kalilurrahman/kr-claudiator-skills - Page 9

finops-strategy

Implement FinOps practices to optimise cloud spend without sacrificing performance. Outputs cost allocation strategy, savings recommendations, tagging taxonomy, and budgeting framework.

kubernetes-security

Harden Kubernetes clusters with RBAC, pod security, network policies, and supply chain controls. Outputs security baseline, admission policies, audit configuration, and hardening checklist.

on-call-management

Design and operate an effective on-call rotation. Outputs rotation schedule, escalation policies, alert routing rules, on-call handbook, and well-being guidelines.

platform-idp

Design an Internal Developer Platform (IDP) that reduces cognitive load for engineers. Outputs platform capabilities, golden paths, self-service workflows, and adoption strategy.

progressive-delivery

Implement progressive delivery strategies including canary releases, feature flags, and traffic splitting. Outputs deployment pipeline, rollout configuration, automated rollback triggers, and observability requirements.

release-management

Design a release management process for coordinated, low-risk software releases. Outputs release workflow, change approval process, rollback procedures, and communication templates.

service-discovery

Implement service discovery for dynamic microservice environments. Outputs discovery patterns, DNS vs registry approaches, health check design, and client-side load balancing.

slos-and-error-budgets

Define Service Level Objectives and manage error budgets for reliability engineering. Outputs SLI/SLO definitions, error budget calculations, burn rate alerts, and reliability review process.

supply-chain-security-pipeline

Secure the software supply chain from source code to production deployment. Outputs SLSA compliance controls, artifact signing, dependency vetting, and provenance attestation pipeline.

wasm-deployment

Deploy WebAssembly workloads for edge computing, plugin systems, and portable compute. Outputs WASM runtime selection, compilation pipeline, deployment patterns, and security sandboxing.

cohort-analysis

Build cohort analyses to understand user retention, behaviour over time, and revenue patterns. Outputs cohort SQL queries, retention visualisations, revenue cohorts, and actionable insights.

customer-segmentation

Build customer segmentation models for personalisation, targeting, and lifecycle management. Outputs RFM analysis, behavioural clustering, segment SQL, and activation playbooks.

data-enrichment

Design data enrichment pipelines that augment first-party data with external sources. Outputs enrichment strategy, provider evaluation, pipeline design, match rate optimisation, and quality controls.

data-virtualization

Implement data virtualisation to query distributed data sources without moving data. Outputs virtual layer design, query federation strategy, performance optimisation, and governance approach.

dbt-best-practices

Apply dbt best practices for scalable, maintainable analytics engineering. Outputs project structure, naming conventions, testing strategy, documentation standards, and CI/CD pipeline.

dbt-patterns

Build production dbt projects with best practices for modelling, testing, documentation, and performance. Outputs project structure, model patterns, macro library, and CI configuration.

event-tracking-plan

Design a comprehensive event tracking plan for product analytics. Outputs event taxonomy, tracking spec, implementation guide, and governance process.

experiment-platform

Build an internal experimentation platform for running A/B tests at scale. Outputs experiment service architecture, assignment engine, metric pipeline, and statistical analysis framework.

feature-flags-analytics

Analyse feature flag experiments to measure impact on key metrics. Outputs statistical test selection, sample size calculation, results interpretation, and ship/no-ship decision framework.

forecasting-models

Build time-series forecasting models for business metrics. Outputs model selection framework, Prophet/ARIMA implementation, evaluation methodology, production serving pattern, and uncertainty quantification.

funnel-analysis

Build conversion funnel analyses to identify drop-off points and optimisation opportunities. Outputs funnel SQL queries, drop-off attribution, segment comparison, and experiment prioritisation.

product-analytics

Build product analytics infrastructure to understand user behaviour, feature adoption, and business outcomes. Outputs event taxonomy, funnel analysis, retention queries, and reporting infrastructure.

revenue-analytics

Build revenue analytics systems tracking MRR, ARR, churn, expansion, and cohort revenue. Outputs revenue recognition logic, MRR waterfall analysis, LTV calculation, and forecasting models.

time-series-analysis

Analyse and model time series data for forecasting, anomaly detection, and trend analysis. Outputs decomposition approach, forecasting model selection, evaluation metrics, and production pipeline.

ai-product-design

Design AI-powered products that are useful, trustworthy, and safe. Outputs capability-first design process, failure mode analysis, human-in-the-loop patterns, and evaluation framework.

ai-testing-strategy

Design comprehensive testing strategies for AI-powered features and LLM applications. Outputs test taxonomy, evaluation harness, regression suite, human evaluation protocol, and CI integration.

context-window-management

Optimise LLM context windows for long-document processing, multi-turn conversations, and token efficiency. Outputs chunking strategies, compression techniques, and memory management patterns.

knowledge-graph-rag

Build RAG systems enhanced with knowledge graphs for multi-hop reasoning and relationship queries. Outputs graph schema, hybrid retrieval pipeline, and query routing strategy.

llm-caching-strategy

Implement caching strategies for LLM applications to reduce costs and latency. Outputs exact cache, semantic cache, prompt cache, and KV cache configurations with measurement.

llm-context-management

Manage LLM context windows effectively for long conversations, document processing, and complex tasks. Outputs context budgeting, summarisation strategies, retrieval injection, and memory patterns.

llm-fine-tuning-data

Prepare high-quality datasets for LLM fine-tuning. Outputs data collection strategy, formatting standards, quality filtering pipeline, deduplication, and evaluation split design.

llm-routing

Route LLM requests to the optimal model based on complexity, cost, and latency. Outputs routing logic, model selection criteria, cost-quality tradeoffs, and fallback chains.

llm-structured-output

Reliably extract structured data from LLM responses using function calling, JSON mode, and validation. Outputs schema definitions, extraction patterns, retry logic, and parsing pipelines.

ml-feature-selection

Select the most predictive features for ML models to improve accuracy and reduce overfitting. Outputs filter, wrapper, and embedded selection methods with validation strategy.

model-compression

Compress and optimise ML models for production deployment. Outputs quantisation, pruning, and distillation approaches with size-accuracy tradeoff analysis.

model-fine-tuning-strategy

Plan and execute model fine-tuning to improve performance on domain-specific tasks. Outputs fine-tuning decision framework, dataset preparation guidelines, evaluation strategy, and deployment plan.

model-serving-infrastructure

Design and deploy ML model serving infrastructure for low-latency production inference. Outputs serving architecture, batching strategy, scaling configuration, and SLO monitoring.

multi-agent-systems

Design and orchestrate multi-agent AI systems with specialist agents, coordination patterns, and shared memory. Outputs agent topology, communication protocol, error handling, and evaluation framework.

prompt-injection-defense

Defend LLM-powered applications against prompt injection attacks. Outputs threat model, input/output sanitisation, privilege separation, detection patterns, and monitoring strategy.

rag-evaluation

Evaluate and improve RAG (Retrieval Augmented Generation) pipeline quality. Outputs retrieval evaluation metrics, answer quality benchmarks, end-to-end evaluation framework, and improvement roadmap.