skills.rest
whynpc9
whynpc9COMMUNITY
Explore all skills by this author →
GitHub

cursor-cli-review

Coordinate Cursor CLI agents for code review and planning in non-interactive mode.

Updated Mar 11, 2026
Search Tags:#automation#planning#code-review#review-process#cursor-cli#development-planning
One-click install
npx skills add https://github.com/whynpc9/cursor-cli-review-skill --skill cursor-cli-review
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cursor-cli-review
Source: https://github.com/whynpc9/cursor-cli-review-skill/tree/main/skills/cursor-cli-review
Command: npx skills add https://github.com/whynpc9/cursor-cli-review-skill --skill cursor-cli-review

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Code review and development planning using Cursor CLI in non-interactive mode. Three modes: (1) Standard Review — spawns 1-3 Cursor reviewers for correctness, design, and security; (2) Adversarial Review — runs a dedicated skeptical reviewer that pressure-tests the chosen approach and failure modes; (3) Plan — spawns 1-3 Cursor planners for architecture, implementation, and risk analysis. Default model: opus-4.6. ONLY trigger this skill when the user explicitly mentions "cursor" in their request — for example "use cursor review", "cursor adversarial review", "用cursor review", "让cursor帮我做计划". Do NOT trigger on generic "review my code" or "make a plan".

Core Features & Use Cases

  • Spawn Cursor CLI agents in non-interactive mode to either review code changes or produce development plans, each from clearly separated perspectives.
  • Implement three modes: Standard Review, Adversarial Review, Development Planning, with a default model.
  • Enforce hard constraints: all analysis must run via Cursor CLI using agent -p; read-only review; gate on explicit trigger.
  • Support deterministic target selection, structured JSON output, and safeguarding against default agent exposure.

Quick Start

Spawn Cursor CLI agents to review code changes or generate development plans in non-interactive mode.

Frequently Asked Questions about cursor-cli-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate code reviews for correctness, design, and security?▼

Automated code review for correctness, design, and security is handled by spawning multiple Cursor CLI reviewers in non-interactive mode. The Standard Review mode deploys up to three agents that analyze code changes from distinct perspectives and return structured output.

What is an adversarial code review and when should I use it?▼

Adversarial code review uses a dedicated skeptical reviewer agent to pressure-test your chosen approach and identify failure modes. Use this mode when you need to validate critical architecture decisions and uncover potential vulnerabilities before merging complex changes.

How do I generate an architecture and risk analysis development plan using AI?▼

To generate a development plan, the Plan mode spawns up to three Cursor CLI planners that analyze architecture, implementation steps, and risks. This provides a structured planning workflow that evaluates technical feasibility and potential project bottlenecks.

Can I run Cursor CLI agents in non-interactive mode for automated planning?▼

Yes, Cursor CLI agents can run in non-interactive mode for automated planning and review. This skill coordinates agents using the agent -p command, enforcing read-only analysis for reviews and deterministic target selection for planning workflows.

Why does the automated code review skill not trigger on generic review requests?▼

Automated code review via this skill only triggers when you explicitly mention the keyword 'cursor' in your request. This gatekeeping mechanism prevents unintended execution on generic commands, ensuring the Cursor CLI agents activate only for targeted review and planning workflows.

Related Skills

Explore More Software Engineering Skills→
alexandrbasisalexandrbasis
12

cursor-cli

Review code changes with Cursor Composer 2 for independent assessment.

Community
Intermediate
tyevanstyevans
14

critique

Review proposals and plans to identify flaws, gaps, and risks.

Community
Intermediate
render-ossrender-oss

render-cli

Automate Render CLI deployments, monitoring, and debugging with API key authentication.

Official
Intermediate
LuisSambranoLuisSambrano
7

code-review

Perform systematic code review and static analysis across multiple programming languages.

Community
Advanced