LaunchKit · 2026
Back to Skills

sovereign-code-review-helper

A comprehensive code review assistant that generates review checklists tailored.

0
333 downloads
by @ryudi84

Setup & Installation

openclaw skills install @ryudi84/sovereign-code-review-helper

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install sovereign-code-review-helper

What This Skill Does

Scans changed files in a git repository and generates review checklists tailored to each file type, covering security vulnerabilities, performance bottlenecks, style consistency, and test coverage gaps. Supports Python, JavaScript, TypeScript, Go, Rust, Java, SQL, Bash, and Ruby. Also generates ready-to-use PR review templates in minimal, standard, or thorough styles.

A single command covers security, performance, style, and test checks across nine languages, replacing a patchwork of separate linters and manual review checklists.

When to use it

  • Catching hardcoded secrets before merging an auth feature branch
  • Generating a thorough PR review template for a critical database migration
  • Running security-only checks on files matching a specific path pattern
  • Posting automated review comments to GitHub PRs in a CI/CD pipeline
  • Producing a JSON report of critical-severity issues to block a merge automatically

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: Review my feature/payments branch against main

AGENT
  1. 1Runs git diff between main and feature/payments to collect changed files
  2. 2Detects file types in the diff and selects the relevant check modules
  3. 3Scans for security patterns (injection, secrets, missing validation), performance issues (N+1 queries, unbounded lists), style violations, and missing tests
  4. 4Ranks findings by severity: critical, warning, or info
  5. 5Outputs a markdown checklist ready to paste into a pull request review
OUTPUT

Markdown checklist categorized by security, performance, style, and tests, with severity labels for each finding