원클릭으로 Manus에서 모든 스킬 실행

시작하기

code-review

스타27

포크3

업데이트2026년 2월 27일 17:59

Systematic code review with severity-ranked findings

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

definableai

definableai/definable.ai

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

When to Use

Use this skill when reviewing code changes (diffs, PRs, or complete files) for correctness, maintainability, security, and adherence to best practices.

Steps

Understand context: Read the full diff or file. Identify the purpose of the change (feature, bugfix, refactor, etc.).
Check correctness: Verify logic, edge cases, error handling, and return values. Look for off-by-one errors, null/undefined handling, and race conditions.
Assess security: Check for injection vulnerabilities (SQL, XSS, command), improper input validation, hardcoded secrets, and insecure defaults.
Evaluate design: Consider naming clarity, function cohesion, abstraction level, and adherence to existing patterns in the codebase.
Review tests: Check if changes are covered by tests. Identify missing test cases for edge cases and error paths.
Rank findings: Assign severity to each finding and present them in priority order.

Severity Levels

Critical: Bugs that will cause crashes, data loss, or security vulnerabilities in production.
Warning: Issues that may cause problems under certain conditions or violate important conventions.
Suggestion: Improvements to readability, naming, or style that are not strictly required.
Nitpick: Minor style preferences with no functional impact.

Rules

Focus on the changed code, not unrelated pre-existing issues (unless they interact with the change).
Provide concrete fix suggestions, not just problem descriptions.
Be specific: reference line numbers, function names, and variable names.
Acknowledge good patterns and well-written code, not just problems.
If you're uncertain whether something is a bug, say so and explain your reasoning.

Output Format

For each finding:

[SEVERITY] file:line — Short title
Description of the issue and why it matters.
Suggested fix or alternative approach.

End with a summary: total findings by severity, overall assessment, and whether the change is ready to merge.

이 저장소의 다른 Skills

같은 저장소

fix

definableai/definable.ai

Use when you have lint errors, formatting issues, or before committing code to ensure it passes CI.

2026-04-0927

memory-manager

definableai/definable.ai

Manages two-tier user memory — working memory (always loaded) and archived memory (indexed, on-demand). Instructs the agent on when and how to store, recall, and forget information.

2026-04-0427

pdf

definableai/definable.ai

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

2026-03-0927

slack-gif-creator

definableai/definable.ai

Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."

2026-03-0927

webapp-testing

definableai/definable.ai

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

2026-03-0927

xlsx

definableai/definable.ai

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

2026-03-0927

name	code-review
description	Systematic code review with severity-ranked findings
version	1.0.0
tags	["code","review","quality","bugs"]

When to Use

Use this skill when reviewing code changes (diffs, PRs, or complete files) for correctness, maintainability, security, and adherence to best practices.

Steps

Understand context: Read the full diff or file. Identify the purpose of the change (feature, bugfix, refactor, etc.).
Check correctness: Verify logic, edge cases, error handling, and return values. Look for off-by-one errors, null/undefined handling, and race conditions.
Assess security: Check for injection vulnerabilities (SQL, XSS, command), improper input validation, hardcoded secrets, and insecure defaults.
Evaluate design: Consider naming clarity, function cohesion, abstraction level, and adherence to existing patterns in the codebase.
Review tests: Check if changes are covered by tests. Identify missing test cases for edge cases and error paths.
Rank findings: Assign severity to each finding and present them in priority order.

Severity Levels

Critical: Bugs that will cause crashes, data loss, or security vulnerabilities in production.
Warning: Issues that may cause problems under certain conditions or violate important conventions.
Suggestion: Improvements to readability, naming, or style that are not strictly required.
Nitpick: Minor style preferences with no functional impact.

Rules

Focus on the changed code, not unrelated pre-existing issues (unless they interact with the change).
Provide concrete fix suggestions, not just problem descriptions.
Be specific: reference line numbers, function names, and variable names.
Acknowledge good patterns and well-written code, not just problems.
If you're uncertain whether something is a bug, say so and explain your reasoning.

Output Format

For each finding:

[SEVERITY] file:line — Short title
Description of the issue and why it matters.
Suggested fix or alternative approach.

End with a summary: total findings by severity, overall assessment, and whether the change is ready to merge.