Claude Devstudio

Reduce cyclomatic complexity with targeted refactoring strategies

Scaffold component library structure with Storybook and documentation

Structured production incident workflow — gather symptoms, run diagnostics, correlate recent deploys, draft a timeline and incident report

Detect and fix testing anti-patterns for better test quality

Docker/container optimization for size, layers, caching, and security

Run a second-model quality gate on staged changes, a skill draft, or any generated output. A cheaper, independent model reviews the primary output for correctness, safety, and completeness before the user sees the final result.

Advanced GitHub automation via MCP GitHub server or gh CLI

Generate database migrations from schema changes

Automate complete release process with versioning and publishing

Audit and curate the 5-layer agent context hierarchy to prevent quality degradation mid-session — rules files, specs, source files, error output, and conversation history.

Extract repeated patterns from archived sessions and offer to convert them into reusable skills

Safe deployment rollback with health checks and database migration reversal

Performance profiling and bottleneck detection for Node.js, Python, and browser apps

Browser automation workflows with Playwright MCP integration

Unified pre-launch checklist + staged rollout strategy (0%→5%→25%→100%) + rollback triggers — consolidates deploy validation, canary monitoring, and rollback planning in one workflow.

Generate architecture diagrams in Mermaid, PlantUML, or diagrams.net formats

Generate context-aware code review checklists for changes

Scan skill files, CLAUDE.md, MCP configs, and agent prompts for prompt injection patterns

Gated 4-phase workflow (Specify → Plan → Tasks → Implement) where nothing advances without explicit human review — surfaces assumptions before any code is written.

Spawn a fresh adversarial reviewer mid-implementation for any non-trivial decision — branching logic, cross-module boundaries, irreversible operations — to catch what confirmation bias misses.

Full deprecation lifecycle for APIs, features, or internal code — Hyrum's Law analysis, deprecation notices, migration path design, and parallel-run execution strategy.

Fetch official docs before writing any framework-specific code — implement to documented patterns, cite the source, and flag any deviation from the official approach.

Enforce vertical-slice discipline — implement one thin slice (~100 lines max), test it, verify it works, commit it, then repeat. Never write more than can be tested in a single step.

Use Chrome DevTools MCP for live DOM inspection, console error capture, network request analysis, and paint profiling — runtime verification beyond what Playwright scripting covers.

Instrument code with structured logging, metrics, and OpenTelemetry tracing — define the on-call questions first, then work backward to the telemetry that answers them.