Claude Skills by paulasilvatech

Find, evaluate, and assemble the smallest compatible set of AI Agent Skills for an end-to-end natural-language goal. Use when a user wants Skills for a multi-step workflow, asks which Skills fit a project, needs an installed-Skill audit or conflict check, has low Skill recall, wants indirect helpers such as humanizers or compliance checks, or wants a project-specific Skill Stack with controlled installation. Search local Skills, registries, GitHub, and OpenCLI; compare adoption, verified fit,...

Verify supply chain integrity for AI agent plugins, MCP servers, tools, and dependencies by generating SHA-256 manifests, verifying installed files, auditing pinned versions, and enforcing promotion gates. Use when asked to verify plugin integrity, generate INTEGRITY.json, check supply chain, detect tampering, audit dependency pinning, sign this plugin, or promote dev → staging → production.

Design evaluator-optimizer, reflection, rubric, LLM-as-judge, and test-driven refinement loops for AI agent outputs. Use when implementing self-critique, iterative improvement, quality gates, agent response evaluation, code refinement, or rubric-based scoring for generated code, reports, or analysis.

Review and improve AI prompts for safety, bias, security, privacy, effectiveness, robustness, and testability. Use this skill when the user asks to audit a prompt, harden a system prompt, identify prompt injection risk, reduce bias, improve guardrails, or produce a safer enhanced prompt.

Help users install and use John Papa's ai-ready skill as the up-to-date source for making repositories AI-ready with AGENTS.md, copilot-instructions.md, CI workflows, issue templates, and stack-specific guidance. Use when the user asks to make a repo ai-ready, set up AI config, prepare for AI contributions, or install ai-ready.

Bootstrap and run a lightweight multi-agent development team. Use when starting or adopting a project, planning multi-step work, coordinating implementation with optional QA, brainstorming with distinct perspectives, or preserving PROJECT_BRIEF context across sessions.

Prevent generic web and iOS interfaces by extracting product-specific design decisions from repository evidence and UIZZE's public catalogue of 800,000+ real web and iOS screens. Use this skill when building, refactoring, or reviewing UI, when asked to browse https://uizze.com before choosing a layout, or when the user wants a hard finish gate against interchangeable dashboard cards, filler metrics, vague headings, and generic calls to action.

Test REST, GraphQL, and gRPC APIs at the contract and behavior level with schema validation, authentication and authorization coverage, error-path assertions, pagination and idempotency checks, and CI-ready suites. Use when the user asks to test an API, validate responses against OpenAPI or a GraphQL schema, cover auth and error cases, or build an integration suite for endpoints.

Design Azure API Management as the runtime AI gateway for model and tool traffic, including token-per-minute controls, token limits, quotas, multi-backend load-balanced backend pools, circuit breakers, semantic caching, token metrics, managed identity, and content safety. Use when fronting model deployments, enforcing token budgets, adding semantic cache, load balancing LLM endpoints, or governing tool API calls at runtime.

Instrument Azure-hosted web apps with Azure Application Insights telemetry by choosing auto-instrumentation or code instrumentation for ASP.NET Core, Node.js, or Python. Use when the user wants to enable telemetry, observe app health, create an App Insights resource, or wire instrumentation into a webapp.

Review an iOS app codebase and metadata for likely Apple App Store rejection risks, compliance gaps, reviewer friction, and fast approval improvements. Use when asked to "review for App Store rejection", "check Apple review readiness", "audit IAP and privacy", "write reviewer notes", or "find App Store approval risks".

Diagnose and remediate Arch Linux incidents with pacman, systemd, journal analysis, rolling-release upgrade discipline, kernel awareness, and rollback practices. Use when the user asks to triage Arch service failures, package conflicts, broken upgrades, boot issues, or post-update regressions.

Generate a comprehensive Project_Architecture_Blueprint.md by analyzing a codebase, detecting technology stacks and architectural patterns, documenting components, dependencies, diagrams, implementation patterns, testing, deployment, and governance. Use when asked to create an architecture blueprint, document project architecture, map layers, produce C4/UML/component diagrams, or guide new development consistency.

Design and implement Arduino integration with Azure IoT Hub and IoT Edge, including secure provisioning, MQTT telemetry, gateway topologies, offline buffering, command handling, OTA configuration, and production guardrails. Use when connecting Arduino sensors or actuators to Azure IoT or edge gateways.

Create, list, inspect, update, and delete Arize AI integrations that store LLM provider credentials for evaluators and Arize features. Use this skill when connecting OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, Vertex AI, Gemini, NVIDIA NIM, or custom providers to Arize; managing AI integration credentials; listing integrations; rotating keys; deleting integrations; or finding integration IDs.

Create, inspect, update, and use Arize annotation configs and annotation queues, then bulk-apply human labels to spans with the Python SDK. Use when asked for "annotation config", "annotation queue", "label schema", "human feedback", "bulk annotate spans", "update_annotations", "labeling queue", "annotate record", or "human review".

Creates, manages, and queries Arize datasets and examples. Covers dataset CRUD, appending examples, exporting data, and file-based dataset creation using the ax CLI. Use when the user needs test data, evaluation examples, or mentions create dataset, list datasets, export dataset, append examples, dataset version, golden dataset, or test set.

Create, update, and run Arize LLM-as-judge evaluators and tasks for spans, traces, sessions, projects, datasets, and experiments. Use when the user mentions create evaluator, LLM judge, hallucination, faithfulness, correctness, relevance, run eval, score spans, score experiment, trigger-run, column mapping, continuous monitoring, or evaluator prompt improvement.

Create, run, export, compare, delete, and troubleshoot Arize experiments with the ax CLI, including real model inference, run files, evaluations, result analysis, and dataset-linked experiment workflows. Use this skill when the user asks to create experiment, run experiment, compare models, evaluate AI, benchmark prompts, A/B test models, export experiment results, measure accuracy, or inspect experiment runs in Arize.

Adds Arize AX tracing to an LLM application for the first time. Use when the user wants to instrument their app, add tracing from scratch, set up LLM observability, integrate OpenTelemetry or OpenInference, or get started with Arize tracing.

Generate Arize UI deep links for traces, spans, sessions, datasets, labeling queues, evaluators, and annotation configs using base64 org and space IDs, resource IDs, and trace/session time windows. Use when the user wants to link to, open, share, or debug an Arize trace, span, session, dataset, queue, evaluator, or annotation config.

Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output quality, prompt engineering, prompt tuning, or system prompt improvement.

Download, export, inspect, and root-cause existing Arize traces, spans, sessions, errors, prompts, retrieval documents, model calls, and behavior regressions with the ax CLI. Use when asked to look at existing trace data, export traces by trace ID, export spans by span ID, download a session, investigate LLM app runtime issues, or analyze Arize behavior regressions.

Work with Aspire distributed applications, AppHost orchestration, CLI commands, service discovery, integrations, MCP docs, dashboard, testing, and deployment. Use this skill when the user asks to create, run, debug, configure, deploy, or troubleshoot an Aspire polyglot app.

Create or review ASP.NET Minimal API endpoints with typed results, DTO validation, endpoint groups, filters, ProblemDetails, and OpenAPI documentation. Use this skill when asked to add Minimal APIs, document endpoints with Swagger/OpenAPI, use .NET 9 built-in OpenAPI, or design request and response types.

Enforce AppSec audit integrity for security analysis, code review, threat modeling, SAST, SCA, and quality scan agents. Use this skill when running a post-analysis quality gate, preventing rationalization, retrying failed evidence collection, running a second-pass self-critique, scoring output from 1-10 with a ≥8 threshold, or recording governed lessons or memories.

Analyze a screen recording of a repetitive manual workflow, extract frames and optional narration, reconstruct the process, and produce tested automation scripts. Use this skill when the user asks to automate a recorded task, turn a screen recording into a script, replace repetitive browser, spreadsheet, email, file-management, terminal, or macOS GUI steps, or create dry-run automation.

Run an autonomous iterative experimentation loop for programming tasks with measurable outcomes. Use when the user asks for autonomous improvement, iterative optimization, experiment loops, auto research, performance tuning, automated experimentation, hill climbing, trying changes automatically, optimizing code, benchmarks, coverage, latency, throughput, build time, memory use, or other metric-driven coding work.

Set up and initialize AWS CDK applications in Python, including prerequisites, credentials, project creation, virtual environments, dependencies, synthesis, bootstrap, diff, deploy, and troubleshooting. Use this skill when the user asks for AWS CDK Python setup instructions, a new CDK Python project, or first deployment guidance.

Investigate AWS production incidents with CloudWatch Logs Insights, Metrics, Alarms, CloudTrail correlation, blast-radius narrowing, metric math, and incident timelines. Use when the user asks to debug CloudWatch alarms, query Logs Insights, correlate alarms to deployments, find Lambda cold starts, OOMs, timeouts, throttling, or reconstruct an AWS incident timeline.

Analyze AWS resources used in the app (IaC files and/or resources in a target account/region) and optimize costs - creating GitHub issues for identified optimizations. Use this skill when the user asks for prerequisites.

Diagnose AWS resource health with AWS CLI, CloudWatch metrics, CloudWatch Logs Insights, Performance Insights, CloudTrail correlation, severity classification, root cause analysis, and remediation plans. Use when the user asks for AWS resource health, issue diagnosis, CloudWatch troubleshooting, or remediation for EC2, Lambda, RDS, ECS, ALB, DynamoDB, SQS, or API Gateway.

Answer natural-language questions about AWS resources by running strictly read-only AWS CLI queries. Use when asking about EC2, S3, RDS, Lambda, ECS, EKS, Secrets Manager, IAM, VPC, networking, messaging, `aws lambda list-event-source-mappings --query 'EventSourceMappings[].[FunctionArn,EventSourceArn,State,BatchSize]' --output table`, or current-state inventory.

Review AWS workloads against the AWS Well-Architected Framework across Operational Excellence, Security, Reliability, Performance Efficiency, Cost Optimization, and Sustainability. Use when the user asks for an AWS well-architected review, IaC architecture assessment, WAF findings, risk classification, or GitHub issue remediation plan.

Analyze Azure IaC files and deployed Azure resources for evidence-based cost optimization, validate current costs, calculate priority scores, and draft GitHub issues. Use when asked to "azure cost optimize", "reduce Azure spend", "find Azure cost savings", "right-size Azure resources", or "create cost optimization issues".

Provides a decision framework for production multi-agent and AI-native systems on GitHub and Azure AI Foundry. Use this skill when designing model routing, prompt caching, semantic caching, memory, context curation, RAG, tools, MCP, identity, guardrails, evaluation, observability, or cost controls.

Build on Azure AI services including AI Search, Speech, Azure OpenAI, and Document Intelligence, covering keyword, vector, hybrid, and semantic search, speech-to-text, text-to-speech, transcription, and OCR. Use when the user asks about AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcription, OCR, or converting text to speech.

Set up AI Runway on AKS from a bare cluster to a running model, covering cluster verification, controller install, GPU assessment, provider setup, and the first deployment. Use when the user asks to set up or install AI Runway, onboard an AKS cluster, run AI Runway setup, deploy a model to AKS, enable GPU inference on AKS, configure KAITO on AKS, run an LLM or vLLM on AKS, set up model serving on AKS, or work with the AI Runway controller.

Design Azure API Center as the enterprise inventory and governance plane for APIs, agent tools, OpenAPI definitions, environments, deployments, metadata, linting, and MCP server discovery. Use when building an API or tool catalog, enforcing API standards, registering MCP servers, or making approved tools discoverable to agent builders.

Assess whether source code is ready to deploy to Azure before any infrastructure work, evaluating build health, app completeness, dependencies and local services, stack compatibility, and deployment feasibility. Use when the user asks to evaluate a repository, check whether an app is ready or deployable to Azure, find deployment blockers, confirm dependency compatibility, ask whether Azure supports a framework, check whether a Dockerfile is needed, or determine what must change before deploying.

Orchestrate an app end to end from a business idea, app idea, or existing codebase to a running Azure deployment with cost estimates and a pre-deploy approval gate, auto-detecting Azure services, scaffolding infrastructure code, and deploying without a generic template. Use when the user wants to bring an app to Azure, plan an Azure deployment, learn what Azure services an app needs, check the cost to run it, deploy an app or all its services to the cloud, migrate an existing app to Azure, or...

Design new Azure infrastructure or analyze existing Azure resources, generate interactive architecture diagrams, refine through conversation, produce Bicep, review, and deploy. Use when asked to design, analyze, modify, or deploy Azure architecture, including "Create X on Azure", "Set up a RAG architecture", "Analyze my current Azure infrastructure", "Draw a diagram for rg-xxx", Foundry slowness, cost reduction, security strengthening, Microsoft Foundry, AI Search, OpenAI, Fabric, ADLS Gen2, ...

ArgoCD CLI operations manage GitOps installation, bootstrap, synchronization, drift detection, rollback checks, and day-2 application workflows. Use this skill when working with argocd login, app create, app sync, app health, ApplicationSet, ArgoCD troubleshooting, GitOps drift, or repository credential configuration.

Azure CLI operations run az commands for cloud resource discovery, subscription context, identity, AKS, ACR, Key Vault, RBAC, managed identity, and federated credential workflows. Use this skill when working with az login, az account, az aks, az acr, az keyvault, resource group checks, or Azure day-2 operations.

Assess and migrate cross-cloud workloads to Azure with assessment reports and code conversion, supporting Lambda to Functions, Beanstalk, Heroku, and App Engine to App Service, and Fargate, Kubernetes, Cloud Run, or Spring Boot to Container Apps. Use when the user asks to migrate Lambda to Functions, move from AWS or GCP to Azure, migrate Beanstalk, Heroku, or App Engine, convert Cloud Run or Fargate workloads, move ECS, GKE, or EKS to Container Apps, or plan a cross-cloud migration.

Run Azure compliance and security audits with azqr plus Key Vault expiration checks, covering best-practice assessment, resource review, policy and compliance validation, and security posture checks. Use when the user asks for a compliance scan or assessment, a security audit, Azure best-practice review, help before running the azqr CLI, Key Vault expiration checks, expired certificates or expiring secrets, or orphaned resource review.

Route Azure virtual machine and scale set work, including size and image selection, pricing comparison, autoscale and orchestration modes, capacity reservation groups, and Essential Machine Management. Use when the user asks to create, provision, deploy, or spin up a VM, recommend a VM size or family, compare VM pricing, work with VMSS, scale sets, autoscale, burstable or GPU sizes, plan HPC, machine learning, or dev/test workloads, estimate compute cost, or reserve and guarantee capacity.

Manage Azure Container Registry with az acr CLI commands for registries, images, cloud builds, ACR Tasks, authentication, tokens, geo-replication, networking, purge, import, and diagnostics. Use when working with ACR, az acr, pushing or importing container images in Azure, or Azure Container Registry operations.

Manage Azure cost by querying actual spend, forecasting future spending, and optimizing resources to reduce waste. Use when the user asks about Azure costs or bills, wants a cost breakdown, asks how much they are spending, wants to forecast spending, optimize or reduce spend, find orphaned resources, rightsize VMs, investigate a cost spike, or lower storage and AKS costs.

Execute Azure deployments for ALREADY-PREPARED applications that have existing .azure/deployment-plan.md and infrastructure files. DO NOT use this skill when the user asks to CREATE a new application — use azure-prepare instead. This skill runs azd up, azd deploy, terraform apply, and az deployment commands with built-in error recovery. Requires .azure/deployment-plan.md from azure-prepare and validated status from azure-validate. WHEN: "run azd up", "run azd deploy", "execute deployment", "p...