spendsmart-dashboard

Use when the user wants a local copy of an existing website — to clone, download, mirror, capture, or get it working offline. Trigger on: "clone [site]", "download [url] locally", "get a local copy of", "mirror [site]", "replicate the look of [site]", "capture before the rebrand", "get [site] working locally", "want [site] offline", "grab this site", "poke around in the DOM locally". This looks simple but isn't — wget silently fails on JS-rendered sites, CDN assets need Referer headers, and asset URLs hide in minified JS variables. Use this skill rather than suggesting wget/curl. Works on: React/Next.js SPAs, Webflow, Vue/Nuxt, Three.js/GSAP/Rive animation sites, any modern website. Do NOT trigger for: building a new site from scratch, data scraping to CSV, screenshot analysis, E2E test setup, or debugging existing code.

Use when a feature, bug fix, or architectural decision needs a design document before code is written. Triggers for new LLDs, bug reports, RFCs, HLD updates, and Mermaid diagrams.

Use when creating design documentation (LLD/HLD), writing RFCs, documenting bug reports, or generating Mermaid diagrams for any design artifact. Invoke for "create a diagram", "generate mermaid", "document architecture", "code to diagram", "create design doc", "convert code to diagram", "design document", or before writing implementation plans. Supports full context loading of all reference guides, Unicode semantic symbols, and Python utilities for diagram extraction and image conversion.

Use when designing REST or GraphQL APIs, creating OpenAPI specifications, or planning API architecture. Invoke for resource modeling, versioning strategies, pagination patterns, error handling standards.

Use when designing new system architecture, reviewing existing designs, or making architectural decisions. Invoke for system design, architecture review, design patterns, ADRs, scalability planning.

AWS cost optimization and FinOps workflows. Use for finding unused resources, analyzing Reserved Instance opportunities, detecting cost anomalies, rightsizing instances, evaluating Spot instances, migrating to newer generation instances, implementing FinOps best practices, optimizing storage/network/database costs, and managing cloud financial operations. Includes automated analysis scripts and comprehensive reference documentation.

CI/CD pipeline design, optimization, DevSecOps security scanning, and troubleshooting. Use for creating workflows, debugging pipeline failures, implementing SAST/DAST/SCA, optimizing build performance, implementing caching strategies, setting up deployments, securing pipelines with OIDC/secrets management, and troubleshooting common issues across GitHub Actions, GitLab CI, and other platforms.

This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.

This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing and mitigating context failures.

This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems.

This skill should be used when the user asks to "optimize context", "reduce token costs", "improve context efficiency", "implement KV-cache optimization", "partition context", or mentions context limits, observation masking, context budgeting, or extending effective context capacity.

Use when setting up CI/CD pipelines, containerizing applications, or managing infrastructure as code. Invoke for pipelines, Docker, Kubernetes, cloud platforms, GitOps.

This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines.

Use when defining new features, gathering requirements, or writing specifications. Invoke for feature definition, requirements gathering, user stories, EARS format specs.

Use when implementing features across frontend and backend, building APIs with UI, or creating end-to-end data flows. Invoke for feature implementation, API development, UI building, cross-stack work.

GitOps deployment workflows with ArgoCD and Flux. Use for setting up GitOps (ArgoCD 3.x, Flux 2.7), designing repository structures (monorepo/polyrepo, app-of-apps), multi-cluster deployments (ApplicationSets, hub-spoke), secrets management (SOPS+age, Sealed Secrets, External Secrets Operator), progressive delivery (Argo Rollouts, Flagger), troubleshooting sync issues, and OCI artifact management. Covers latest 2024-2025 features: ArgoCD annotation-based tracking, fine-grained RBAC, Flux OCI artifacts GA, image automation, source-watcher.

Infrastructure as Code with Terraform and Terragrunt. Use for creating, validating, troubleshooting, and managing Terraform configurations, modules, and state. Covers Terraform workflows, best practices, module development, state management, Terragrunt patterns, and common issue resolution.

Systematic Kubernetes troubleshooting and incident response. Use when diagnosing pod failures, cluster issues, performance problems, networking issues, storage failures, or responding to production incidents. Provides diagnostic workflows, automated health checks, and comprehensive remediation guidance for common Kubernetes problems.

Use when designing distributed systems, decomposing monoliths, or implementing microservices patterns. Invoke for service boundaries, DDD, saga patterns, event sourcing, service mesh, distributed tracing.

Monitoring and observability strategy, implementation, and troubleshooting. Use for designing metrics/logs/traces systems, setting up Prometheus/Grafana/Loki, creating alerts and dashboards, calculating SLOs and error budgets, analyzing performance issues, and comparing monitoring tools (Datadog, ELK, CloudWatch). Covers the Four Golden Signals, RED/USE methods, OpenTelemetry instrumentation, log aggregation patterns, and distributed tracing.

Use when building Python 3.14+ applications requiring type safety, async programming, or production-grade patterns. Invoke for type hints, pytest, async/await, dataclasses, mypy configuration.

Use when building React 18+ applications requiring component architecture, hooks patterns, or state management. Invoke for Server Components, performance optimization, Suspense boundaries, React 19 features.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. Also use this when users want to create a new workflow. This is the single entry point for creating ANY new capability — whether it's a lightweight workflow file or a full skill folder with scripts and assets.

Use when defining SLIs/SLOs, managing error budgets, or building reliable systems at scale. Invoke for incident management, chaos engineering, toil reduction, capacity planning.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when implementing any feature or bugfix, before writing implementation code

Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Use when executing implementation plans with independent tasks in the current session