review-pr

Solid

Comprehensive PR review -- full branch diff against base, commit-by-commit analysis, breaking change detection, conventional commit verification.

Code & Development 53 stars 9 forks Updated 2 days ago MIT

Install

View on GitHub

Quality Score: 88/100

Stars 20%
58
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Review PR Comprehensive code review of a pull request or branch diff against its base. Unlike review-delta (quick review of uncommitted local changes), this reviews ALL commits in a branch for PR submission readiness. **Token optimization:** Before starting, call `help(topic="graph")` for the full actions reference. Never include full files unless explicitly asked. ## Steps 1. **Identify the changes** for the PR: - If a PR number or branch is provided, use `git diff main...<branch>` to get changed files - Otherwise auto-detect from the current branch vs main/master 2. **Update the graph** by calling `graph(action="build", base="main")` to ensure the graph reflects the current state. 3. **Commit-by-commit analysis** (for PRs with >3 commits): - `git log --oneline main..HEAD` to list all commits - Group related commits by area (feature, fix, refactor, test, docs) - Verify each commit message follows Conventional Commits (`type(scope): description`) - Flag commits that mix unrelated changes 4. **Get the full review context** by calling `review(base="main")`: - Returns all changed files across all commits in the PR - Includes impacted nodes and blast radius 5. **Analyze impact** by calling `query(action="impact", base="main")`: - Review the blast radius across the entire PR - Identify high-risk areas (widely depended-upon code) 6. **Breaking change detection** for public APIs: - Identify exported/public functions, classes, types that ch...

Details

Author
n24q02m
Repository
n24q02m/better-code-review-graph
Created
2 months ago
Last Updated
2 days ago
Language
Python
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category