skills.rest
vib795
vib795COMMUNITY
Explore all skills by this author →
WebsiteGitHub

ce-review

Coordinate parallel reviewer personas and consolidate findings into a code review report.

Updated Apr 16, 2026
Search Tags:#automation#code-review#json-output#agent-based#diff-scope#risk-routing
One-click install
npx skills add https://github.com/vib795/copilot-anatomy --skill ce-review-vib795
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ce-review
Source: https://github.com/vib795/copilot-anatomy/tree/main/.github/skills/ce-review
Command: npx skills add https://github.com/vib795/copilot-anatomy --skill ce-review-vib795

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Structured code review using tiered persona agents, confidence-gated findings, and a merge/dedup pipeline to streamline PR reviews.

Core Features & Use Cases

  • Spawn always-on reviewers and optional cross-cutting/CE agents to inspect diffs
  • Merge and deduplicate findings into a single report with routing guidance
  • Support diff scope across PRs, branches, or standalone work, with modes interactive/autofix/report-only/headless
  • Integrates with plan discovery and project standards when available to validate intent and requirements

Quick Start

Run ce-review on the current checkout to generate a synthesized code review report.

Frequently Asked Questions about ce-review

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

FAQPage Schema
How do I automate code review for a pull request diff?▼

Automated code review is performed by orchestrating parallel reviewer personas that inspect PR diffs, consolidate findings, and produce a single deduplicated report with specific routing decisions and actionable residuals.

What is the best way to deduplicate code review findings from multiple reviewers?▼

Deduplicating code review findings is handled by a merge pipeline that consolidates outputs from parallel reviewer personas into a single synthesized report, ensuring confidence-gated findings remain unique and actionable.

Can I run code review in headless or report-only mode for my branch changes?▼

Code review supports configurable modes including interactive, autofix, report-only, and headless, allowing you to process standalone branch changes or PR diffs without manual intervention.

Does structured code review work without external dependencies?▼

Structured code review operates with zero external dependencies, coordinating tiered persona agents natively to validate project intent and generate JSON-formatted findings based on the current checkout.

How does agent-based code review handle risk routing and confidence gating?▼

Agent-based code review applies risk routing by evaluating confidence levels of findings from spawned reviewer personas, filtering out low-confidence noise and directing actionable residuals to the consolidated report.

When do I need JSON output for my code review process?▼

JSON output for code review is needed when integrating findings into downstream CI/CD pipelines, requiring a structured Code Review Findings schema to parse reviewer-specific results and routing decisions automatically.

Related Skills

Explore More Software Engineering Skills→
SeventeenthEarthSeventeenthEarth

17th-pr-summary

Generate standardized PR titles and summaries from git diffs and commit history.

Community
Basic
RDEWAIRDEWAI
5

validate-pipeline

Validate YAML CI/CD pipeline files for syntax, stages, and security.

Official
Intermediate
KrismithReddy12KrismithReddy12

health

Calculate a weighted 0-10 code quality score from linters and test runners.

Community
Advanced
hsigstadhsigstad

style-review

Review prose against academic writing standards using a linter and language model.

Community
Intermediate