Skip to content
cccskills
FreePublished on GitHub

code-review

Review code for quality, bugs, and design issues. Use when the user says "review this code", "do a code review", "check this PR", "review this diff", "is this code good", "what's wrong with this code", "code quality check", or pastes code and wants feedback - even if they don't explicitly say "code review".

The English summary is being prepared. Showing the original description.

qa-aman/claude-skills
See how to install

Files included (1)

  • SKILL.md3.9 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Overview

Based on "Clean Code" by Robert C. Martin. Martin's central argument: code is read far more than it is written. Clean code reads like well-written prose - the reader can understand the intent without decoding it. A code review is not just a bug hunt - it's a check that the code communicates its intent clearly to the next developer who reads it.

Workflow

Step 1: Read for intent first

Before looking for bugs, read the code as a whole. Can you understand what it does without reading comments or documentation? If not, that's the first finding.

Step 2: Check naming

Martin's rule: names should reveal intent. Review every variable, function, and class name.

  • Does the name tell you what it does, not how it does it?
  • Would a new team member understand this name without context?
  • Are booleans named as predicates? (isValid, hasPermission, not flag, check)

Bad: d = datetime.now() - start Good: elapsed_time = datetime.now() - start

Step 3: Check function size and responsibility

Martin's single responsibility principle: a function should do one thing and do it well.

  • Functions longer than 20 lines are candidates for extraction
  • If a function needs a comment to explain what each section does, split it
  • If a function has multiple levels of abstraction mixed together, extract

Step 4: Check error handling

  • Are errors handled explicitly or silently swallowed?
  • Do error messages help the caller understand what went wrong and how to fix it?
  • Are exceptions used for exceptional cases only - not flow control?

Step 5: Check for duplication

Martin's DRY principle: duplication is the root of all evil in software.

  • Is this logic duplicated elsewhere in the codebase?
  • Could this be extracted to a shared utility?
  • Are magic numbers duplicated? (extract to named constants)

Step 6: Check tests

  • Are there tests for the new or changed behavior?
  • Do tests cover the happy path AND failure cases?
  • Are test names descriptive? (test_login_fails_with_invalid_password not test_login_2)

Step 7: Write the review

Structure feedback as:

  • Must fix - bugs, security issues, broken contracts
  • Should fix - Clean Code violations that will cause maintenance pain
  • Consider - style suggestions, optional improvements
  • Praise - what was done well (important for team morale and learning)

Anti-Patterns

1. Nitpicking style without flagging real issues Bad: 10 comments about variable naming, zero comments about a missing null check. Good: Prioritize by impact. Fix correctness first, then clarity, then style.

2. No positive feedback Bad: Only listing problems. Good: Note what was done well. Reviewers who only criticize produce defensive engineers.

3. Vague feedback Bad: "This function is too complex." Good: "This function does 3 things: validates input, transforms data, and saves to DB. Extract each into its own function so each can be read and tested independently."

4. Reviewing without running the code Bad: Approving a PR without checking it builds and tests pass. Good: CI should enforce this automatically. If CI is absent, run tests locally before approving.

Quality Checklist

  • Intent is clear - code reads without needing to decode it
  • Names reveal intent at every level (variables, functions, classes)
  • Functions have single responsibility and fit in one screen
  • Error handling is explicit - no silent failures
  • No unnecessary duplication - DRY applied
  • Tests cover happy path and failure cases
  • Must fix / should fix / consider clearly separated
  • At least one specific piece of positive feedback included

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

11-star-framework

Free

Rate any product, feature, or experience on the 11-star scale (Brian Chesky's Airbnb thought experiment). Use when user says "rate this experience", "11-star", "star rating", "experience audit", "how good is this", "experience rating", "product audit", "quality assessment", or wants to evaluate product quality and identify improvement paths. Also trigger when user wants to benchmark a feature, assess where a product stands, or map out what "great" looks like - even if they don't explicitly say "11-star".

The English summary is being prepared. Showing the original description.

qa-aman/claude-skills21Updated Oct 19, 2026

ab-copy-writer

Free

Generate A/B copy variants grounded in Eugene Schwartz's awareness and market-sophistication stages and John Caples' tested-headline discipline. Every variant declares its angle, the awareness stage it targets, and a falsifiable hypothesis, and the skill recommends which pair to test first and what delta counts as signal. Use when the user says "A/B test this", "write variants", "give me options", "test different angles", "copy variants", "ab copy", "test this headline", "multiple versions", "which version is better", or wants to test copy before publishing. For reviewing copy that already exists, see copy-review. For sample size and stopping rules, see growth-experiment. For diagnosing a page rather than its words, see page-cro. For full paid ad sets by platform, see ad-campaign-writer.

The English summary is being prepared. Showing the original description.

qa-aman/claude-skills21Updated Oct 19, 2026

ab-test-design

Free

Design statistically rigorous experiments to test data science hypotheses. Use when the user says "design an A/B test", "run an experiment", "test this hypothesis", "is this difference significant", "how many samples do I need", "randomized controlled trial", "causal inference", "uplift test", "holdout group", "significance test", "power calculation", "avoid p-hacking", or needs to determine whether an observed effect is real before making a product or model decision. For lean build-measure-learn product experiments without the statistics, use experiment-design instead.

The English summary is being prepared. Showing the original description.

qa-aman/claude-skills21Updated Oct 19, 2026

acceptance-criteria-writer

Free

Write measurable acceptance criteria for requirements or user stories. Use when the user says "write acceptance criteria", "definition of done", "how do we test this", "fit criteria", "given when then", "Gherkin scenarios", "what does done look like", "testable conditions", "how will we know this works" - even if they don't explicitly say "acceptance criteria".

The English summary is being prepared. Showing the original description.

qa-aman/claude-skills21Updated Oct 19, 2026

account-plan

Free

Build a strategic account plan for winning, retaining, or expanding a named account. Use when the user says "build an account plan", "strategic account planning", "how do I grow this account", "account expansion strategy", "whitespace analysis", "QBR prep", "key account review", "map the stakeholders in this account", "land and expand plan", "how do I break into [company]", or wants a structured strategy for a specific account.

The English summary is being prepared. Showing the original description.

qa-aman/claude-skills21Updated Oct 19, 2026

ad-campaign-writer

Free

Write paid ad copy for LinkedIn, Google, Meta, and YouTube. Produces multiple variants per platform, each targeting a different Eugene Schwartz awareness level and Cialdini persuasion principle. Use when the user asks for ad copy, ad variants, "write LinkedIn ads", Google ads, Meta ads, paid social copy, ad headlines, or wants creative for a paid campaign. Reads brand voice, ICP, and positioning from knowledge/. For organic social posts, see linkedin-post or social-calendar. For the landing page the ad points at, see landing-page-writer. For testing variants, see ab-copy-writer.

The English summary is being prepared. Showing the original description.

qa-aman/claude-skills21Updated Oct 19, 2026

See all skills by qa-aman

Report a problem with this skill