Code Review Excellence

Software development skill, available on Zeplik

Code Review Excellence is a ready-to-run software development skill on Zeplik. Not for review of your own branch (use requesting-code-review). Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer.

The Code Review Excellence skill loads automatically when your request matches it, or you can invoke it directly by typing /code-review-excellence in any chat. It works with attachments, connectors, and any model that supports the task, so you get the same expert method every time without setting anything up.

What the Code Review Excellence skill can do

Try these prompts on Zeplik

Pick a prompt to open it in the Zeplik app. If you are not signed in yet, your prompt is waiting for you the moment you do.

How the Code Review Excellence skill works

/code-review-excellence

Review the code the user shares directly. Read the diff, find the real problems, and say what matters — no process performance.

Answer directly. Give the review, not a description of how you'll review. Do not impose phases, time-boxes, generic checklists, or templates unless the user explicitly asks for a reusable checklist or team standard. Match depth to the size of the change: a 20-line diff gets a few sharp comments, not a four-phase audit.

What actually matters in a review

Look for real defects, in roughly this priority:

  • Correctness — edge cases, off-by-one, null/undefined, race conditions, wrong logic.
  • Security — unvalidated input, injection (SQL/command/XSS), authz gaps, leaked secrets or PII.
  • Resource/performance — N+1 queries, unbounded loops/allocations, blocking I/O on hot paths, leaks.
  • Maintainability — unclear names, functions doing too much, magic numbers, missing error handling.
  • Tests — do they cover the risky paths, and do they assert behavior rather than internals?

Skip anything a linter/formatter owns (style, imports, trivial typos). Don't rewrite working code to your taste.

How to phrase comments

Be specific and actionable, about the code not the person, and flag the good parts too. Prefix each comment with a severity label so the author can triage:

  • [blocking] must fix before merge (bugs, security holes)
  • [important] should fix, open to discussion
  • [nit] minor, non-blocking
  • [suggestion] an alternative worth considering
  • [praise] genuinely good work

Point at the concrete failure, then offer the fix:

[blocking] This query interpolates userId into the SQL string — injectable. Use a parameterized query.

[nit] uc → userCount reads clearer. Not blocking.

End with a clear verdict — approve, comment, or request-changes — and the one or two things that drive it. If the intent, tests, or CI status you'd need to judge a change aren't in what the user pasted, ask for them rather than guessing.

For requesting a review or responding to feedback on your own branch, defer to requesting-code-review / receiving-code-review.

/code-review-excellence $ARGUMENTS

How to use the Code Review Excellence skill

  1. Sign in to Zeplik

    Create a free Zeplik account or sign in. New accounts start with free credits, so you can try the Code Review Excellence skill right away.

  2. Describe your software development task

    Ask in plain language, or type /code-review-excellence to invoke the skill directly. Zeplik recognizes the Code Review Excellence skill and applies its method.

  3. Review and refine the result

    Zeplik returns a clear, structured answer. Ask follow-ups in the same chat to refine it or take the next step.

Source and credit

Author
wshobson
License
MIT

Adapted from the open-source wshobson/agents project and tuned to run natively on Zeplik. View source on GitHub.

Frequently asked questions

What is the Code Review Excellence skill?
Code Review Excellence is a ready-to-run software development skill on Zeplik. Not for review of your own branch (use requesting-code-review). Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer.
How do I use Code Review Excellence on Zeplik?
Sign in to Zeplik and ask in plain language, or type /code-review-excellence in any chat to invoke it directly. The skill applies its method and returns a result you can refine in the same conversation.
Which AI model does the Code Review Excellence skill use?
Any model you choose. Zeplik works across every model in one chat, so the Code Review Excellence skill runs on your preferred model for the task.
Where does the Code Review Excellence skill come from?
The Code Review Excellence skill is adapted from the open-source wshobson/agents project (MIT) and tuned to run natively on Zeplik. The original source is linked on this page.
How much does the Code Review Excellence skill cost?
Using the skill is free to start. You only spend Zeplik credits when the assistant runs, and new accounts begin with free credits.

Related software development skills

More on Zeplik

Try Code Review Excellence on Zeplik

Every model, one chat. Bring the Code Review Excellence skill into your next conversation and let the assistant do the work.

Browse all skills
Code Review Excellence - Software development skill for Zeplik AI | Zeplik Chat