Skill Creator
pvillega
12 published skills · 132 GitHub stars across the catalog. View on GitHub ↗
architecture-discipline
Use when designing/modifying system architecture or evaluating technology choices. Enforces 7-section TodoWrite with 22+ items. Triggers: "design architecture", "system design", "architectural decision", "should we use [tech]", "compare [A] vs [B]", "add new service", "microservices", "database choice", "API design", "scale to [X] users", "infrastructure decision". If thinking ANY of these, USE THIS SKILL: "quick recommendation is fine", "obvious choice", "we already know the answer", "just need to pick one", "simple architecture question".
backend-reliability-enforcer
Use when implementing backend APIs, data persistence, or external integrations. Enforces TodoWrite with 25+ items. Triggers: "backend API", "REST endpoint", "external integration", "data persistence". If thinking "just a quick endpoint" - use this.
confidence-check
Use before implementing when uncertainty exists. Weighted scoring across 5 checks (requires ≥80%). Triggers: "before implementing", "verify readiness", "should I proceed", "am I ready". If thinking "this is overkill" - use it.
deployment-automation-enforcer
Use when designing deployment pipelines, CI/CD, terraform, or infrastructure automation. Enforces rollback checkpoint then TodoWrite with 19+ items. Triggers: "deploy", "CI/CD", "kubernetes", "terraform". If thinking "rollback later" - use this first.
duplicate-code-detector
Use when asked about code quality or duplication. Runs jscpd analysis for quantitative metrics and TDD refactoring plans. Triggers: "duplicate code", "code quality", "find clones", "copy-paste detection". If thinking "manual review is fine" - automate instead. NOTE: For "refactor" or "technical debt" → use this skill FIRST to identify targets, THEN use incremental-refactoring to implement changes.
edge-case-discovery
Use when user requests exhaustive edge case analysis. Enforces TodoWrite with 15+ items (5 categories). Triggers: "all edge cases", "what could break", "bulletproof", "failure modes". If thinking "main path is sufficient" - use this.
frontend-production-quality
Use before implementing UI changes or frontend PRs. Enforces TodoWrite with 18+ items. Triggers: "accessibility audit", "WCAG", "Lighthouse", "screen reader", "a11y", "NVDA", "VoiceOver", "keyboard navigation", "focus indicator". For "Core Web Vitals" in frontend/UI context, use this skill. For pure backend/API performance optimization, use performance-optimization instead. If thinking "WIP doesn't need this" - use it anyway.
incremental-refactoring
Use when IMPLEMENTING refactoring changes. Enforces metrics-driven protocol with before/after measurements. Triggers: "implement refactor", "apply refactoring pattern", "clean up code smell", "extract method", "move method". No exceptions for "simple" refactorings - use this. NOTE: If you need to FIND duplicates first, use duplicate-code-detector, then return here for implementation.
agent-creator
Use when creating agents. Routes to Simple (30-55 lines), Standard (100-300 lines), or Full (500+ lines) path based on complexity. Triggers: "create agent", "automate workflow". If thinking "just create basic agent" - that's valid for Simple path.
performance-optimization
Use when creating performance optimization plan for backend, API, or general system performance. Enforces BASELINE → PROFILE → OPTIMIZE → VALIDATE sequence. Triggers: "optimize API", "backend slow", "API latency", "database performance", "query optimization", "server response time". For "Core Web Vitals" in backend/API context, use this skill. For frontend UI accessibility + performance (WCAG, Lighthouse accessibility), use frontend-production-quality instead. If thinking "bottleneck is obvious" - profile first.
security-compliance-audit
Use for formal compliance audits requiring documentation (SOC2, PCI-DSS, HIPAA, GDPR, ISO 27001). Enforces TodoWrite with 20+ items. Triggers: "compliance audit", "regulatory assessment", "auditor documentation". NOT for casual PR checks. If thinking "ad-hoc review" - use this.
threat-modeling
Use when implementing auth, file uploads, payments, or external APIs. Applies STRIDE framework systematically. Triggers: "authentication", "file upload", "payment", "multi-tenant", "external API". If thinking "I know security" - use this anyway.