Stats
Actions
Tags
From dodi-dev
Use after implementation is complete and before creating a PR — agent-driven code review checking spec compliance, code quality, security, and regression risk
How this skill is triggered — by the user, by Claude, or both
Slash command
/dodi-dev:reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Comprehensive agent-driven code review. Run after implementation, before PR.
Comprehensive agent-driven code review. Run after implementation, before PR.
| Category | What to Look For |
|---|---|
| Spec compliance | Does the code implement what was specified? Nothing missing, nothing extra |
| Code quality | Clean, idiomatic, follows project conventions (CLAUDE.md, style guides) |
| Security | Injection, auth bypass, data leaks, OWASP top 10 |
| Regression risk | Does this change break assumptions in callers/consumers? |
| Error handling | Silent failures, swallowed exceptions, missing edge cases |
| API contracts | If touching APIs — are request/response shapes backwards-compatible? |
git diff <base>...HEAD)dodi-dev:submit"Tests pass" is not a review. Tests verify behavior; review verifies intent, quality, and risk.
npx claudepluginhub dodi-hq/dodi-skills --plugin dodi-devValidates code changes against original plan using git diffs and full file reads, then launches parallel subagents for quality, security, and test coverage checks. Use post-implementation or /recheck.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.