code-review

Reviews a git diff against coding standards and the originating spec using parallel sub-agents.

Updated Feb 22, 2024
One-click install
npx skills add https://github.com/tlipoca9/dotfiles --skill code-review-tlipoca9
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/tlipoca9/dotfiles/tree/main/home/dot_agents/skills/code-review
Command: npx skills add https://github.com/tlipoca9/dotfiles --skill code-review-tlipoca9

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Reviewing a branch or PR requires checking two separate things at once: whether the code follows the repo's documented standards and whether it actually implements what the issue or spec asked for. Doing both in one pass lets one concern mask the other, so findings get lost or misranked. ## Core Features & Use Cases - Two-axis review: Runs a Standards review (documented repo conventions plus a fixed Fowler code-smell baseline) and a Spec review (requirements coverage, scope creep, wrong implementations) as parallel sub-agents, then reports them side by side without merging or reranking. - Fixed-point diffing: Compares HEAD against any user-supplied commit, branch, tag, or merge-base using a three-dot git diff, validating the ref and non-empty diff before spawning reviewers. - Spec discovery: Locates the originating spec from issue references in commit messages, a user-provided path, or spec files under docs/, specs/, or .scratch/. - Use Case: Before merging a feature branch, ask for a review since main and receive separate Standards and Spec reports, each citing the violated rule or spec line, with a one-line summary per axis. ## Quick Start Ask the assistant to review the changes since main on the current branch using the code-review skill.

Frequently Asked Questions about code-review

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

FAQPage Schema
How do I review all changes on a branch since main?▼

Provide the fixed point (for example main, a tag, or a commit SHA) and the skill runs git diff with three-dot syntax against HEAD. It then spawns two parallel sub-agents covering standards and spec, and aggregates their findings under separate headings.

What coding standards does an automated code review check?▼

It checks whatever the repo documents, such as CODING_STANDARDS.md or CONTRIBUTING.md, plus a fixed baseline of Fowler code smells like Duplicated Code, Feature Envy, and Shotgun Surgery. Documented repo standards always override the baseline.

Can code review verify a diff against the original issue or spec?▼

Yes, the Spec axis locates the originating spec from issue references in commit messages, a user-provided path, or files under docs/, specs/, or .scratch/. It reports missing requirements, scope creep, and incorrect implementations, quoting the spec line for each finding.

What happens if there is no spec for the changes being reviewed?▼

If no spec is found and the user confirms none exists, the Spec sub-agent is skipped and the final report notes that no spec was available. The Standards review still runs normally against the diff.

Why does the review fail before the sub-agents start?▼

The skill validates the fixed point with git rev-parse and confirms the diff is non-empty before spawning reviewers. An unresolvable ref or empty diff fails fast at that step rather than inside the parallel sub-agents.