Stacks Documentation
SkillsChangelog
TeamSponsorsPartnersPostcardwareAwesome StacksContributing

Review

Copy page
Copy page as Markdown for LLMs
View as Markdown
View this page as plain text
Open in ChatGPT
Copy content and open ChatGPT
Open in Claude
Copy content and open Claude
Open in Perplexity
Search with Perplexity AI
On this page 4

stacks-review · Engineering craft · model-invoked

Two-axis review of a diff. Standards asks whether the code follows this repo's rules and stays clear of the Fowler smell baseline. Spec asks whether it does what was actually asked. The two are reported separately and never merged, because code can follow every rule while implementing the wrong thing.

When to reach for it

  • A PR
  • A branch
  • Staged work
  • The diff since a fixed point. Reviews on two axes
  • Standards (does it follow this repo's rules and avoid the smell baseline) and Spec (does it do what was asked)
  • Plus a test coverage audit and an auto-fix pass

Inside the skill

The sections an agent reads once the skill loads.

    1. Pin the scope
    1. Identify the spec source
    1. Run both axes
    1. Test coverage audit
  • Test coverage
    1. Auto-fix
  • Output
  • Standards
  • Spec
  • Test coverage
  • Summary
  • Rules

Using it

This one is model-invoked. Your agent reaches for it on its own when the task matches, and you can also call it by name:

/stacks-review

Source: stacks-review/SKILL.md. Shadow it for one project with app/Skills/stacks-review/SKILL.md, then re-run buddy setup:ai. See Writing your own.