claude-skillz

Verify task completion before finishing work. Catches incomplete work, bugs, and quality issues.

Automatic code review on session stop with configurable rules

Periodic full codebase review using automatic-code-review rules. Reviews entire codebase, not just modified files.

Capture mistakes and improvement opportunities with automatic 5 whys analysis

Define collaboration style between Claude Code and user: step-by-step, deep-think, or pair programming

Analyze PR feedback patterns from CodeRabbit, SonarQube, and reviewers to suggest config updates that catch issues locally

Force critical evaluation of proposals from 5 adversarial perspectives (Skeptic, Pragmatist, Edge Case Hunter, Structural Critic, Root Cause Analyst)

Three-phase design review producing an ADR: Architect → Refiner → Critique → Interactive Review. Run /arc-review after to produce the ADR. Run /arc-prd to add architecture section to a PRD.

Two-agent optimization team: researcher proposes, critic challenges, lead presents synthesized result

Detects Claude Code version updates and surfaces relevant new features. SessionStart hook nudges on updates, /whats-new command analyzes changelog and blog for applicable changes.

Analyze session transcripts for optimization opportunities using 4 parallel subagents

Fetch CircleCI job logs via v1.1 API with step-level output and failure analysis