Skip to content

andrsj/validation-architecture-skill

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 

Repository files navigation

validation-architecture-review

A Claude Code plugin shipping a single skill that reviews Go code against opinionated best practices for validation in clean / onion / hexagonal architecture.

Each rule is its own file with motivation, code smells, good/bad examples, a review checklist, and primary sources. At review time, one subagent per actionable rule runs in parallel, so each check is focused on a single principle and the main context stays small.

Important

This skill is explicit-trigger only and review-only. It does not auto-activate on .go files, and it never applies fixes unless you explicitly ask it to. Findings are presented as recommendations you can accept, reject, or discuss.

Install

Option 1 — Via the marketplace (recommended)

Inside any Claude Code session:

/plugin marketplace add andrsj/validation-architecture-skill
/plugin install validation-architecture-review@andrsj-skills
/reload-plugins

The skill appears namespaced as /validation-architecture-review:review.

Option 2 — --plugin-dir (for development / live-edit)

git clone https://github.com/andrsj/validation-architecture-skill.git
claude --plugin-dir ./validation-architecture-skill

Edits to any skill file pick up live with /reload-plugins.

Option 3 — Standalone copy (no namespace)

git clone https://github.com/andrsj/validation-architecture-skill.git
cp -R validation-architecture-skill/skills/review ~/.claude/skills/validation-architecture-review
# then edit ~/.claude/skills/validation-architecture-review/SKILL.md — change `name: review` to `name: validation-architecture-review`

The skill then activates as /validation-architecture-review (un-namespaced).

What's inside

  • skills/review/SKILL.md — the index + review workflow
  • skills/review/rules/NN-*.md — one file per rule (7 total)

Categories

Category Count Meaning
actionable 5 Generates findings during review
tooling 1 Verifies the schema/validator is wired up, no code findings
philosophical 1 Informs judgment, no findings emitted

How a review works

  1. Main agent identifies the .go files in scope.
  2. For each actionable rule, dispatch a subagent with the rule file and the file list.
  3. Each subagent loads only its own rule file, reads the code, and returns findings as <file>:<line> — <observation> or the literal no findings.
  4. Main agent groups results by rule and produces the final report.
  5. Recommendations only — the skill never edits code. If you want fixes, ask explicitly.

You can also ask for a partial review (e.g. "check only #2 and #4") or a single-rule explanation.

The 7 rules

See skills/review/SKILL.md for the full index with links to each rule file.

Sources

Rule content is synthesized from:

Every rule file lists its own sources at the bottom.

Related

Sister plugins/skills by the same author:

License

MIT — see LICENSE.

About

Claude Code skill for reviewing Go code against validation best practices in clean / onion / hexagonal architecture. 7 rules, explicit-only, review-only.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors