Back to catalog
Human reviewedDevelopment

Skill dossier

code-reviewer

Source declaration

Analyzes code diffs and files to identify bugs, security vulnerabilities (SQL injection, XSS, insecure deserialization), code smells, N+1 queries, naming issues, and architectural concerns, then produces a structured review report with prioritized, actionable feedback. Use when reviewing pull requests, conducting code quality audits, identifying refactoring opportunities, or checking for security issues. Invoke for PR reviews, code quality checks, refactoring suggestions, review code, code quality. Complements specialized skills (security-reviewer, test-master) by providing broad-scope review across correctness, performance, maintainability, and test coverage in a single pass.

The author's original description, preserved in English. It describes intent, not verified performance.

Analyzes code diffs and files to identify bugs, security vulnerabilities (SQL injection, XSS, insecure deserialization), code smells, N+1 queries, naming issues, and architectural concerns, then produces a structured review report with prioritized, actionable feedback. Use when reviewing pull requests, conducting code quality audits, identifying refactoring opportunities, or checking for security issues. Invoke for PR reviews, code quality checks, refactoring suggestions, review code, code quality. Complements specialized skills (security-reviewer, test-master) by providing broad-scope review across correctness, performance, maintainability, and test coverage in a single pass.

developmentreferences

Research summary

Human reviewed

Skill Atlas editorial review · editorial-preview-1.0.0

Reviews pull requests and code diffs for bugs, security issues, N+1 queries and design concerns, and returns a prioritized report with a verdict.

Review scope

Deterministic static analysis of collected SKILL.md and supporting text/code. Machine-assisted candidates and findings await human editorial review; no dynamic behavior or effect is assessed.

Observable capabilities

  • Summarizes the PR's intent in one sentence before reviewing.
  • Reviews structure, details, security and performance, including N+1 queries and injection risks.
  • Checks test coverage and whether tests assert behavior.
  • Produces a categorized report with critical, major and minor issues, praise and a final verdict.

Limitations & scope

  • Declares allowed-tools of Read, Grep and Glob, so it is a read-only reviewer that does not run code.
  • Findings come from reading, not from executing tests or tooling.
  • Deeper checklists and security coverage depend on reference files and the related security-reviewer skill.

Relevant for

  • Reviewers of pull requests
  • Teams running code quality audits
  • Authors self-reviewing before opening a PR

What ships with the skill

The file inventory comes from the collected source at the recorded commit. Paths and sizes are structural observations, not a measure of quality.

files
7
Markdown files
7
scripts
0
references
6
Size
32.3 KB
Structural complexity
Low

File inventory

PathTypeBytes
skills/code-reviewer/references/common-issues.mdReference2.9 KB
skills/code-reviewer/references/feedback-examples.mdReference3.4 KB
skills/code-reviewer/references/receiving-feedback.mdReference6.5 KB
skills/code-reviewer/references/report-template.mdReference3 KB
skills/code-reviewer/references/review-checklist.mdReference2.4 KB
skills/code-reviewer/references/spec-compliance-review.mdReference8.8 KB
skills/code-reviewer/SKILL.mdInstruction5.2 KB

SKILL.md frontmatter

{
  "name": "code-reviewer",
  "description": "Analyzes code diffs and files to identify bugs, security vulnerabilities (SQL injection, XSS, insecure deserialization), code smells, N+1 queries, naming issues, and architectural concerns, then produces a structured review report with prioritized, actionable feedback. Use when reviewing pull requests, conducting code quality audits, identifying refactoring opportunities, or checking for security issues. Invoke for PR reviews, code quality checks, refactoring suggestions, review code, code quality. Complements specialized skills (security-reviewer, test-master) by providing broad-scope review across correctness, performance, maintainability, and test coverage in a single pass.",
  "license": "MIT",
  "allowed-tools": "Read Grep Glob",
  "metadata": {
    "author": "https://github.com/Jeffallan",
    "company": "https://synergetic.solutions",
    "version": "1.1.0",
    "domain": "quality",
    "triggers": "code review, PR review, pull request, review code, code quality",
    "role": "specialist",
    "scope": "review",
    "output-format": "report",
    "related-skills": "security-reviewer, test-master, architecture-designer"
  }
}

A reading of the operating sequence

This workflow reconstructs the apparent sequence from source material. Unless controlled evaluation is explicitly recorded, it is provisional—not an observed trace.

  1. 01
    Input

    Gather context

    Read the PR description and summarize its intent in one sentence, asking the author if unclear.

  2. 02
    Action

    Review details

    Check code quality, security and performance, including N+1 queries, hardcoded secrets and injection risks.

  3. 03
    Decision

    Surface critical issues

    If critical issues are found, note them immediately instead of waiting until the end.

  4. 04
    Output

    Deliver the report

    Produce a report with summary, issues by severity, positive feedback, questions and a verdict.

Potential risk surfaces

Static findings identify points to inspect before installation. They do not establish that a skill is safe, malicious, or effective.

Attention recommended

16 deterministic lexical finding(s) require review across the collected text. Findings can occur in documentation and do not prove execution or exploitability; binary-only files were not scanned.

Network accessObserved
File writesObserved
Credential useObserved
Note

File modification is described or implemented

5 occurrences

This line contains a possible file-write or redirection operation. Check destination paths and overwrite behavior; the static review did not write any file. This rule matched 5 location(s) in the collected text; 3 representative location(s) are cited. Matching text may be documentation, and the analyzer did not execute it.

Medium

Network access is mentioned

10 occurrences

A URL or network client appears in this source line. Review destinations, data sent, and trust boundaries; static text cannot establish actual network activity. This rule matched 10 location(s) in the collected text; 3 representative location(s) are cited. Matching text may be documentation, and the analyzer did not execute it.

High

Credential or secret material is referenced

This line resembles a credential literal or reads a sensitive environment value. Do not expose its contents; verify whether it is a placeholder, required secret, or accidentally committed material. This rule matched 1 location(s) in the collected text; 1 representative location(s) are cited. Matching text may be documentation, and the analyzer did not execute it.

Editorial security note

Because it is limited to read-only tools this is low risk, but still confirm the allowed-tools setting is honored in your environment.

Where context can be spent

Discovery, activation, and resource layers have different meanings. Exact values appear only when the official token-counting method was run with a named model.

Exact token counts unavailable

All token values, including per-file inventory, are null until the pipeline performs an official exact count with an explicit model.

No token measurement was recorded with the required official method. This dossier does not substitute character counts, file sizes, or estimates.

Controlled evaluation

No controlled evaluation

This skill has only the evidence identified above. No task success, token efficiency, latency, or quality advantage is claimed.

Not tested

Use with the source in view

Install command
git clone https://github.com/Jeffallan/claude-skills.git cd claude-skills # Copy this skill directory into one of: # ~/.claude/skills/code-reviewer # .claude/skills/code-reviewer
  1. Open the pinned source at https://github.com/Jeffallan/claude-skills/blob/67c1961b180dc92cf08983344627109e983e8f51/skills/code-reviewer/SKILL.md.
  2. Review the license, prerequisites and all bundled reference files.
  3. Install the skill into a personal or project-level Claude Code skills directory.
  4. Restart or refresh Claude Code so the skill can be discovered.
Verify installation

Confirm code-reviewer/SKILL.md exists at the destination, then ask Claude Code to use the code-reviewer skill on a small test task.

Prerequisites

  • Declares allowed-tools of Read, Grep and Glob, so it is a read-only reviewer that does not run code.
  • Findings come from reading, not from executing tests or tooling.
  • Deeper checklists and security coverage depend on reference files and the related security-reviewer skill.

Example prompts

Representative task

Use the code-reviewer skill to review the changes on this branch against main, summarize the intent first, and give me a report with critical, major and minor issues and a verdict.

Inspect before use

Read the code-reviewer skill at https://github.com/Jeffallan/claude-skills/blob/67c1961b180dc92cf08983344627109e983e8f51/skills/code-reviewer/SKILL.md and its referenced files. Explain its workflow, required tools, permissions and the main risks before I decide whether to install it.

A decision, with its limits attached

Strengths

  • Tool access is limited to read-only operations.
  • Sets a respectful tone: acknowledge the author's reasoning and avoid nitpicking when linters exist.

Considerations

  • Cannot confirm behavior by running the code.
  • A single broad pass may miss specialized security or test-design issues.
Research conclusion

A well-scoped, read-only review skill that gives structured feedback but does not replace running tests or a dedicated security review.

Traceable by construction

The dossier is a time-bound reading of a public artifact, not an endorsement. Use the source link to inspect the exact upstream material.

Jeffallanclaude-skillsskills/code-reviewer
Source type
Community
Commit
67c1961b180dc92cf08983344627109e983e8f51
Collected
20 Nov 2026
Last checked
20 Nov 2026
Upstream license
MIT
Repository stars
12,464
Content basis

Deterministic lexical parsing, YAML frontmatter validation, file inventory, source-described workflow extraction, and heuristic provisional classification of the supplied files only. Generated by machine; no LLM, execution, dynamic testing, or human editorial approval.