karsten-s-nielsen/mad-scientist-skills
Plugin Claude Code
Architecture auditing (beta), C4 architecture diagrams, cognitive interface auditing, two-tier security auditing, two-tier observability auditing (beta), optimization auditing, documentation auditing, and pre-commit quality gate for Claude Code.
karsten-s-nielsen/mad-scientist-skills
Plugin Claude Code
Architecture auditing (beta: Hexagonal/Ports & Adapters, Domain-Driven Design, Clean Architecture, SOLID principles, coupling/cohesion analysis, bounded context assessment), C4 architecture diagrams (Structurizr DSL), cognitive interface auditing (GOMS task models, Norman's Gulfs, Wood 7-layer error tolerance, Gergle…
karsten-s-nielsen/mad-scientist-skills
Command
Round 2+ review — confirm revisions landed, catch regressions, do not re-litigate.
karsten-s-nielsen/mad-scientist-skills
Command
Unbiased review of another session's implementation (diff, staged, or branch).
karsten-s-nielsen/mad-scientist-skills
Command
Unbiased review of another session's implementation plan.
karsten-s-nielsen/mad-scientist-skills
Command
Unbiased review of another session's spec or design doc.
karsten-s-nielsen/mad-scientist-skills
Skill Claude CodeCodex
Comprehensive architecture audit with two modes and a single tier (beta). Planning mode evaluates architectural patterns, bounded context decomposition, dependency direction, and SOLID compliance for new systems. Audit mode scans existing codebases for architectural drift, coupling violations, domain model quality…
karsten-s-nielsen/mad-scientist-skills
Skill Claude CodeCodex
Creates interactive C4 model architecture diagrams using Structurizr DSL — the official C4 notation by Simon Brown. Produces self-contained single-file HTML visualizations with embedded SVGs rendered locally via Java 21+ and the Structurizr export pipeline (structurizr.war + plantuml.jar). Generates System Context…
karsten-s-nielsen/mad-scientist-skills
Skill Claude CodeCodex
Comprehensive cognitive interface audit with two modes and a single tier. Planning mode designs task models, user expertise mapping, and error tolerance strategy. Audit mode evaluates mental model alignment (Norman's Gulfs), consistency (Gestalt), error tolerance (Wood 7-layer defense), cognitive load (NASA-TLX…
karsten-s-nielsen/mad-scientist-skills
Skill Claude CodeCodex
Comprehensive documentation audit with two modes and a single tier. Planning mode designs documentation strategy, content type maps, learning paths, and scaffolding architecture. Audit mode evaluates linguistic precision (Strunk & White, Google/Microsoft style guides), structural taxonomy (Diataxis quadrant…
karsten-s-nielsen/mad-scientist-skills
Skill Claude CodeCodex
Pre-commit quality gate — reviews all code and documentation for consistency, best practices, and completeness, then generates or updates the C4 architecture diagram. Use before committing, or when you want a thorough quality check of the project. Triggers on phrases like "final review", "pre-commit check", "review…
karsten-s-nielsen/mad-scientist-skills
Skill Claude CodeCodex
Pre-change measurement gate for perf-sensitive functions. Use BEFORE modifying any function that has a pytest-benchmark test, appears in a performance baselines file, or is flagged as a hot path in CLAUDE.md. Captures baseline median and p95, verifies the change does not regress beyond a configurable threshold…
karsten-s-nielsen/mad-scientist-skills
Skill Claude CodeCodex
Comprehensive observability audit with two modes and two tiers (beta). Planning mode designs telemetry strategy, SLIs/SLOs, and instrumentation architecture. Audit mode scans code and infrastructure for observability gaps including logging, metrics, tracing, alerting, pipeline monitoring, and ML model drift detection.…
karsten-s-nielsen/mad-scientist-skills
Skill Claude CodeCodex
Comprehensive optimization audit with two modes and a single tier. Planning mode designs performance strategy, capacity planning, and scaling architecture. Audit mode scans code and infrastructure for performance anti-patterns, inefficient algorithms, N+1 queries, missing caching, concurrency issues, and resource…
karsten-s-nielsen/mad-scientist-skills
Skill Claude CodeCodex
Comprehensive security audit with two modes and two tiers. Planning mode reviews architecture for security gaps (STRIDE threat modeling, auth design, data classification, AI regulatory compliance). Audit mode scans code, infrastructure, dependencies, and secrets for vulnerabilities. Covers OWASP Top 10, ML/AI model…
karsten-s-nielsen/mad-scientist-skills
Skill Claude CodeCodex
Use when reviewing a spec, plan, or implementation produced by another session - verifies its claims against the actual repo, grades TDD and hexagonal discipline, and reports severity-ranked findings without writing the fix. Triggers on "review this spec/plan/implementation", "second opinion on", "check this design"…