Skip to content
TrustedSkillsbeta
Back to all skills

Review Quality

Checked
heyvhuang·vlatest·frontend·MIT

Evaluates text reviews based on clarity, relevance, sentiment, and helpfulness, providing actionable improvement suggestions.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add heyvhuang/ship-faster --skill review-quality -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

heyvhuang

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned heyvhuang/ship-faster at 64047d24e0.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
64047d24e0
Manifest
skills/review-quality/SKILL.md
Scanned
2 files, 243 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The Review Quality skill provides a unified review process to determine if code changes are ready for merging or production deployment. It combines three perspectives: merge readiness (alignment with requirements, risk assessment, and verification), code maintainability based on Clean Code principles, and documentation consistency between the codebase and associated documentation. This skill aims to streamline reviews and reduce decision fatigue by automatically triaging review lenses.

When to use it

  • As a standard part of the Ship Faster review process – always run this skill first.
  • When evaluating changes that might impact React/Next.js performance.
  • When UI surface changes are introduced, ensuring adherence to Web Interface Guidelines (accessibility, focus management, forms, motion, and content overflow).
  • For reviews where documentation consistency is a key concern.

Key capabilities

  • Unified Review Lens: Combines merge readiness, code maintainability, and documentation consistency into a single review.
  • Auto-Triage: Automatically determines which specialized review lenses to apply based on the diff content.
  • React/Next.js Performance Risk Detection: Identifies changes that may impact React/Next.js performance and suggests running review-react-best-practices.
  • Web Interface Guidelines Audit: Checks UI code against Web Interface Guidelines, providing concise file:line findings.
  • Docs-Only Change Optimization: Focuses the review on documentation consistency and release risk when changes are limited to documentation files.

Example prompts

  • "Review these changes for merge readiness."
  • "Evaluate this pull request's code maintainability."
  • "Check if these UI changes adhere to accessibility guidelines."

Tips & gotchas

  • Input Requirements: For best results, provide BASE_SHA and HEAD_SHA representing the diff being reviewed. Optional inputs like PLAN_OR_REQUIREMENTS path, docs scope, and run_dir can further refine the review.
  • Auto-Triage Limitations: The auto-triage system uses predefined rules to determine which additional reviews to run; these rules are not customizable by the user.
  • Performance Keyword Detection: The React/Next.js performance check relies on keyword detection within the diff, which might not be exhaustive.