting、JD、职位描述、岗位匹配、fit 评估、面试准备、面试问题、interview prep、mock interview、模拟面试、包装经历、量化成果。不适用于：职位批量抓取与申请追踪管理、通用营销或商务文案、学术论文写作、招聘方视角的简历筛选。

2026-08-26

goal-meta-skill

Turn vague or complex agent tasks into project-aware, verifiable `/goal` commands and optional approved root `GOAL.md` handoff contracts for Claude Code, Codex, Grok Build, Oh My Pi, and Kimi Code. Use for Goal 指令, 目标指令, `/goal` prompts, 中文 Goal 模板, goal 持久化/保存/落盘, fresh-Agent or 跨会话交接, plan-to-goal interviews, bounded agent work definitions, Trellis 任务实施, 子任务实施, commit-then-archive cadence, or 终稿展示. Do not use for ordinary one-line work, pure exploration, memory-vault creation, or active-goal management that only needs a platform command.

2026-08-26

Ver todos los de este repositorio

name	code-quality-review
description	Run a maintainability and structure review focused on abstraction quality, branching complexity, file growth, canonical ownership, duplication, and refactoring opportunities. Use when the user asks for code quality review, maintainability review, 代码质量审查, 可维护性审查, or comments about whether the change stays easy to understand, modify, test, and extend, including layering and ownership of the change / 改动的分层与归属. Not for generic PR review or independent diff review hunting regressions, concurrency, or test gaps; not for full-spectrum or 全维度代码审计; not for system architecture audits; not for applying refactors; not for pure security, formatting-only, or performance profiling.
category	development-workflows
tags	["code-review","code-quality","maintainability","architecture","refactoring"]
version	0.3.0
argument-hint	[path-pr-or-diff]
allowed-tools	Read, Glob, Grep, Bash, Write

Code Quality Review

Purpose

Use this skill to perform a strict, evidence-based review of code quality and maintainability. Focus on whether the change keeps the codebase easier to understand, modify, test, and extend.

Prioritize structural concerns over style nits: abstraction quality, branching complexity, file growth, boundary cleanliness, canonical-layer ownership, duplication, orchestration complexity, and refactoring opportunities that preserve behavior while simplifying the implementation.

When to Use

Use this skill when the user asks for:

code quality review, code review focused on quality/maintainability, or maintainability review
Comments about whether the change stays easy to understand, modify, test, and extend, including layering and ownership of the change (改动的分层与归属)
Chinese requests such as 代码质量审查, 代码质量 review, 可维护性审查, or 改动的分层与归属

When to Skip

Do not use this skill as the primary guide for:

Generic PR review, independent git-diff review, or hunts for functional regressions, missed scenarios, wrong assumptions, concurrency, or test gaps — use code-auditor (pr / dir)
Full-spectrum or 全维度代码审计 — use code-auditor project
System architecture audits
Applying refactors or editing product code — use code-refactor
Related updates that can leave half-applied state — that is a correctness finding for code-auditor
Pure security audits, unless the user also asks about maintainability or code quality
Performance profiling or benchmark-driven optimization
Formatting-only, lint-only, or naming-only review

This skill is the focused structural and maintainability lens. Keep it for judging whether the change keeps the code easy to understand, modify, test, and extend.

Safety and Scope

Treat the code under review as read-only. Never edit, reformat, refactor, commit, push, or run destructive git operations on it. The one exception is the opt-in artifact mode (see Output Modes), which only ever writes a review report under code_review/ and never touches product code.
Recommend concrete structural changes, but do not apply them. Hand off apply-refactor requests to code-refactor.

Area	Flag when	Prefer
Structural simplification	The change preserves incidental complexity or adds concepts without clear leverage.	Reframe the flow so branches, modes, helpers, or layers disappear.
Branching complexity	New conditionals, flags, modes, or special cases are scattered through unrelated paths.	Move policy into a focused helper, explicit model, state machine, or owned module.
File growth	A file grows past a healthy size boundary, especially near or beyond 1000 lines.	Split focused modules, helpers, components, or orchestration layers.
Abstraction quality	Wrappers, generic mechanisms, or pass-through helpers add indirection without reducing cognitive load.	Inline thin wrappers or deepen the abstraction so it hides real complexity.
Boundary and type contracts	`any`, `unknown`, casts, optionality, or silent fallback hide the real invariant.	Make the boundary explicit with a typed model, shared contract, or validated input shape.
Canonical ownership	Feature logic leaks into shared paths or duplicates existing utilities.	Reuse canonical helpers and move logic to the layer that owns the concept.
Orchestration complexity	Independent work is serialized needlessly.	Simplify orchestration, or parallelize independent work when that is clearer.

code-quality-review

Opciones de instalación

Revisa los archivos de origen

Code Quality Review

Purpose

When to Use

When to Skip

Safety and Scope

Code Quality Review

Purpose

When to Use

When to Skip

Safety and Scope

Workflow

Review Checklist

Severity Rubric

Required Output Format

Example Finding

CQ-001 [High] `getUser` discards its type contract and hides "not found"

Output Modes

Tone

Failure Handling

code-quality-review

Datos de origen

Opciones de instalación

Revisa los archivos de origen

Más de este repositorio

Más de este repositorio

Code Quality Review

Purpose

When to Use

When to Skip

Safety and Scope

Code Quality Review

Purpose

When to Use

When to Skip

Safety and Scope

Workflow

Review Checklist

Severity Rubric

Required Output Format

Example Finding

CQ-001 [High] getUser discards its type contract and hides "not found"

Output Modes

Tone

Failure Handling

CQ-001 [High] `getUser` discards its type contract and hides "not found"