requesting-code-review

Verifies git diffs with static security scans, baseline tests, and independent reviewer subagents before commit.

1|Updated Jun 24, 2026
One-click install
npx skills add https://github.com/maopujie10-sys/Bailongma --skill requesting-code-review-maopujie10-sys
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: requesting-code-review
Source: https://github.com/maopujie10-sys/Bailongma/tree/main/skills/hermes-skills/software-development/requesting-code-review
Command: npx skills add https://github.com/maopujie10-sys/Bailongma --skill requesting-code-review-maopujie10-sys

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code changes often get committed without independent verification, letting security flaws, logic errors, and regressions slip through because the same agent that wrote the code also reviewed it. ## Core Features & Use Cases - Static Security Scanning: Greps added diff lines for hardcoded secrets, shell injection, eval/exec, unsafe pickle deserialization, and SQL injection patterns. - Baseline-Aware Quality Gates: Runs pytest, npm test, cargo test, or go test plus linters like ruff, mypy, eslint, and clippy, comparing against a pre-change baseline so only new failures block the commit. - Independent Reviewer Subagent: Delegates the diff to a fresh-context reviewer via delegate_task with fail-closed JSON verdicts, then runs an auto-fix loop of up to two cycles before committing with a [verified] prefix. - Use Case: After implementing a feature touching multiple files, trigger this pipeline before git push to catch a leaked API key and a new test regression, auto-fix them, and commit only after the independent reviewer passes. ## Quick Start Ask the agent to verify and review my staged changes before committing them.

Frequently Asked Questions about requesting-code-review

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

FAQPage Schema
How do I review code changes before committing with git?

Stage your changes with git add, then run this verification pipeline. It extracts the diff via git diff --cached, scans for security issues, runs tests against a baseline, and dispatches an independent reviewer subagent before allowing the commit.

What security issues does pre-commit code review detect?

The static scan greps added diff lines for hardcoded secrets and API keys, shell injection via os.system or subprocess shell=True, eval/exec calls, pickle deserialization, and SQL injection through string-formatted queries. Any match is fed to the reviewer as a blocking concern.

How is this different from reviewing GitHub pull requests?

This skill verifies your own local changes before committing, while github-code-review comments on other people's PRs on GitHub. Use this one pre-commit; use the GitHub variant for inbound PR review with inline comments.

Does the verification work without a test framework installed?

Yes. If no test framework is detected, the regression check is skipped and the reviewer verdict still runs. Missing lint tools like ruff or eslint are also skipped silently rather than failing the pipeline.

What happens when the auto-fix loop keeps failing?

The pipeline allows a maximum of two fix-and-reverify cycles using a separate fix agent. If verification still fails after two attempts, it escalates to the user with the remaining issues and suggests git stash or git reset to undo the changes.