Agent skill

Mz PR Review

by MaterializeInc in MaterializeInc/materialize

Local code review of current branch vs Materialize standards.

Custom licenceAuto-check: notesDevelopment

Install Mz PR Review

skills CLI
$ npx skills add MaterializeInc/materialize --skill mz-pr-review -a claude-code

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

GitHub CLI
$ gh skill install MaterializeInc/materialize mz-pr-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/MaterializeInc/materialize.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/mz-pr-review .claude/skills/mz-pr-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
mz-pr-review
GitHub stars
6.4k
Token cost
~1.6k tokens
SKILL.md length
748 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
Custom licence

At a glance

Local code review of current branch vs Materialize standards.

  • Works in 5 steps: Parse arguments from: $ARGUMENTS — a PR… → Get the diff using the first method that… → Get the file list from the same diff… → …
  • Tasks that involve Pull requests
  • SKILL.md covers Steps, Review checklist, One semantic change rule and Rules
  • Calls gh, git and cargo

What it does

Mz PR Review is an agent skill from MaterializeInc/materialize. Local code review of current branch vs Materialize standards. Trigger: "review my code", "review my changes", "check my diff", "does this look ok", "what do you think of this PR", "code review", or look over changes before merging. Also PR number + wants feedback on quality, style, correctness.

Its SKILL.md is about 1.6k 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 Pull requests, Code review and SQL. It works with SQL, Rust, Git and PostgreSQL. The repository describes itself as: The live data layer for apps and AI agents. Create up-to-the-second views into your business, just using SQL.

When your agent uses it

  • Tasks that involve Pull requests
  • Tasks that involve Code review
  • Tasks that involve SQL

Example prompts

  • “review my code”
  • “review my changes”
  • “check my diff”
  • “/mz-pr-review”

Requirements

  • Pre-approved tools (allowed-tools): Bash, Read, Grep, Glob, Task

Workflow steps

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

  1. Parse arguments from: $ARGUMENTS — a PR number, base branch, or nothing.
  2. Get the diff using the first method that works
  3. Get the file list from the same diff (add --stat for git, --stat for jj, or gh pr diff 123 --stat for PR).
  4. Review the diff against the checklists below.
  5. Present findings organized as: Blocking, Strong suggestions, Nits.

What it can do on your machine

Read from SKILL.md and the folder at commit 6515d14. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Grep
    • Glob
    • Task

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh
    • git
    • cargo

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

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    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

Mz PR Review loads about 1.6k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 748 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~77
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Grep, Glob, Task

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 748 words (~1,617 tokens).

“Perform a local code review of the current branch's changes against Materialize project standards.”

— opening of SKILL.md by MaterializeInc, Custom licence
name
mz-pr-review
allowed-tools
Bash, Read, Grep, Glob, Task
argument-hint
base-branch

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .agents/skills/mz-pr-review of MaterializeInc/materialize.

Open the folder on GitHubat commit 6515d14

Compare with similar skills

Mz PR 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.

Mz PR Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Mz PR Review this skillMaterializeInc/materialize6.4k—~1.6kAutomated safety check: NotesCustom licence
Coding Agentmastra-ai/mastra29k—~2.3kAutomated safety check: PassCustom licence
SeekDB Code Reviewoceanbase/seekdb3.1k—~2.1kAutomated safety check: PassApache-2.0
Resolve PR Reviewshencangsheng/easydb_app590—~2.4kAutomated safety check: PassMIT
Citus Backportcitusdata/citus13k—~3.2kAutomated safety check: PassAGPL-3.0
Diesel Guardayarotsky/diesel-guard121—~3.1kAutomated safety check: PassMIT

Similar skills

  • Coding Agent

    mastra-ai/mastra

    Authoring playbook for building agents that write, edit, review, or refactor code.

    29k GitHub stars~2.3k tokensUpdated today
    DevelopmentAuto-check passed
  • SeekDB Code Review

    oceanbase/seekdb

    Reviews seekdb pull requests and diffs for real defects in correctness, resources, concurrency, security and tests, reporting only Blocker or Major findings.

    3.1k GitHub stars~2.1k tokensUpdated today
    DevelopmentAuto-check passed
  • Resolve PR Review

    shencangsheng/easydb_app

    Resolve pull request code review comments end-to-end. An agent skill from shencangsheng/easydb_app.

    590 GitHub stars~2.4k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Citus Backport

    citusdata/citus

    Backport one or more merged citusdata/citus main commits/PRs onto the active release branches.

    13k GitHub stars~3.2k tokensUpdated yesterday
    DatabasesAuto-check passed
  • Diesel Guard

    ayarotsky/diesel-guard

    Lints Diesel and SQLx Postgres migrations for unsafe schema changes that lock tables or cause downtime, and authors custom Rhai checks.

    121 GitHub stars~3.1k tokensUpdated 11 days ago
    DatabasesAuto-check passed
  • SQL Code Review

    totvs/engpro-advpl-tlpp-skills

    Universal SQL code review assistant that performs comprehensive security, maintainability, and code quality analysis across SQL databases (PostgreSQL, SQL Server, Oracle).

    143 GitHub stars~3.5k tokensUpdated 4 days ago
    DatabasesAuto-check passed

More from MaterializeInc/materialize

All 15 skills in this repo
  • Mz Release Signoff

    MaterializeInc/materialize

    Verify a release candidate on the Grafana dashboards and sign off in release.

    6.4k GitHub stars~7.2k tokensUpdated today
    Auto-check passed
  • Mz Benchmark

    MaterializeInc/materialize

    Add/modify/debug Materialize perf benchmark scenarios. An agent skill from MaterializeInc/materialize.

    6.4k GitHub stars~2.8k tokensUpdated today
    Auto-check passed
  • Mz Commit

    MaterializeInc/materialize

    Trigger: "commit", "prepare commit", "create PR", "push", "open pull request", or mentions committing, pre-commit checks, pull requests in Materialize.

    6.4k GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Mz Dbt Release

    MaterializeInc/materialize

    Cut a dbt-materialize PyPI release: bump the version in version.py and setup.py, date the Unreleased CHANGELOG entry, and open the release PR with a Ship: <url body.

    6.4k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Mz Debug CI

    MaterializeInc/materialize

    Investigate CI failures on PR via gh + Buildkite MCP or bk CLI.

    6.4k GitHub stars~3.9k tokensUpdated today
    Auto-check passed
  • Mz Limits Test

    MaterializeInc/materialize

    Add/modify/debug limits test. An agent skill from MaterializeInc/materialize.

    6.4k GitHub stars~808 tokensUpdated today
    Auto-check passed

Categories

Questions about Mz PR Review

What does Mz PR Review do?

Local code review of current branch vs Materialize standards. Mz PR Review is an agent skill from MaterializeInc/materialize. Local code review of current branch vs Materialize standards.

When should I use Mz PR Review?

Mz PR Review fits situations like: tasks that involve Pull requests; tasks that involve Code review; tasks that involve SQL.

How do I install Mz PR Review in Claude Code?

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

How do I install Mz PR Review in Codex?

Run `npx skills add MaterializeInc/materialize --skill mz-pr-review -a codex`. Or copy the skill folder (.agents/skills/mz-pr-review in MaterializeInc/materialize) into .agents/skills/mz-pr-review in your project. Codex loads it when a task matches its description.

Can I use Mz PR 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 MaterializeInc/materialize --skill mz-pr-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/mz-pr-review, .gemini/skills/mz-pr-review, .github/skills/mz-pr-review and .opencode/skills/mz-pr-review in your project.

What does Mz PR Review need to run?

Going by SKILL.md and its folder, Mz PR Review needs the command-line tools its instructions call (gh, git and cargo). Its frontmatter pre-approves these tools: Bash, Read, Grep, Glob, Task.

Does Mz PR Review access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Mz PR Review safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Mz PR Review use?

Mz PR Review has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Mz PR Review use?

About 1.6k tokens (SKILL.md is roughly 6.5k 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 Mz PR Review?

Skills that share tags, products or a category with Mz PR Review: Coding Agent (mastra-ai/mastra, 29k stars), SeekDB Code Review (oceanbase/seekdb, 3.1k stars), Resolve PR Review (shencangsheng/easydb_app, 590 stars) and Citus Backport (citusdata/citus, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mz PR Review?

MaterializeInc (a GitHub organization) maintains it in MaterializeInc/materialize, which has 6,377 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 9, 2026.

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