From spec-superflow
Reviews completed implementation batches for spec compliance and code quality. Dispatches a reviewer subagent and acts on feedback with severity-based prioritization.
How this skill is triggered — by the user, by Claude, or both
Slash command
/spec-superflow:code-reviewerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Two responsibilities: requesting review (dispatching a reviewer subagent) and receiving review (acting on feedback with technical rigor). **Review early, review often. Verify before implementing feedback.**
Two responsibilities: requesting review (dispatching a reviewer subagent) and receiving review (acting on feedback with technical rigor). Review early, review often. Verify before implementing feedback.
Mandatory after: each task in SDD, each major feature, each execution batch, before merge. Optional: when stuck, before refactoring, after fixing complex bugs.
BASE_SHA=$(git rev-parse HEAD~1) and HEAD_SHA=$(git rev-parse HEAD)general-purpose subagent using template at skills/code-reviewer/code-reviewer-prompt.md[DESCRIPTION] (what was built), [PLAN_OR_REQUIREMENTS] (contract/spec reference), [BASE_SHA], [HEAD_SHA]| Level | Meaning | Action |
|---|---|---|
| Critical | Bugs, security, data loss, broken functionality | Fix immediately |
| Important | Architecture problems, missing features, poor error handling, test gaps | Fix before next batch |
| Minor | Code style, optimization, documentation polish | Note for later |
Never: performative agreement ("You're right!", "Great point!"), blind implementation before verification, thanking the reviewer. Instead: restate the requirement, ask clarifying questions, push back with reasoning, or just fix it (actions > words).
If any item is unclear → STOP. Do not implement anything yet. Ask for clarification on unclear items. Partial understanding = wrong implementation.
From user: Trusted — implement after understanding. Still ask if scope unclear. No performative agreement.
From external reviewer: Before implementing, check: technically correct for this codebase? breaks existing functionality? reason for current implementation? works on all platforms? reviewer understands full context? If suggestion seems wrong, push back with technical reasoning.
Suggestion breaks existing functionality, reviewer lacks context, violates YAGNI, technically incorrect for this stack, legacy/compatibility reasons, conflicts with user's architectural decisions. Push back with technical reasoning, not defensiveness.
| Mistake | Fix |
|---|---|
| Performative agreement | State requirement or just act |
| Blind implementation | Verify against codebase first |
| Batch without testing | One at a time, test each |
| Assuming reviewer is right | Check if breaks things |
| Avoiding pushback | Technical correctness > comfort |
| Partial implementation | Clarify all items first |
scripts/review-package. Empty diff = nothing to reviewnpx claudepluginhub magebyte-zero/spec-superflow --plugin spec-superflowDispatches code-reviewer subagent using git SHAs for reviews after tasks, major features, or before merging to verify requirements.
Dispatches code-reviewer subagent to evaluate code changes via git SHAs after tasks, major features, or before merging, with focused context on implementation and requirements.
Requests code review by dispatching a subagent with git diff context. Use after completing tasks, major features, or before merging to catch issues early.