From superpowers-plus
Per-batch adversarial code review using 3 critic personas (Nitpick, Arch, Prod) scored on 5 dimensions each. Average < 8.0 triggers conditional pass or reject. Faster than full review, more rigorous than lint.
How this skill is triggered — by the user, by Claude, or both
Slash command
/superpowers-plus:micro-harsh-reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> **Wrong skill?** Full PR -> progressive-code-review-gate. Non-code -> progressive-harsh-review. Style -> enforce-style-guide.
Wrong skill? Full PR -> progressive-code-review-gate. Non-code -> progressive-harsh-review. Style -> enforce-style-guide.
Announce at start: "I am using the micro-harsh-review skill to review this change."
# Example: 3-critic scoring
echo "=== Micro Harsh Review: router pattern change ==="
echo "Critic 1 (Nitpick): 8/10 - case sensitivity concern"
echo "Critic 2 (Arch): 9/10 - minimal scope, pattern-local"
echo "Critic 3 (Prod): 7/10 - no collision test added"
echo "Average: 8.0 -> PASS (conditional: add collision test)"
Full access. START FROM the local diff. PRIORITIZE line-by-line syntax, naming, and surface-level correctness.
| Check | Score /10 | Notes |
|---|---|---|
| Off-by-one | ||
| Null handling | ||
| String comparison | ||
| Error messages | ||
| Variable naming |
Full access. START FROM interface contracts and public APIs. PRIORITIZE ripple analysis across callers and downstream consumers.
Respects patterns? /10 . Downstream impact? /10 . Minimal scope? /10 . 10x load? /10 . Reversible? /10
Full access. START FROM failure modes and state transitions. PRIORITIZE error handling, retry/rollback logic, and 3 AM operational safety.
Edge cases? /10 . Failure mode? /10 . Logging? /10 . Backward compat? /10 . Ship at 3 AM? /10
Average = (Nitpick + Arch + Prod) / 3
= 8.0 -> PASS
= 6.0 -> CONDITIONAL — fix flagged, re-review
| Anti-Pattern | Detection | Correction |
|---|---|---|
| Rubber-stamp | All scores 9-10, no notes | Find >=1 concern per critic |
| Inflated scores | Average > 9.0 consistently | Recalibrate with known-bad code |
| Critics agree | Same findings across all 3 | Force second-order critique: each must name ≥1 failure mode or cite a specific property of the change explaining why none exists (generic "it's straightforward" = rubber-stamp) |
| Review > coding time | >15 min for <20 lines | Top 3 risks only |
| Failure | Detection | Recovery |
|---|---|---|
| Rubber-stamp (all 10s) | No notes | Find >=1 concern per critic |
| Review > change time | >15 min for <20 lines | Top 3 risks only |
| Critics agree on everything | Same findings | Force second-order critique: name ≥1 plausible failure mode or cite specific change property explaining why none exists |
| Score inflation | Average > 9.0 consistently | Recalibrate with bad code |
npx claudepluginhub bordenet/superpowers-plus --plugin superpowers-plusGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.