Agent skill

Code Review

by RunoreLab in RunoreLab/MahoShojo-Generator

A skill your agent uses when reviewing MahoShojo-Generator code, a branch, commit range, pull request, or implementation against current behavior and accepted ADR/spec requirements.

Apache-2.0Auto-check passedDevelopment

Install Code Review

skills CLI
$ npx skills add RunoreLab/MahoShojo-Generator --skill code-review -a claude-code

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

GitHub CLI
$ gh skill install RunoreLab/MahoShojo-Generator code-review --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/RunoreLab/MahoShojo-Generator.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/code-review .claude/skills/code-review && 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-review
GitHub stars
167
Token cost
~425 tokens
SKILL.md length
172 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when reviewing MahoShojo-Generator code, a branch, commit range, pull request, or implementation against current behavior and accepted ADR/spec requirements.

  • Works in 5 steps: Resolve the actual target branch/commit… → Read docs/AGENTS.md, docs/README.md, the… → Check especially → …
  • Reviewing MahoShojo-Generator code
  • SKILL.md covers Review priorities, Workflow and Verdict
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Code Review is an agent skill from RunoreLab/MahoShojo-Generator. Use when reviewing MahoShojo-Generator code, a branch, commit range, pull request, or implementation against current behavior and accepted ADR/spec requirements. Do not use when the primary request is to implement a known fix.

Its SKILL.md is about 430 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Architecture decision records, Code review and Pull requests. The repository describes itself as: 基于 AI 结构化生成的个性化魔法少女角色生成器。 The licence is Apache-2.0.

When your agent uses it

  • Reviewing MahoShojo-Generator code
  • Implementation against current behavior and accepted ADR/spec requirements
  • The primary request is to implement a known fix

Example prompts

  • “/code-review”

Workflow steps

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

  1. Resolve the actual target branch/commit range and current repository facts before comparing with docs.
  2. Read docs/AGENTS.md, docs/README.md, the relevant topic page, and applicable accepted ADR/spec only for the affected domain.
  3. Check especially
  4. Report findings ordered by severity with file/behavior evidence, impact, and a concrete closure criterion.
  5. Distinguish confirmed defects from design questions and optional cleanup. Do not inflate style preferences into blockers.

What it can do on your machine

Read from SKILL.md and the folder at commit e7e8d4b. 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 Review loads about 425 tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 172 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~425

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 RunoreLab/MahoShojo-Generator at commit e7e8d4b, republished under its Apache-2.0 licence (© RunoreLab). 172 words, ~425 tokens.

Download SKILL.mdSave it as .claude/skills/code-review/SKILL.md (or your agent's skills folder).
name
code-review
description
Use when reviewing MahoShojo-Generator code, a branch, commit range, pull request, or implementation against current behavior and accepted ADR/spec requirements. Do not use when the primary request is to implement a known fix.

Code Review

Review priorities

Find behavior, security, data, compatibility and migration regressions. Lint/format problems that CI can mechanically report are not primary findings unless they reveal a deeper defect.

Workflow

  1. Resolve the actual target branch/commit range and current repository facts before comparing with docs.
  2. Read docs/AGENTS.md, docs/README.md, the relevant topic page, and applicable accepted ADR/spec only for the affected domain.
  3. Check especially:
    • accepted MUST/MUST NOT requirements;
    • illegal app→app, package→app, cross-runtime deep imports, or client→server-secret dependencies;
    • credential leakage, increased client trust, or server-authority bypass;
    • API/DTO/schema/wire changes without synchronized producer/consumer/adapter/compatibility tests;
    • migrations, release, secrets, permissions or cutover paths missing fail-closed behavior, rollback, idempotency or auditability;
    • tests that prove only compilation/happy path while missing the actual regression risk.
  4. Report findings ordered by severity with file/behavior evidence, impact, and a concrete closure criterion.
  5. Distinguish confirmed defects from design questions and optional cleanup. Do not inflate style preferences into blockers.

Verdict

When useful, end with an overall Block, Changes required, or Looks good with minor follow-ups assessment tied to the requested scope.

© RunoreLab, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/code-review of RunoreLab/MahoShojo-Generator.

Open the folder on GitHubat commit e7e8d4b

Compare with similar skills

Code Review 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 Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Code Review this skillRunoreLab/MahoShojo-Generator167—~425Automated safety check: PassApache-2.0
Review GitHub PRNVIDIA/OpenShell15k—~1.7kAutomated safety check: PassApache-2.0
Dsh Code ReviewZhou-Yujing114514/deepseek-harness-linux118—~2.1kAutomated safety check: PassMIT
Code Review Responsewado-lang/wado117—~1.5kAutomated safety check: PassMIT
Alego Code Reviewsingula-ai/alego109—~2.4kAutomated safety check: PassMIT
Grill Menrwl/nx29k—~1.2kAutomated safety check: PassMIT

Similar skills

  • Review GitHub PR

    NVIDIA/OpenShell

    Official

    Review a GitHub pull request by summarizing its diff and key design decisions.

    15k GitHub stars~1.7k tokensUpdated today
    DevelopmentAuto-check passed
  • Dsh Code Review

    Zhou-Yujing114514/deepseek-harness-linux

    A skill your agent uses when reviewing a pull request in the deepseek-harness repo — orients the reviewer to this codebase's standards (AGENTS.md conventions, defensive patterns, ADRs, quality…

    118 GitHub stars~2.1k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Code Review Response

    wado-lang/wado

    How to answer code review feedback — a human reviewer, CodeRabbit, or any review bot.

    117 GitHub stars~1.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Alego Code Review

    singula-ai/alego

    A skill your agent uses when reviewing a pull request in the alego repo — orients the reviewer to this codebase's standards (AGENTS.md conventions, defensive patterns, ADRs, quality gates) and the…

    109 GitHub stars~2.4k tokensUpdated 9 days ago
    DevelopmentAuto-check passed
  • Grill Me

    nrwl/nx

    Grill the user relentlessly about a plan, design, decision, or set of review findings — working the decision tree in rounds until nothing is left silently assumed.

    29k GitHub stars~1.2k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • 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

More from RunoreLab/MahoShojo-Generator

  • API Contract Change

    RunoreLab/MahoShojo-Generator

    A skill your agent uses when changing API/DTO/schema/wire-format contracts, SSE/event payloads, shared protocol packages, or producer/consumer mappings across MahoShojo-Generator runtimes.

    167 GitHub stars~362 tokensUpdated today
    Auto-check passed
  • Platform Migration

    RunoreLab/MahoShojo-Generator

    A skill your agent uses for platform-rearchitecture, runtime migration, hosted/local routing changes, storage/session/DR migrations, or staged movement between old and new application boundaries in…

    167 GitHub stars~423 tokensUpdated today
    Auto-check passed
  • Release Readiness

    RunoreLab/MahoShojo-Generator

    A skill your agent uses when preparing or reviewing a MahoShojo-Generator version release, release candidate, changelog/docs readiness, deployment impact, migration notes, or final pre-release…

    167 GitHub stars~342 tokensUpdated today
    Auto-check passed

Categories

Questions about Code Review

What does Code Review do?

A skill your agent uses when reviewing MahoShojo-Generator code, a branch, commit range, pull request, or implementation against current behavior and accepted ADR/spec requirements. Code Review is an agent skill from RunoreLab/MahoShojo-Generator. Use when reviewing MahoShojo-Generator code, a branch, commit range, pull request, or implementation against current behavior and accepted ADR/spec requirements.

When should I use Code Review?

Code Review fits situations like: reviewing MahoShojo-Generator code; implementation against current behavior and accepted ADR/spec requirements; the primary request is to implement a known fix.

How do I install Code Review in Claude Code?

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

How do I install Code Review in Codex?

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

Can I use Code Review 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 RunoreLab/MahoShojo-Generator --skill code-review -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-review, .gemini/skills/code-review, .github/skills/code-review and .opencode/skills/code-review in your project.

What does Code Review need to run?

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

Does Code Review 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 Review 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 Review use?

Code Review is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Code Review use?

About 425 tokens (SKILL.md is roughly 1.7k 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 Review?

Skills that share tags, products or a category with Code Review: Review GitHub PR (NVIDIA/OpenShell, 15k stars), Dsh Code Review (Zhou-Yujing114514/deepseek-harness-linux, 118 stars), Code Review Response (wado-lang/wado, 117 stars) and Alego Code Review (singula-ai/alego, 109 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Code Review?

RunoreLab (a GitHub organization) maintains it in RunoreLab/MahoShojo-Generator, which has 167 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 8, 2026.

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