Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

code-review

Étoiles11

Forks1

Mis à jour23 mars 2026 à 07:53

When coding is done and changes need review → multi-dimensional code review (SOLID, security, quality, edge cases), outputs structured report.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

cklxx

cklxx/elephant.ai

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

Explorateur de fichiers

8 fichiers

SKILL.md

readonly

name	code-review
description	When coding is done and changes need review → multi-dimensional code review (SOLID, security, quality, edge cases), outputs structured report.
triggers	{"intent_patterns":["review\|审查\|code review\|CR\|代码审查\|review code","帮我看看代码\|check.my.code\|看下.改得.对不对","代码.有没有.问题\|any.issues\|有没有.bug\|security.check","merge.前.检查\|pre.merge\|提交前.审\|before.commit","代码.质量\|code.quality\|clean.code\|重构.建议\|refactor.suggestion","看下.diff\|review.changes\|这次.改动\|check.diff","有没有.安全.*问题\|vulnerability\|漏洞\|注入\|injection"],"context_signals":{"keywords":["review","审查","CR","code review","代码质量","merge","diff","安全","质量","检查","vulnerability","refactor"]},"confidence_threshold":0.6}
priority	9
requires_tools	["bash"]
max_tokens	200
cooldown	60

code-review

Run a multi-dimensional code review (SOLID architecture, security, quality, edge cases, cleanup) on the current diff and output a structured report with severity levels (P0-P3). All review checklists, workflow steps, and report generation are handled by run.py.

调用

python3 skills/code-review/run.py review

Plus depuis ce dépôt

même dépôt

openbench

cklxx/elephant.ai

When prompt, tool, or agent logic changes need regression testing → run eval benchmarks to detect regressions or improvements.

2026-03-2311

openmax

cklxx/elephant.ai

When a task can be parallelized (bulk code review, multi-module refactor, batch analysis) → split into subtasks running in isolated git worktrees via multiple workers.

2026-03-2311

openseed

cklxx/elephant.ai

When the user wants to research academic papers → search ArXiv, extract PDFs, summarize/review/Q&A, generate experiment code.

2026-03-2311

browser-use

cklxx/elephant.ai

When you need to interact with web pages using the user's logged-in browser → control Chrome via @playwright/cli daemon, reusing cookies/session with persistent tabs.

2026-03-2311

anygen

cklxx/elephant.ai

When user needs AnyGenIO content generation → unified CLI for task execution with progressive disclosure.

2026-03-2311

artifact-management

cklxx/elephant.ai

When you need to persist files (reports, docs, evidence) beyond the session → create/query/delete durable artifacts.

2026-03-2311

name	code-review
description	When coding is done and changes need review → multi-dimensional code review (SOLID, security, quality, edge cases), outputs structured report.
triggers	{"intent_patterns":["review\|审查\|code review\|CR\|代码审查\|review code","帮我看看代码\|check.my.code\|看下.改得.对不对","代码.有没有.问题\|any.issues\|有没有.bug\|security.check","merge.前.检查\|pre.merge\|提交前.审\|before.commit","代码.质量\|code.quality\|clean.code\|重构.建议\|refactor.suggestion","看下.diff\|review.changes\|这次.改动\|check.diff","有没有.安全.*问题\|vulnerability\|漏洞\|注入\|injection"],"context_signals":{"keywords":["review","审查","CR","code review","代码质量","merge","diff","安全","质量","检查","vulnerability","refactor"]},"confidence_threshold":0.6}
priority	9
requires_tools	["bash"]
max_tokens	200
cooldown	60

code-review

调用

python3 skills/code-review/run.py review