CI-optimized code review: multi-agent parallel review with confidence scoring and atomic GitHub PR review posting. Runs 6 (lean) or 9 (full) specialized review agents including one unconstrained deep-reviewer, scores findings for confidence, filters false positives, and submits a single atomic GitHub PR review with inline comments via gh api. Supports --single for cost-effective single-agent reviews with confidence scoring, --agent profile for AI-authored PRs (surfaces more findings since fixes are cheap). Use --min-severity to control finding threshold. Use when reviewing PRs in CI pipelines, GitHub Actions workflows, or locally. Triggers: /ci-review, review PR, CI code review, automated PR review. Use --model to override the reviewer model (e.g., --model opus for deeper analysis). Use: /ci-review [focus text] [--full|--lean|--single] [--agent] [--model sonnet|opus] [--min-severity ]
Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI
Supported by the Atlas install prompt. Skill-specific requirements vary.
Skill stats
Skills1CategoryEngineeringStars0
About this skill
CI-optimized code review: multi-agent parallel review with confidence scoring and atomic GitHub PR review posting. Runs 6 (lean) or 9 (full) specialized review agents including one unconstrained deep-reviewer, scores findings for confidence, filters false positives, and submits a single atomic GitHub PR review with inline comments via gh api. Supports --single for cost-effective single-agent reviews with confidence scoring, --agent profile for AI-authored PRs (surfaces more findings since fixes are cheap). Use --min-severity to control finding threshold. Use when reviewing PRs in CI pipelines, GitHub Actions workflows, or locally. Triggers: /ci-review, review PR, CI code review, automated PR review. Use --model to override the reviewer model (e.g., --model opus for deeper analysis). Use: /ci-review [focus text] [--full|--lean|--single] [--agent] [--model sonnet|opus] [--min-severity ]
Quick start
Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
CI-optimized code review: multi-agent parallel review with confidence scoring and atomic GitHub PR review posting. Runs 6 (lean) or 9 (full) specialized review agents including one unconstrained deep-reviewer, scores findings for confidence, filters false positives, and submits a single atomic GitHub PR review with inline comments via gh api. Supports --single for cost-effective single-agent reviews with confidence scoring, --agent profile for AI-authored PRs (surfaces more findings since fixes are cheap). Use --min-severity to control finding threshold. Use when reviewing PRs in CI pipelines, GitHub Actions workflows, or locally. Triggers: /ci-review, review PR, CI code review, automated PR review. Use --model to override the reviewer model (e.g., --model opus for deeper analysis). Use: /ci-review <PR#> [focus text] [--full|--lean|--single] [--agent] [--model sonnet|opus] [--min-severity <level>]
About this listing
Category
Engineering
Reported license
MIT
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLI