Claude Skills by paulasilvatech

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.

Configure and run CodeQL code scanning with GitHub Actions workflows, default or advanced setup, CodeQL CLI databases, SARIF uploads, custom query packs, monorepo categories, build modes, and alert triage. Use this skill when the user asks to create or customize codeql.yml, choose CodeQL setup, configure a language matrix, run codeql database create or database analyze, upload SARIF, troubleshoot CodeQL builds, or interpret code scanning alerts.

Pre-breach impact analysis: inventories sensitive data (PII, PHI, PCI-DSS, credentials), traces data flows, scores exposure vectors, and produces a regulatory blast radius report with fine ranges sourced verbatim from GDPR Art. 83, CCPA § 1798.155(a), and HIPAA 45 CFR § 160.404. Cost benchmarks from IBM Cost of a Data Breach Report (annually updated). All citations in references/SOURCES.md for verification. Use when asked: "assess breach impact", "what data could be exposed", "calculate blast...

Apply GDPR-compliant engineering practices across code, APIs, data models, authentication, logging, retention, deletion jobs, cloud infrastructure, and pull requests. Use this skill when handling personal data, user accounts, cookies, analytics, emails, audit logs, encryption, pseudonymization, anonymization, data exports, breach response, CI/CD pipelines with real data, or questions asking whether a design is GDPR-compliant.

Configure and manage GitHub secret scanning, push protection, custom patterns, exclusions, alert triage, remediation, bypass workflows, and pre-commit secret scans through the Advanced Security plugin. Use this skill when enabling secret scanning, resolving blocked pushes, writing secret_scanning.yml, creating regex patterns, triaging alerts, or scanning code before committing.

Scan codebases and files for exploitable security vulnerabilities by tracing data flows, dependencies, secrets, authentication, authorization, injection, cryptography, and business logic issues. Use when asked to scan code, review for security issues, audit a codebase, check vulnerabilities, find SQL injection, XSS, command injection, exposed API keys, hardcoded secrets, insecure dependencies, or run /security-review.

Produce full or incremental STRIDE-A threat models for repositories and systems, including architecture overviews, DFD diagrams, findings, STRIDE heatmaps, and executive assessment. Use when the user asks to threat model a repo, refresh an existing threat-model-* report, compare commits or reports, identify trust boundary risks, or map findings to CVSS 4.0, CWE, and OWASP.

Creates valid Microsoft Threat Modeling Tool (.tm7) files compatible with the Microsoft Threat Modeling Tool v7.3+. Use when asked to create, generate, or modify a .tm7 threat model file, or when performing STRIDE threat modeling that should output a .tm7 file that opens cleanly in the Microsoft Threat Modeling Tool.

Two related workflows for a locally-cloned codebase, in one skill. Use this skill when enforced*** — i.e. whether any workflow is a **required status check /; branch-protection rule** that actually blocks merges, versus one that merely; runs — since that distinction is a manual, human-configured setting that.

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.

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.

Suggest relevant GitHub Copilot custom agent files from the github/awesome-copilot repository by comparing repository context with available agents, detecting already installed or outdated local .github/agents/*.agent.md files, and presenting a no-install table. Use when the user asks to suggest awesome GitHub Copilot custom agents, find agents to add, compare local agents with awesome-copilot, or update outdated custom agents.

Suggest relevant GitHub Copilot instruction files from the awesome-copilot repository by comparing repository context, chat needs, local .github/instructions files, and remote versions. Use this skill when the user asks what Copilot instructions to add, whether local instructions are outdated, or how to install/update awesome-copilot instructions without duplicates.

Suggest relevant GitHub Copilot Agent Skills from the awesome-copilot repository by comparing remote skills with local repository skills, detecting missing or outdated skills, bundled assets, duplicates, and repository-fit gaps. Use when the user asks which awesome-copilot skills to install, update, compare, or recommend for the current repository.

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.

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.

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.

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.

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.

Use when designing or provisioning Azure Managed Redis for cache, semantic cache, vector memory, session store, or agent memory in AI-native systems; produces SKU guidance, network and identity controls, Bicep deployment steps, and integration recommendations. DO NOT USE FOR: general agent architecture (use agentic-architecture-patterns), Foundry agent runtime design (use foundry-agent-blueprint), or general Azure infrastructure (use azure-infrastructure). Triggers include \"design Redis sema...

Create Agent Users in Microsoft Entra ID from Agent Identities, enabling AI agents to act as digital workers with user identity capabilities in Microsoft 365 and Azure environments. Use this skill when the user asks for skill: creating agent users in microsoft entra agent id.

Create, register, deploy, update, and synchronize prompt-based Azure AI Foundry agents from a local JSON manifest using the Agent Service REST API. Use when users ask to sync Foundry agents, create agents in Foundry, push agents, update agent instructions, scaffold a foundry-agents.json manifest, or add sync scripts.

Guide ongoing development of CopilotKit frontends connected over AG-UI to Microsoft Agent Framework agents and Azure AI Foundry hosted agents. Use when adding or gating tools, wiring human-in-the-loop approval, building generative UI, synchronizing shared state, debugging AG-UI event streams, upgrading preview packages, or deploying hosted agent updates.

Create, update, refactor, explain, or review Microsoft Agent Framework applications, agents, workflows, and migrations in .NET or Python. Use this skill when working with Microsoft Agent Framework, successor guidance for Semantic Kernel or AutoGen, Azure AI Foundry, Azure OpenAI, OpenAI providers, MCP tools, workflows, middleware, checkpointing, or language-specific samples.

Create, update, refactor, explain, or review Semantic Kernel applications, plugins, function-calling flows, and AI integrations in .NET or Python. Use when the user asks for Semantic Kernel implementation help, current SDK guidance, Azure OpenAI or Azure AI Foundry connector patterns, plugin design, or language-specific SK samples.

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...

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...

Prepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Terraform), and Dockerfiles for the Azure Developer CLI (azd) workflow. USE ONLY when the user explicitly wants to use azd as the deployment tool, or the project already has an azure.yaml file. DO NOT USE FOR: non-azd deployments, Python App Service code-only deploys (use python-appservice-deploy), or cross-cloud migration (use azure-cloud-migrate). WHEN: prepare app for azd, create azure.yaml, set up...

Scaffold a complete, production-ready Azure project from scratch for any use case, including RAG chatbots, multi-agent systems, API backends, data pipelines, Azure Functions, full-stack web apps, ML training and inference, and event-driven microservices. Use when the user wants to gather requirements through adaptive questioning and generate a full project structure with source files, Bicep infrastructure, azure.yaml for azd, Docker configuration, CI/CD workflows, a README with architecture d...

Run pre-deployment validation for Azure readiness with deep checks on configuration, Bicep or Terraform infrastructure, RBAC role assignments, managed identity permissions, and prerequisites. Use when the user wants to validate an app or azure.yaml, check deployment readiness, run preflight checks, verify configuration before deploying, validate Bicep, Azure Functions, or Container Apps deployments, review role assignments and managed identity permissions, run what-if analysis, or troubleshoo...

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".

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.

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.

Architect and provision enterprise Azure infrastructure from workload descriptions for cloud architects and platform engineers, covering networking, identity, security, compliance, and multi-resource topologies with Well-Architected alignment, and generating Bicep or Terraform directly without azd. Use when the user asks to plan Azure infrastructure, architect a landing zone, design a hub-spoke network, plan a multi-region disaster recovery topology, set up virtual networks, firewalls, and pr...

Azure infrastructure patterns guide landing-zone, networking, identity, naming, tagging, and private connectivity decisions. Use this skill when designing hub-spoke networks, private endpoint patterns, Workload Identity, naming conventions, tag strategies, AKS architecture, Key Vault access, or secure PaaS topology.

Fetch live Azure Retail Prices API data and estimate Azure service, SKU, region, reservation, savings plan, spot, and Copilot Studio credit costs. Use when the user asks about Azure pricing, Azure costs, Azure billing, workload estimates, SKU comparison, Copilot Credits, Copilot Studio pricing, or agent usage estimation.

Analyze Azure resource health, logs, metrics, and telemetry to diagnose operational issues and produce a prioritized remediation plan. Use this skill when the user asks to troubleshoot an Azure resource, inspect Azure Resource Health, analyze Log Analytics or Application Insights data, classify root causes, or create Azure CLI remediation and rollback steps.