KS
Killer-Skills

review-preflight — how to use review-preflight how to use review-preflight, review-preflight setup guide, automated code review tools, Codex CLI integration, review-preflight vs manual code review, review-preflight install, what is review-preflight, review-preflight alternative, review-preflight tutorial

v1.0.0
GitHub

About this Skill

Perfect for Code Review Agents needing automated pre-review safety checks for lint, tests, and PR diff context. review-preflight is a canonical execution contract for running automated code reviews with Codex CLI, ensuring a consistent and efficient review process.

Features

Runs a minimal pre-review safety pass using Codex CLI
Checks lint, tests, PR diff context, and obvious risky changes
Supports optional PR number and base branch inputs
Provides a fixed order of checks for consistent results
Generates output that can be pasted into a PR comment

# Core Topics

wakadorimk2 wakadorimk2
[0]
[0]
Updated: 3/5/2026

Quality Score

Top 5%
47
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add wakadorimk2/personal-mcp-core/review-preflight

Agent Capability Analysis

The review-preflight MCP Server by wakadorimk2 is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use review-preflight, review-preflight setup guide, automated code review tools.

Ideal Agent Persona

Perfect for Code Review Agents needing automated pre-review safety checks for lint, tests, and PR diff context.

Core Value

Empowers agents to run a minimal pre-review safety pass, checking lint, tests, and PR diff context, providing a consistent review process with tools like Codex CLI, and enabling them to identify obvious risky changes through a fixed order of checks.

Capabilities Granted for review-preflight MCP Server

Automating code review preflight checks for PRs
Validating lint and test results before in-depth review
Identifying high-risk changes in PR diff context

! Prerequisites & Limits

  • Requires PR number and base branch as optional inputs
  • Default base branch set to 'cu' if not provided
  • Limited to running a fixed order of checks
Project
SKILL.md
2.0 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

review-preflight

This is the canonical execution contract for running the review preflight with Codex CLI. The human-facing intent lives in docs/skills/review-preflight.md.

Goal

Run a minimal pre-review safety pass before deeper review work starts. Check lint, tests, PR diff context, and obvious risky changes in a fixed order so the result can be pasted into a PR comment.

Inputs

  • PR number (optional)
  • Base branch (optional, default: current branch upstream or main)
  • Expected commands: ruff check ., pytest, gh pr diff <PR> when PR number is available

If the PR number is missing, skip gh pr diff and use local git diff against the chosen base branch. If the base branch is missing, prefer the current branch upstream; otherwise use main.

Procedure

Run the checks in this order.

  1. Run ruff check .
  2. Run pytest
  3. Collect diff context
    • If PR number is provided: run gh pr diff <PR>
    • Otherwise: inspect local git diff against the chosen base branch
  4. Summarize the diff in 2 to 5 lines
  5. Flag obvious risks
    • destructive file operations
    • wide-scope refactors outside the stated review target
    • dependency, CI, or release-impacting changes
    • missing tests for behavior changes

Output Format

Return Markdown with the sections below in this order.

Summary

  • Overall status: / ⚠️ /
  • One-line summary

Checks

  • ruff: / ⚠️ /
  • pytest: / ⚠️ /
  • diff: / ⚠️ /

Diff Summary

  • 2 to 5 short lines

Risks

  • None if no obvious risk was found
  • Otherwise list each risk in one line

Fix Candidates

  • Minimal, local fixes only
  • None if no fix is needed before review

Next Action

  • One line stating whether review can proceed

Constraints

  • Do not push
  • Do not use external web search or fetch arbitrary remote content
  • Do not perform destructive operations
  • Do not change files unless explicitly asked in the current task
  • Keep recommendations inside the current review scope

Related Skills

Looking for an alternative to review-preflight or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication