gds-code-review

Reviews code changes with parallel adversarial review layers and structured triage.

Updated Mar 14, 2026
One-click install
npx skills add https://github.com/ArchaonHW/MingGoRTS --skill gds-code-review-archaonhw
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gds-code-review
Source: https://github.com/ArchaonHW/MingGoRTS/tree/main/.agents/skills/gds-code-review
Command: npx skills add https://github.com/ArchaonHW/MingGoRTS --skill gds-code-review-archaonhw

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code reviews often miss subtle bugs, edge cases, or deviations from the spec because a single reviewer has one perspective. This Skill runs an adversarial multi-layer review of your code changes and triages every finding into actionable categories, so nothing slips through and no noise wastes your time. ## Core Features & Use Cases - Parallel Adversarial Review Layers: Launches a Blind Hunter (diff only, no context), an Edge Case Hunter (diff plus project access), and an Acceptance Auditor (diff against spec) to catch different classes of issues. - Structured Triage: Normalizes, deduplicates, and classifies findings into decision_needed, patch, defer, or dismiss buckets, then writes them into the story file and a deferred-work log. - Flexible Diff Sources: Reviews uncommitted changes, staged changes, branch diffs, commit ranges, or user-provided diffs, with optional sprint-status integration to auto-detect stories awaiting review. - Use Case: After finishing a feature branch, ask for a code review; the Skill gathers the diff, runs three review layers in parallel, presents triaged findings, applies approved patches, and updates the story and sprint status. ## Quick Start Ask the assistant to run a code review on your current branch changes against main.

Frequently Asked Questions about gds-code-review

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

FAQPage Schema
How do I run an adversarial code review on my changes?

Trigger the workflow by asking to run a code review, then choose a diff source such as uncommitted changes, staged changes, a branch diff, or a commit range. The Skill constructs the diff, launches parallel review layers, and triages the findings.

What review layers does this code review workflow use?

It uses three parallel layers: a Blind Hunter that sees only the diff, an Edge Case Hunter with project read access, and an Acceptance Auditor that checks the diff against a spec file. Findings from all layers are merged, deduplicated, and classified.

Can I review code without a spec or story file?

Yes, the workflow supports a no-spec mode where the Acceptance Auditor layer is skipped. Findings that would need a human decision are reclassified as patch or defer, and results are presented without being written to a story file.

What happens if a review subagent fails or returns nothing?

The failed layer name is recorded and the review continues with the remaining layers. If zero findings survive triage while any layer failed, the workflow warns that the review may be incomplete instead of declaring a clean pass.

Does the code review update story and sprint status automatically?

Yes, when a spec file and story key are available, the workflow sets the story status to done or in-progress based on the outcome and syncs the matching entry in sprint-status.yaml. Without a story key, only the story file is updated.