Skip to main content
skill CX Codex

review · parcadei — Claude Code skill: what it does, how to install

Runs parallel specialized subagents to evaluate code quality, architecture, and impact, then synthesizes a final merge verdict.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add parcadei/Continuous-Claude-v3 --skill review -a claude-code
Open on GitHub

What review does

The skill establishes a multi-perspective review workflow before merging changes. In the first phase, it fires background tasks across specialized roles: critic inspects code style, readability, error handling, and test coverage, while plan-reviewer runs twice to verify architectural alignment and assess regression risks.

In the second phase, review-agent collects the findings into a synthesized report. It outputs a clear verdict (APPROVE, REQUEST_CHANGES, or NEEDS_DISCUSSION), groups feedback into blocking and non-blocking issues, and drafts notes for the pull request description.

You can run a lightweight check using --quick to keep only the code critic, or add --security to include the aegis agent. Because the workflow relies on Task invocations targeting predefined subagent roles, it requires an environment configured to handle those specific subagent types.

What it helps with

  • split code style, architectural alignment, and regression risk into parallel reviews
  • produce an explicit review verdict separating blocking issues from non-blocking notes
  • evaluate backward compatibility and impacted components before merging
  • trigger an additional security audit using the --security flag

Example prompts for the agent

  • /review
  • /review --quick
  • /review PR #123

How to install review

1Skills CLI (Vercel)

npx skills add parcadei/Continuous-Claude-v3 --skill review -a claude-code

2Manually: put the files in place

~/.claude/skills/review/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/review/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about review

How to install review in Claude Code?

Run npx skills add parcadei/Continuous-Claude-v3 --skill review -a claude-code.

What does the review skill do?

It coordinates critic and plan-reviewer subagents to review code quality, architecture, and risks in parallel, then uses review-agent to deliver a prioritized summary.

What execution flags does review support?

It supports a standard full run via /review, a critic-only pass via /review --quick, PR inspection via /review PR #123, and a security-focused audit via /review --security.

Source text

SKILL.md · MIT
---
name: review
description: Comprehensive code review workflow - parallel specialized reviews → synthesis
---

# /review - Code Review Workflow

Multi-perspective code review with parallel specialists.

## When to Use

- "Review this code"
- "Review my PR"
- "Check this before I merge"
- "Get feedback on implementation"
- Before merging significant changes
- Quality gates

## Workflow Overview

```
         ┌──────────┐
         │  critic  │ ─┐
         │ (code)   │  │
         └──────────┘  │
                       │
         ┌──────────┐  │      ┌──────────────┐
         │plan-reviewer│ ─┼────▶ │ review-agent │
         │ (plan)   │  │      │ (synthesis)  │
         └──────────┘  │      └──────────────┘
                       │
         ┌──────────┐  │
         │plan-reviewer│ ─┘
         │ (change) │
         └──────────┘

         Parallel                Sequential
         perspectives            synthesis
```

## Agent Sequence

| # | Agent | Focus | Execution |
|---|-------|-------|-----------|
| 1 | **critic** | Code quality, patterns, readability | Parallel |
| 1 | **plan-reviewer** | Architecture, plan adherence | Parallel |
| 1 | **plan-reviewer** | Change impact, risk assessment | Parallel |
| 2 | **review-agent** | Synthesize all reviews, final verdict | After 1 |

## Review Perspectives

- **critic**: Is this good code? (Style, patterns, readability)
- **plan-reviewer**: Does this match the design? (Architecture, plan)
- **plan-reviewer**: Is this change safe? (Risk, impact, regressions)
- **review-agent**: Overall assessment and recommendations

## Execution

### Phase 1: Parallel Reviews

```
# Code quality review
Task(
  subagent_type="critic",
  prompt="""
  Review code quality: [SCOPE]

  Evaluate:
  - Code style and consistency
  - Design patterns used
  - Readability and maintainability
  - Error handling
  - Test coverage

  Output: List of issues with severity (critical/major/minor)
  """,
  run_in_background=true
)

# Architecture review
Task(
  subagent_type="plan-reviewer",
  prompt="""
  Review architecture alignment: [SCOPE]

  Check:
  - Follows established patterns
  - Matches implementation plan (if exists)
  - Consistent with system design
  - No architectural violations

  Output: Alignment assessment with concerns
  """,
  run_in_background=true
)

# Change impact review
Task(
  subagent_type="plan-reviewer",
  prompt="""
  Review change impact: [SCOPE]

  Assess:
  - Risk level of changes
  - Affected systems/components
  - Backward compatibility
  - Potential regressions
  - Security implications

  Output: Risk assessment with recommendations
  """,
  run_in_background=true
)

# Wait for all parallel reviews
[Check TaskOutput for all three]
```

### Phase 2: Synthesis

```
Task(
  subagent_type="review-agent",
  prompt="""
  Synthesize reviews for: [SCOPE]

  Reviews:
  - critic: [code quality findings]
  - plan-reviewer: [architecture findings]
  - plan-reviewer: [change impact findings]

  Create final review:
  - Overall verdict (APPROVE / REQUEST_CHANGES / NEEDS_DISCUSSION)
  - Prioritized action items
  - Blocking vs non-blocking issues
  - Summary for PR description
  """
)
```

## Review Modes

### Full Review
```
User: /review
→ All four agents, comprehensive review
```

### Quick Review
```
User: /review --quick
→ critic only, fast feedback
```

### Security Focus
```
User: /review --security
→ Add aegis (security agent) to parallel phase
```

### PR Review
```
User: /review PR #123
→ Fetch PR diff, review changes
```

## Example

```
User: /review the authentication changes

Claude: Starting /review workflow...

Phase 1: Running parallel reviews...
┌────────────────────────────────────────────┐
│ critic: Reviewing code quality...          │
│ plan-reviewer: Checking architecture...         │
│ plan-reviewer: Assessing change impact...         │
└────────────────────────────────────────────┘

critic: Found 2 issues
- [minor] Inconsistent error messages in auth.ts
- [major] Missing input validation in login()

plan-reviewer: ✅ Matches authentication plan

plan-reviewer: Medium risk
- Affects: login, signup, password reset
- Breaking change: session token format

Phase 2: Synthesizing...

┌─────────────────────────────────────────────┐
│ Review Summary                              │
├─────────────────────────────────────────────┤
│ Verdict: REQUEST_CHANGES                    │
│                                             │
│ Blocking:                                   │
│ 1. Add input validation to login()          │
│                                             │
│ Non-blocking:                               │
│ 2. Standardize error messages               │
│                                             │
│ Notes:                                      │
│ - Document session token format change      │
│ - Consider migration path for existing      │
│   sessions                                  │
└─────────────────────────────────────────────┘
```

## Verdicts

- **APPROVE**: Ready to merge, all issues are minor
- **REQUEST_CHANGES**: Blocking issues must be fixed
- **NEEDS_DISCUSSION**: Architectural decisions need input

© parcadei · MIT · parcadei/Continuous-Claude-v3

Similar skills

Everything for Code review and refactoring →

review by other authors comes first.

review official anthropics Reviews inbound agreements against your playbook and routes each document to the relevant review workflow. Use it for MSA, NDA, and SaaS subscription documents. CX Codex +1 728installs review JuliusBrussee Runs an adversarial senior review of the spec before any code is written. Builds a skeptic and tries to refute the plan instead of rubber-stamping it. CX Codex +1 787installs review owainlewis The skill spins up a separate subagent that reads a change and hunts for defects without editing anything. Handy before a merge when you want a second opinion. CX Codex +1 748installs review jsmastery-pro Audits completed features against your original plan, system architecture, and production readiness. Flags discrepancies in a structured report without making code edits. CX Codex +1 946installs review entireio Reads checkpoint transcripts to learn what the developer meant, then audits the diff. Useful before a merge, when you want to catch code that drifted from the plan. CX Codex +1 395installs om-review-prs open-mercato Walks every open pull request that still needs review, newest first, and runs a full review on each. Good as a day-start sweep. CX Codex +1 2,600installs review-pr tirth8205 This skill reviews a PR or branch through a code knowledge graph, showing risk, affected flows, and test gaps. Use it when a diff needs structural context. CX Codex +1 1,200installs attach-review-to-pr NeoLabHQ This skill shows the agent how to post review comments on specific lines of a pull request using GitHub CLI or an MCP tool. Handy when review happens in the terminal. CX Codex +1 1,200installs github-pr-review fvadicamo Pulls review comments from a GitHub pull request, sorts them by severity and proposes fixes. Useful once a PR has collected a pile of feedback. CX Codex +1 576installs traiage-review NeoLabHQ Traiage-review prioritizes repository changes and pinpoints files that human reviewers must inspect first. CX Codex +1 381installs code-review official anthropics The skill reviews diffs and pull requests for security, performance and correctness. Useful when a change needs a look before merging. CX Codex +1 9,900installs

From the same set69

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor