agentsclimarketplace

Devteam review

Skill michael-harris/devteam/skills/devteam-review

Run a coordinated code review across multiple reviewers. Launches the Code Review Coordinator to orchestrate language-specific and domain-specific reviewers.From its SKILL.md

Install
npx -y skills add michael-harris/devteam --skill devteam-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 20 stars20 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.2 KB, as published. Nobody here has run it

Current session: !source "${CLAUDE_PLUGIN_ROOT}/scripts/state.sh" && get_current_session 2>/dev/null || echo "No active session" Active sprint: !source "${CLAUDE_PLUGIN_ROOT}/scripts/state.sh" && get_kv_state "active_sprint" 2>/dev/null || echo "None" Failure count: !source "${CLAUDE_PLUGIN_ROOT}/scripts/state.sh" && get_kv_state "consecutive_failures" 2>/dev/null || echo "0"

DevTeam Review Command

Command: /devteam:review [target] [options]

Run a coordinated code review across multiple reviewers. Launches the Code Review Coordinator to orchestrate language-specific and domain-specific reviewers.

Usage

# Review current changes (staged + unstaged)
/devteam:review

# Review specific files
/devteam:review "src/api/auth.ts" "src/models/user.ts"

# Review specific scope
/devteam:review --scope "src/api/"

# Review with specific focus
/devteam:review --focus security
/devteam:review --focus performance
/devteam:review --focus architecture

# Review a PR
/devteam:review --pr 42

Options

OptionDescription
--scope <path>Limit review to specific files/directories
--focus <area>Focus on: security, performance, architecture, correctness, all
--pr <number>Review a specific pull request
--severity <level>Minimum severity to report: critical, warning, info
--ecoCost-optimized execution

Your Process

Phase 0: Initialize Session

source "${CLAUDE_PLUGIN_ROOT}/scripts/state.sh"
source "${CLAUDE_PLUGIN_ROOT}/scripts/events.sh"

SESSION_ID=$(start_session "/devteam:review $*" "review")
log_session_started "/devteam:review $*" "review"

Phase 1: Launch Code Review Coordinator

Delegate to the orchestration:code-review-coordinator agent, which will:

  1. Detect languages and frameworks in the target files
  2. Select appropriate language-specific code reviewers
  3. Run database reviewers if schema changes are detected
  4. Aggregate findings across all reviewers
  5. Produce a unified review report with severity ratings
const result = await Task({
    subagent_type: "orchestration:code-review-coordinator",
    prompt: `Code review request:

        Target: ${target || 'current changes'}
        Scope: ${scope || 'auto-detect'}
        Focus: ${focus || 'all'}

        Coordinate reviewers to check:
        1. Code correctness and logic errors
        2. Security vulnerabilities
        3. Performance issues
        4. Code style and best practices
        5. Test coverage gaps
        6. Documentation needs`
})

Phase 2: Report

Output a review report showing:

  • Summary of findings by severity
  • File-by-file review comments
  • Recommended changes
  • Overall code quality assessment

See Also

  • /devteam:implement - Implement review feedback
  • /devteam:bug - Fix bugs found during review
  • /devteam:test - Run tests to verify fixes

Keep looking

Skills are one crate of 627,801. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.