- Home
- Skills
- Code Quality & Review
- pr review lite
pr review lite
Review Git diffs for critical logic errors and security vulnerabilities while ignoring style nits.
$5
Works with the AI Agents you already use
pr review lite
Example session with this skill installed
Review my staged changes for any security issues or logic errors.
- Read your context and instructions
- Compiled the pr review lite
I have analyzed the staged changes. Found two issues requiring attention before commit.
Code Review Findings
| Severity | File:Line | Issue | Suggested Fix |
|---|---|---|---|
| 🔴 High | auth.ts:42 | Hardcoded API secret found in the connection string. | Use process.env.STRIPE_SECRET_KEY instead of a string literal. |
| 🟡 Med | user_repo.py:112 | Unhandled None case when user ID does not exist in the cache. | Add an explicit check: if user is None: return fetch_from_db(id). |
Next steps
- Move the secret key to your
.envfile. - Implement the null check in the repository layer.
- Run the review again to confirm the fix.
Connects securely to your tools. The creator never sees your data.
About this skill
Code reviews are often delayed by nitpicks or missed by fatigue. This skill automates the detection of critical logic and security flaws in your Git diffs before they reach production.
What it does
- Diff analysis scans staged changes or provided PR diffs for immediate feedback.
- Logic validation identifies unhandled edge cases and flawed business logic.
- Security auditing flags SQL injection, XSS risks, and hardcoded secrets.
- Race condition detection spots potential concurrency issues in asynchronous code.
- Format filtering ignores style and syntax noise to focus exclusively on functional bugs.
How it works
- Fetch diff via
git diff --stagedor by ingestion of a provided pull request file. - Review the code against the internal criteria checklist for high-impact errors.
- Generate a structured report using a severity-based markdown table.
Frameworks & tools
This skill is language-agnostic and works with any Git-based workflow. It is designed to complement existing linters and CI pipelines.
Why this beats prompting it yourself
Generic prompts often return subjective style critiques or miss subtle logic flaws. This skill uses a strict checklist to enforce a high-signal, low-noise review that prioritizes security and execution over aesthetics.
Use cases
- Reviewing staged changes locally before running
git commit. - Auditing a team member's pull request for security vulnerabilities.
- Debugging complex logic flows in new feature branches.
Known limitations
Does not check for code style, formatting, or documentation completeness. Requires access to the Git diff.
Does not check for code style, formatting, or documentation completeness. Requires access to the Git diff.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 20 days ago
Requires