skills.rest
catlog22
catlog22COMMUNITY
Explore all skills by this author →
GitHub

team-review

Orchestrate multi-agent code review workflows with scanner, reviewer, and fixer agents.

511|63|Updated Mar 17, 2026
Search Tags:#automation#llm#multi-agent#orchestration#pipeline#code-review#semgrep
One-click install
npx skills add https://github.com/catlog22/Maestro-Flow --skill team-review-catlog22
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: team-review
Source: https://github.com/catlog22/Maestro-Flow/tree/main/.claude/skills/team-review
Command: npx skills add https://github.com/catlog22/Maestro-Flow --skill team-review-catlog22

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinating thorough, multi-tool code reviews across teams is slow, error-prone, and manual; team-review automates scanning, enriched reviewer analysis, and deterministic fixes so projects get reliable, auditable results faster.

Core Features & Use Cases

  • Three-role pipeline: scanner (toolchain + LLM scan), reviewer (deep enrichment and root-cause analysis), and fixer (plan, apply, verify with rollback).
  • Session and task orchestration: automatic session directory management, task creation/dispatch, team-worker spawning, and message-bus driven progress tracking.
  • Verification & safety: deterministic fix plans, per-file rollback-on-failure, verification with tsc/eslint/jest/pytest/semgrep, and configurable fix scopes (all / critical/high).
  • Use Case: Run a full review on a TypeScript repo to find security, correctness, performance, and maintainability issues, produce an enriched review report, and optionally apply verified fixes.

Quick Start

Ask the coordinator to run a full team-review on the current repository using the maestro CLI with the --full flag.

Frequently Asked Questions about team-review

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

FAQPage Schema
How do I automate multi-agent code reviews for a TypeScript repository?▼

You can automate multi-agent code reviews by orchestrating a scanner, reviewer, and fixer pipeline. The team-review Skill coordinates toolchain scanning, root-cause analysis, and programmatic fixes across agents for reliable repository analysis.

What is multi-agent code review orchestration?▼

Multi-agent code review orchestration automates scanning, enriched reviewer analysis, and deterministic fixes by dispatching tasks across specialized agents. It manages sessions, spawns team-workers, and tracks progress via a message bus for auditable results.

Can I use eslint and semgrep together in an automated code review pipeline?▼

Yes, the pipeline integrates toolchains including eslint, semgrep, tsc, jest, and pytest to scan code and verify fixes. The scanner agent runs these tools alongside LLM analysis to identify security, correctness, and performance issues.

How do I apply automated code fixes with rollback on failure?▼

The fixer agent generates deterministic fix plans, applies changes per file, and verifies results using configured toolchains. If verification fails, it automatically rolls back changes to ensure repository safety and prevent broken states.

Does multi-agent code review support Python repositories?▼

Yes, the pipeline supports Python repositories through pytest and semgrep integration for verification and scanning. It applies the same scanner, reviewer, and fixer workflow to find security and correctness issues across different languages.

What is the best way to coordinate code scanning and fixing across multiple agents?▼

The best way is using a session-based orchestration model that creates tasks, dispatches them to team-worker agents, and tracks progress via a message bus. This ensures coordinated scanning, enriched analysis, and verified fixes with rollback safety.

Related Skills

Explore More Software Engineering Skills→
MomoDavilukeMomoDaviluke
2

verification-loop

Automate builds, type checks, linting, tests, and security scans for Claude Code sessions.

Community
Advanced
Kling0012Kling0012
1

Verification & Quality Assurance

Automate verification checks with truth scoring and rollback for CI/CD pipelines.

Community
Advanced
Ibrahim-3dIbrahim-3d
371

message-bus

Coordinate multi-agent workflows with a file-based message bus.

Community
Advanced
BrunoSantanaDeveloperBrunoSantanaDeveloper

parallel-agents

Coordinate multiple specialized agents for multi-domain tasks in a unified session.

Community
Advanced