viktorbezdek

Finds and fixes bugs through systematic root cause analysis, stack trace interpretation, browser DevTools automation, CI/CD pipeline debugging, performance profiling, test pollution detection, and AI-powered error analysis. Use when the user asks to debug, fix a bug, investigate an error, analyze a stack trace, find root cause of a failure, profile performance, diagnose test failures (unit/integra

Loop workflow for making real progress on a legacy codebase without breaking production. Starts by generating a codemap so you actually understand what exists (documentation-generator), identifies feedback-center modules (systems-thinking), gets a second perspective on areas you'll touch (code-review), builds a test safety net before any changes (test-driven-development), plans changes with rollba

Apply RICE, MoSCoW, ICE, and effort-impact frameworks to rank options and decide what to work on next. Use when the user asks to prioritize a backlog, rank features, decide what to build first, apply RICE or MoSCoW scoring, cut scope, or compare items by effort vs impact. NOT for defining success metrics or OKRs (use outcome-orientation). NOT for making a strategic bet under uncertainty (use strat

Use when evaluating a Claude Code plugin or single SKILL.md and a verdict is needed — ship-ready, needs improvement, or rework. Multi-pass audit workflow that composes plugin-dev's structural validation, plugin-evaluation's activation and output measurement, and skill-foundry's anti-pattern audit to grade quality across five dimensions: structure, activation reliability, content discipline, output

This skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm architecture", "coordinate multiple agents", or mentions multi-agent patterns, context isolation, agent handoffs, sub-agents, or parallel agent execution. NOT for agent memory or persistence (use memory-systems), NOT for tool design or tool interfaces (use tool-design), NOT fo

Analyze trade-offs between competing product options using cost-benefit, opportunity cost, reversibility (one-way vs two-way doors), and second-order effects. Use when the user faces a product choice with non-trivial trade-offs, asks "what are we giving up", weighs short-term vs long-term impact, or needs to frame a decision before committing. NOT for scored prioritization of a backlog (use priori

Test framework router and infrastructure setup across multiple languages and platforms. Use when the user asks to choose a test framework, scaffold test infrastructure, add focused unit/integration/E2E/accessibility coverage, or integrate tests into CI/CD. Covers Rust, TypeScript/React, PHP/TYPO3, Shell, Playwright, accessibility, mutation, and fuzz testing as selectable modules. NOT for TDD metho

Identify what users actually need using functional/emotional/social jobs, needs-vs-wants laddering, latent-need surfacing, and job statements. Use when the user asks what users truly need, wants to write a job statement (When/I-want-to/So-I-can), wants to move past stated wants to underlying needs, needs to separate functional jobs from emotional or social ones, or wants to spot latent needs the u

Narrative-build workflow for turning data, technical results, or project outcomes into a compelling story for leadership, investors, or customers. Structures the narrative using proven story frameworks — 3-act, SparkLines, situation-complication-resolution (storytelling), finds the surprising angle through lateral thinking and reframing (creative-problem-solving), anchors every claim to measurable

Loop workflow for debugging a complex issue you've been stuck on for more than 30 minutes. Runs systematic hypothesis formation (debugging skill), feedback-loop mapping when the bug looks like a dynamic problem (systems-thinking), context-pathology check when it's an LLM/agent bug (context-degradation), blast-radius assessment before any fix attempt (risk-management), and uses test-driven-developm

Decide what and when to write down, and produce Architecture Decision Records (ADRs), one-pagers, runbooks, and decision logs. Use when the user asks whether something should be documented, wants to write an ADR, needs a runbook or operational playbook, wants to keep a decision log, or is trying to decide between a one-pager and an RFC. NOT for auto-generating docs from code (use documentation-gen

Design formal knowledge models — classes, properties, relationships, hierarchies, and semantic graphs — for knowledge representation and reasoning. Use when the user asks to build an ontology, design a knowledge graph, model entity relationships formally, define class hierarchies, create a taxonomy for semantic reasoning, or structure data for RDF/OWL. NOT for CMS content types, editorial workflow