nicolas-codemate/skills/deep-review

Deep Review Skill

Orchestrates code review by delegating to an isolated code-reviewer agent.

Purpose

The review MUST be performed by a fresh agent with NO prior conversation context. This prevents confirmation bias - an agent that participated in the implementation unconsciously validates its own approach instead of questioning it.

<constraints> - Do not review the code yourself in the current context — confirmation bias from "having seen" the implementation is exactly what we're guarding against. - Delegate to an Agent (`subagent_type: "code-reviewer"`). - The agent receives only: ticket content, plan content, git diff, and project CLAUDE.md. No conversation history, no implementation reasoning, no debugging context. - The agent prompt must be fully self-contained (all text inline, no file paths to read). - Display the agent's review report verbatim — do not filter or soften findings. </constraints>

Inputs

Required context (gathered by YOU, passed inline to the agent):

• Ticket content (ticket.md text)
• Implementation plan (plan.md text)
• Git diff of changes
• Project CLAUDE.md (conventions)

Process

Step 1: Gather Context (you do this)

1. Read ticket from .claude-work/{ticket-id}/ticket.md -> TICKET_CONTENT
2. Read plan from .claude-work/{ticket-id}/plan.md -> PLAN_CONTENT
3. Read project CLAUDE.md from project root -> PROJECT_RULES
4. Get git diff and stats:

   git diff {base-branch}...HEAD
   git diff {base-branch}...HEAD --stat
   

Step 2: Delegate to Fresh Agent

Agent:
  subagent_type: code-reviewer
  description: "Fresh code review {ticket-id}"
  prompt: |
    You are reviewing code for ticket {ticket-id}.
    You have NO prior knowledge of this implementation. Review with fresh eyes.

    <ticket>
    {TICKET_CONTENT}
    </ticket>

    <implementation_plan>
    {PLAN_CONTENT}
    </implementation_plan>

    <project_conventions>
    {PROJECT_RULES}
    </project_conventions>

    <diff_stats>
    {DIFF_STATS}
    </diff_stats>

    <diff>
    {DIFF_CONTENT}
    </diff>

    Perform a complete code review following your review process.
    Return the full review report in markdown format.

Step 3: Present Results

Display the review report returned by the agent verbatim.

Step 4: Save Report

Write review report to .claude-work/{ticket-id}/review.md

Configuration

From .claude/ticket-config.json:

{
  "review": {
    "enabled": true,
    "auto_fix": false,
    "severity_threshold": "important",
    "block_on_critical": true
  }
}

Status Values

• pending: Review not yet started
• in_progress: Review in progress
• completed: Review finished successfully
• skipped: Review skipped (disabled or no implementation)
• failed: Review encountered an error

Integration

Invoked by /resolve workflow (step 08-review) or directly by the user.