madappgang/magus
57 skills
$npx skills add madappgang/magusSkillInstalls
adr-documentationArchitecture Decision Records (ADR) documentation practice. Use when documenting architectural decisions, recording technical trade-offs, creating decision…agent-coordination-disciplineUse when deciding whether to launch an agent, selecting which agent to use, or coordinating multiple agents.agent-modelChoose the browser-use agent brain LLM per task. Use when picking a model or provider for retry_with_browser_use_agent or a cloud session, or when the user…api-designUse when designing REST or GraphQL APIs, defining endpoints, implementing pagination/filtering, handling API versioning, or establishing API documentation with…auditOn-demand security and code quality audit. Use when checking for vulnerabilities, security issues, code smells, or compliance problems.auth-patternsUse when implementing authentication (JWT, sessions, OAuth), authorization (RBAC, ABAC), password hashing, MFA, or security best practices for backend services.browser-debuggingTests UI in a real browser, validates design fidelity with AI vision, monitors console, and tracks network via Chrome MCP.browser-use-integrationDetects the browser-use@magus plugin and captures screenshots of URL-based references.bunjsProvides Bun.js/Hono patterns — HTTP endpoints, Prisma/SQLite, Zod validation, Bun test. Use when building a Bun.js service or wiring Hono routes with Prisma.bunjs-apidogUse when creating OpenAPI specs for Bun.js APIs, integrating with Apidog, documenting endpoints with schemas, or automating API specification imports via…bunjs-architectureProvides Bun.js clean architecture patterns — routes/controllers/services/repositories, camelCase conventions, Prisma schemas.bunjs-productionProvides Bun.js production patterns — Docker, AWS ECS/Fargate, Redis caching, security hardening, CI/CD.code-roastRoasts code with severity-graded sins, cites file:line, and offers redemption in a humorous tone.compareProvides the compare.ts CLI invocation pattern, semantic comparison prompt template, severity thresholds, and model selection guide for UI design comparison.context-detectionUse when detecting project technology stack from files/configs/directory structure, auto-loading framework-specific skills, or analyzing multi-stack fullstack…core-apiReference for the 24 Browser Use MCP tools — parameters, return formats, session lifecycle.css-modulesProvides CSS Modules patterns with Lightning CSS, PostCSS, *.module.css, TypeScript, and Vite.database-patternsUse when designing database schemas, implementing repository patterns, writing optimized queries, managing migrations, or working with indexes and transactions…db-branchingBranches Neon, Turso, or Supabase databases per git worktree for isolated schema work.debug-localization3-strategy fault localization with context budget enforcement — stack trace grep, keyword search, AST expansion. Used by /dev:debug standard path and /dev:fix.debug-modeManages agentdev debug mode — records tool, skill, hook, and agent events to JSONL.debug-shared-initShared initialization for debugging workflows — session setup, stack detection, reproduction, and bug report generation. Used by /dev:debug and /dev:fix.debug-standardEnhanced standard debug workflow — 6-phase orchestration with 3-strategy localization, self-critique, and agent delegation.debug-uiVisual UI debugging — screenshot capture and analysis, responsive layout checking at multiple viewport sizes, CSS validation via DOM state, visual regression…debugging-strategiesUse when troubleshooting bugs, analyzing stack traces, using debugging tools (breakpoints, loggers), or applying systematic debugging methodology across any…deep-analysisRuns a multi-perspective codebase audit using all mnemex AST commands with PageRank and chain-of-thought reasoning.design-referencesProvides design system references — Material 3, Apple HIG, Tailwind UI, Ant Design, Shadcn/ui. Use when reviewing UI against an established design system.design-system-guardrailsEnforces single-source-of-truth UI — design tokens for styles, one Storybook library, variants over call-site restyling.designer-integrationDetects the designer@magus plugin and delegates pixel-level design validation.dingoUse when working with Dingo meta-language for Go, implementing optionals/results, using generics shortcuts, or transpiling .dingo files to .go while…documentation-standardsUse when writing README files, API documentation, user guides, or technical documentation following industry standards from Google, Microsoft, and GitLab style…enforcementEnforces evidence-based phase completion for /dev:feature — artifacts, validation criteria, outer loops, show-your-work.error-handlingUse when implementing custom error classes, error middleware, structured logging, retry logic, or graceful shutdown patterns in backend applications.golangUse when building Go backend services, implementing goroutines/channels, handling errors idiomatically, writing tests with testify, or following Go best…golang-performanceUse when profiling Go applications (pprof), running benchmarks, optimizing memory/CPU usage, or debugging performance bottlenecks in production Go code.hybrid-debuggingCombines Browser Use (DOM, clicks, screenshots) with claude-in-chrome (console, network, JS) for full-spectrum debugging.investigateRoutes code investigation to the right mnemex AST workflow — architecture (map/PageRank), implementation (callers/callees), tests, or debugging.mnemex-orchestrationUse when orchestrating multi-agent code analysis with mnemex. Run mnemex once, share output across parallel agents.mnemex-searchPerforms semantic code search and AST analysis via mnemex MCP/CLI — map, symbol, callers, callees, context, PageRank.navigation-patternsURL navigation, multi-tab orchestration, session creation and management, back/forward navigation, browser profile persistence, session export/import for…patternsCommon agent patterns and templates for Claude Code. Use when implementing agents to follow proven patterns for Tasks integration, quality checks, and external…pythonUse when building FastAPI applications, implementing async endpoints, setting up Pydantic schemas, working with SQLAlchemy, or writing pytest tests for Python…rustUse when building Axum applications, implementing type-safe handlers, working with SQLx, setting up error handling with thiserror, or writing Rust backend…schemasYAML frontmatter schemas for Claude Code agents and commands. Use when creating or validating agent/command files.systematic-debuggingUse when debugging failures, errors, or unexpected behavior. Covers root cause investigation, data flow tracing, hypothesis-driven debugging, and fix…task-managementUse when orchestrating multi-phase workflows to manage Claude Code Tasks with optional GTD plugin integration for cross-session persistence.test-driven-developmentEnforces the RED-GREEN-REFACTOR cycle: write failing test, make it pass, improve design.testing-strategiesUse when writing tests, setting up test frameworks, implementing mocking strategies, or establishing testing best practices (unit, integration, E2E) across any…ui-analyseAnalyzes UI visually using Gemini 3 Pro — prompting patterns, severity guidelines, analysis-only.ui-design-reviewPrompting patterns and review templates for UI design analysis with Gemini multimodal capabilities.ui-style-formatSpecifies the UI design style file format and schema for .claude/design-style.md and .claude/design-references/.universal-patternsUse when implementing language-agnostic patterns like layered architecture, dependency injection, error handling, or code organization principles across any…verification-before-completionRequires evidence-based proof before claiming a task is complete.web-scrapingStructured data extraction from web pages — pagination patterns, dynamic SPAs, authenticated scraping, rate limiting, anti-bot handling, JSON/CSV output.worktree-lifecycleUse when starting isolated feature work or before executing implementation plans.xml-standardsXML tag structure patterns for Claude Code agents and commands.yaml-agent-formatYAML format for Claude Code agent definitions as alternative to markdown.