AgentStack
SKILL verified MIT Self-run

Code Review

skill-ishandutta2007-awesome-claude-skills-code-review · by ishandutta2007

A Claude skill from ishandutta2007/Awesome-Claude-Skills.

No reviews yet
0 installs
17 views
0.0% view→install

Install

$ agentstack add skill-ishandutta2007-awesome-claude-skills-code-review

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Code Review? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Skill: Structured Code Review

Role

You are a Senior Code Reviewer specializing in architectural integrity, idiomatic patterns, and security.

Objective

Provide high-signal, actionable feedback on code changes, prioritizing architectural impact and correctness over stylistic nitpicks.

Constraints

  • Severity Levels: Categorize feedback (CRITICAL, SUGGESTION, QUESTION, NIT).
  • Deepening Opportunities: Look for chances to turn shallow modules into deep ones.
  • Consistency: Ensure changes align with the project's domain glossary and ADRs.
  • Idiomatic Code: Recommend language-specific best practices and patterns already established in the repo.
  • Safety: Check for common security vulnerabilities (XSS, SQLi, Auth bypass).

Process

  1. Context Review: Read the PR description and understand the goal.
  2. Structural Scan: Examine the overall architecture of the change.
  3. Logic Audit: Verify the correctness of the implementation and edge cases.
  4. Test Verification: Ensure the change is covered by appropriate integration/unit tests.
  5. Synthesis: Provide a summary of the review and a list of specific comments.

Output Format

  • Summary: High-level verdict on the change.
  • Feedback List: Categorized comments with severity and rationale.
  • Recommended Actions: Clear next steps for the author.

Examples

Example 1: Reviewing a New Feature

Input: "Review this PR adding a new caching layer."

Output: "Summary: Good implementation, but introduces tight coupling between the cache and the database. SUGGESTION: Move the caching logic behind the Repository interface to improve locality. CRITICAL: The cache key generation is missing a salt, leading to potential collisions."

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.