pydantic/monty · Archived

review-general

Review the current branch against its merge base for bugs, CPython divergence, sandbox escapes, resource-limit escapes, performance regressions, verbose comments and missing ./limitations/ or docs/ updates. Use for a general pre-merge review of a branch or PR.

First seen Aug 23, 2026

Installation

$ npx skills add pydantic/monty --skill review-general

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from pydantic/monty.

npx skills add pydantic/monty

Browse all from pydantic/monty

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 8.1K
License LICENSE
Default branch main
Open issues 69
Status Archived

Skill metadata

Parsed from SKILL.md frontmatter.

Declared agents claude-code

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 2,024 B
  • docs SUMMARY.md 282 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 1 installs

SKILL.md

General branch review

git diff --stat origin/main...HEAD   # scope first
git diff origin/main...HEAD

Read the changed files in full — a hunk is rarely enough to judge correctness. Look for:

  • Bugs — logic errors, DropWithContext values not released on every exit path (the

fix is deferdrop!/DropGuard, not more dropwith calls), borrow/aliasing mistakes, unhandled error paths.

  • CPython divergence — different results, exception types or messages, missing

attributes. Check anything you're unsure of with python-playground.

  • Sandbox escapes — sandboxed code reaching the host filesystem, environment,

network or subprocesses.

  • Resource-limit escapes — allocations not charged to the tracker (an unbounded or

amplifying String build without StringBuilder), unbounded loops, recursion without a depth guard.

  • Performance — regressions the branch introduces, and improvements you spot.
  • Verbose comments — docstrings and comments should be concise as per CLAUDE.md.
  • Cleanups — duplication, misplaced logic, functions grown too complex.
  • ./limitations/ — a new divergence with no entry is a finding.
  • Docs parity — a user-visible change reflected in only one of README.md, docs/,

limitations/ and the crate READMEs is a finding. CLAUDE.md "Documentation surfaces that must stay in sync" has the obligation table. For a full pass, delegate to the docs-parity-reviewer subagent.

Report

Concise, most severe first. Per finding: file:line, what's wrong, the concrete failure it causes. Don't pad with what the branch got right.

Report only, unless the user asks for fixes.