New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Code Reviewer

by elithrar in elithrar/dotfiles

Review a specified code change for actionable defects. An agent skill from elithrar/dotfiles.

MITAuto-check passedDevelopment

Install Code Reviewer

skills CLI
$ npx skills add elithrar/dotfiles --skill code-reviewer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install elithrar/dotfiles code-reviewer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/elithrar/dotfiles.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/code-reviewer .claude/skills/code-reviewer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
code-reviewer
GitHub stars
202
Token cost
~1.1k tokens
SKILL.md length
595 words
Files
3
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Review a specified code change for actionable defects. An agent skill from elithrar/dotfiles.

  • Works in 8 steps: Read the applicable AGENTS.md and… → Resolve the exact review target and… → For a base-branch review, resolve the… → …
  • Uncommitted changes
  • SKILL.md covers Workflow, Validation, Review Focus and Finding Standard, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Code Reviewer is an agent skill from elithrar/dotfiles. Review a specified code change for actionable defects. Use for uncommitted changes, base-branch diffs, commits, PRs or MRs; review alone is read-only, and requested fixes follow the review. Not a repository-wide security or complexity audit.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `agents/openai.yaml` and `evals/evals.json`).

It sits in Development, covering Code review. The repository describes itself as: dotfiles for my macOS & Linux environments ⌨️. The licence is MIT.

When your agent uses it

  • Uncommitted changes
  • Base-branch diffs
  • Review alone is read-only
  • Requested fixes follow the review

Example prompts

  • “/code-reviewer”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Read the applicable AGENTS.md and repository review instructions.
  2. Resolve the exact review target and inspect the complete diff.
  3. For a base-branch review, resolve the requested base and compute its merge base with the review head. Prefer the remote-tracking ref of…
  4. Read enough surrounding implementation, tests, callers, and configuration to understand each changed path.
  5. Identify the intended behavior, preserved invariants, externally reachable paths, and highest-risk changes.
  6. Verify each candidate finding from code, relevant history, or the smallest diagnostic check that can confirm or disprove it.
  7. Continue through the complete diff after finding an issue.
  8. Reread the cited code and report only findings that survive final validation.

What it can do on your machine

Read from SKILL.md and the folder at commit 26e8a4b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Code Reviewer loads about 1.1k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 595 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from elithrar/dotfiles at commit 26e8a4b, republished under its MIT licence (© elithrar). 595 words, ~1,102 tokens.

Download SKILL.mdSave it as .claude/skills/code-reviewer/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
code-reviewer
description
Review a specified code change for actionable defects. Use for uncommitted changes, base-branch diffs, commits, PRs or MRs; review alone is read-only, and requested fixes follow the review. Not a repository-wide security or complexity audit.

Code Reviewer

Keep review-only requests read-only. When the user also requests fixes, a PR, or posted findings, complete the review and then perform the authorized follow-up. The skill does not authorize additional external actions.

Use the target named by the user. If no target is given, review uncommitted changes. If the working tree is clean, report that no uncommitted target exists rather than silently reviewing the last commit.

Review behavior introduced or materially affected by the change. Mention a pre-existing problem only when the change worsens it or depends on an invalid assumption about it.

Workflow

  1. Read the applicable AGENTS.md and repository review instructions.
  2. Resolve the exact review target and inspect the complete diff.
  3. For a base-branch review, resolve the requested base and compute its merge base with the review head. Prefer the remote-tracking ref of that base when it is ahead of its local ref; the feature branch's own upstream is not the base.
  4. Read enough surrounding implementation, tests, callers, and configuration to understand each changed path.
  5. Identify the intended behavior, preserved invariants, externally reachable paths, and highest-risk changes.
  6. Verify each candidate finding from code, relevant history, or the smallest diagnostic check that can confirm or disprove it.
  7. Continue through the complete diff after finding an issue.
  8. Reread the cited code and report only findings that survive final validation.

Validation

Prefer repository instructions and configured project commands. Run a targeted check only when it can confirm or disprove a candidate finding or material regression.

Do not install dependencies, invoke generic package runners that may download tools, or run broad suites solely because a manifest exists.

Attribute a failure to the reviewed change before presenting it as a finding. Otherwise report it as a verification limitation.

Review Focus

Look for meaningful, change-introduced defects involving:

  • Correctness and state transitions.
  • Authorization, validation, secrets, or data exposure.
  • Concurrency, persistence, retries, or partial failure.
  • Public contracts and compatibility.
  • Performance on reachable paths and realistic input sizes.
  • Maintainability only when the change creates concrete bug risk or costly coupling.

Spend the most depth on high-impact or externally reachable paths.

Do not report style preferences, speculative future concerns, intentional behavior changes, pre-existing problems, or mechanical issues already enforced reliably by configured tooling.

Show full SKILL.md (221 more words)Show less

Finding Standard

Report a finding only when all of these are true:

  • It affects correctness, security, performance, or maintainability meaningfully.
  • It is discrete and actionable.
  • It was introduced by the reviewed change.
  • The affected input, state, sequence, or call path can be demonstrated.
  • The author would probably fix it if they knew about it.

Cite the smallest changed line range that causes the issue. The cited range must overlap the reviewed diff. Explain the concrete scenario in the finding paragraph.

Drop speculative concerns and findings that cannot be tied to the reviewed change.

Review Passes

Use multiple focused passes when useful, but do not delegate unless the user or host workflow explicitly requests independent reviewers. Revalidate every compiled finding against the code. Disagreement is a reason to inspect further, not to choose the higher severity.

Output

Present findings first, ordered by priority. Use one entry per issue:

text
[P1] Imperative finding title — path/to/file.ts:42

Follow with one short paragraph describing the affected scenario and why the behavior is wrong. Add a fix direction only when it is not obvious.

  • P0: Universal release blocker or critical failure.
  • P1: Urgent defect that should be fixed next.
  • P2: Ordinary defect that should be fixed.
  • P3: Low-impact issue still worth fixing.

If no finding qualifies, say No findings. Then add a brief overall assessment and any material test gaps or residual risks.

© elithrar, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in .agents/skills/code-reviewer of elithrar/dotfiles.

  • SKILL.md
  • agents/openai.yaml
  • evals/evals.json

Open the folder on GitHubat commit 26e8a4b

Compare with similar skills

Code Reviewer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Code Reviewer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Code Reviewer this skillelithrar/dotfiles202—~1.1kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT
Backend Code Reviewlangflow-ai/langflow156k—~3.5kAutomated safety check: NotesMIT
Understand Diff AnalysisEgonex-AI/Understand-Anything86k1 repos~1.4kAutomated safety check: PassMIT
Mole Bug Patternstw93/Mole70k—~2kAutomated safety check: PassGPL-3.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed

  • Backend Code Review

    langflow-ai/langflow

    Review backend code for quality, security, maintainability, and best practices based on established checklist rules.

    156k GitHub stars~3.5k tokensUpdated today
    DevelopmentAuto-check: notes

  • Understand Diff Analysis

    Egonex-AI/Understand-Anything

    Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.

    86k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed

  • Mole Bug Patterns

    tw93/Mole

    A catalog of recurring bug shapes in the Mole Mac cleaner, used to review safety-sensitive diffs for deletion safety, unbounded commands, shell traps and weak tests.

    70k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed

  • Backend Code Review

    langgenius/dify

    Reviews backend code under api/ for concrete, reproducible defects, routes to rule packs for architecture, schema, repositories and SQLAlchemy, and ranks findings from P0 to P3.

    158k GitHub stars~676 tokensUpdated today
    DevelopmentAuto-check passed

More from elithrar/dotfiles

All 12 skills in this repo

  • Prompt Engineer

    elithrar/dotfiles

    Audit and revise system prompts, developer instructions, tool descriptions, and reusable LLM prompt templates.

    202 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Cut Ready

    elithrar/dotfiles

    Prepare or review CAD and vector artwork for physical fabrication, cutting, printing, or machining.

    202 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Logging Sucks

    elithrar/dotfiles

    Design or review structured application logging, canonical request events, correlation, redaction, and sampling.

    202 GitHub stars~720 tokensUpdated today
    Auto-check passed

  • Motronic

    elithrar/dotfiles

    Diagnose Porsche Carrera 3.2 Bosch Motronic faults and interpret DME ROMs or calibration changes.

    202 GitHub stars~753 tokensUpdated today
    Auto-check passed

  • Neo Industrial Design

    elithrar/dotfiles

    Design or restyle web interfaces in the user's neo-industrial or editorial-brutalist style.

    202 GitHub stars~940 tokensUpdated today
    Auto-check passed

  • Web Perf

    elithrar/dotfiles

    Diagnose page-load and interaction performance using browser traces, network evidence, and source code.

    202 GitHub stars~721 tokensUpdated today
    Auto-check passed

Categories

Questions about Code Reviewer

What does Code Reviewer do?

Review a specified code change for actionable defects. An agent skill from elithrar/dotfiles. Code Reviewer is an agent skill from elithrar/dotfiles. Review a specified code change for actionable defects.

When should I use Code Reviewer?

Code Reviewer fits situations like: uncommitted changes; base-branch diffs; review alone is read-only; requested fixes follow the review.

How do I install Code Reviewer in Claude Code?

Run `npx skills add elithrar/dotfiles --skill code-reviewer -a claude-code`. Or copy the skill folder (.agents/skills/code-reviewer in elithrar/dotfiles) into .claude/skills/code-reviewer in your project. Claude Code loads it when a task matches its description.

How do I install Code Reviewer in Codex?

Run `npx skills add elithrar/dotfiles --skill code-reviewer -a codex`. Or copy the skill folder (.agents/skills/code-reviewer in elithrar/dotfiles) into .agents/skills/code-reviewer in your project. Codex loads it when a task matches its description.

Can I use Code Reviewer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add elithrar/dotfiles --skill code-reviewer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-reviewer, .gemini/skills/code-reviewer, .github/skills/code-reviewer and .opencode/skills/code-reviewer in your project.

What does Code Reviewer need to run?

SKILL.md names no scripts, command-line tools or credentials: Code Reviewer is instructions for the agent only.

Does Code Reviewer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Code Reviewer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Code Reviewer use?

Code Reviewer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Code Reviewer use?

About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Code Reviewer?

Skills that share tags, products or a category with Code Reviewer: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Backend Code Review (langflow-ai/langflow, 156k stars) and Understand Diff Analysis (Egonex-AI/Understand-Anything, 86k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Code Reviewer?

elithrar (a GitHub user) maintains it in elithrar/dotfiles, which has 202 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 7, 2026.

Source: elithrar/dotfiles on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.