Claude Skills by paulasilvatech

Preview, publish, update, inspect, or uninstall managed modernization repository customizations with conflict detection, ownership hashes, transactional rollback, and safe archives. Use when installing a mainframe modernization track's context, stage agents, prompts, instructions, or automation into a target repository.

Analyze Software AG Natural programs, maps, data areas, copycodes, JCL, Adabas DDMs, FDTs, descriptors, MU/PE fields, and call or data dependencies with source citations. Use when reading or inventorying a Natural/Adabas legacy system before modernization.

Review existing PostgreSQL SQL, schema, migrations, functions, triggers, indexes, JSONB, arrays, custom types, domains, extensions, privileges, and Row Level Security for PostgreSQL-specific anti-patterns. Use when asked to audit or critique PostgreSQL code, database migrations, PL/pgSQL, RLS policies, or schema design.

Design, tune, and modernize PostgreSQL SQL, schemas, indexes, functions, and maintenance workflows using PostgreSQL-specific capabilities. Use this skill when the user asks for PostgreSQL optimization, query tuning, JSONB or array design, EXPLAIN ANALYZE interpretation, index strategy, full-text search, custom types, range/geometric types, pg_stat_statements, VACUUM, ANALYZE, partitioning, or secure parameterized database development.

Elicits, normalizes, validates, and traces requirements through a complete Spec-Driven Development workflow using EARS. Use when converting notes, PRDs, legacy evidence, or design inputs into FRD/NFRD, SPECIFICATION.md, architecture and task artifacts, traceability matrices, quality gates, or an implementation-ready SDD handoff.

Load the SIFAP Natural/Adabas workshop profile, source-evidence boundaries, target stack, traceability contract, and sensitive-data rules. Use when analyzing, specifying, designing, implementing, testing, or operationalizing the SIFAP modernization.

Coordinate the SIFAP modernization workshop through archaeology, architecture, build, and evolution stages with evidence gates, role handoffs, branch intent, and observable completion criteria. Use when starting a stage, checking readiness, or handing work to the next SIFAP stage agent.

Author and validate SIFAP EARS requirements with unique REQ-NNN identifiers, real source_legacy evidence, Given/When/Then acceptance criteria, and test lineage. Use when creating, reviewing, synchronizing, or gating SIFAP specifications and requirement-backed tests.

Model Adabas files, DDM and FDT definitions, MU and PE structures, packed and unpacked numerics, descriptors, and ISN identity as a PostgreSQL schema, then prove equivalence with recorded reconciliation numbers. Use when designing or reviewing an Adabas to PostgreSQL data migration, mapping legacy field formats to column types, deciding child-table versus array storage, or verifying that migrated data matches the legacy source.

Use this skill when the user asks to modernize legacy code with a disciplined GitHub Copilot workflow: brief, assess, map, extract business rules, reimagine architecture, transform modules, and harden with tests and security review. Trigger for COBOL, JCL, legacy Java, .NET, C++, classic ASP, monolith modernization, behavior-preserving rewrite, business-rule extraction, modernization assessment, or legacy-to-modern transformation.

Create an Architectural Decision Record (ADR) as a structured Markdown document with front matter, coded consequences, alternatives, implementation notes, and references. Use when the user asks to document an architecture decision, create an ADR, capture alternatives and trade-offs, or save a decision under docs/adr.

Review, audit, author, and harden GitHub Actions workflows against Actions-specific threats: untrusted-input script injection, privileged trigger escalation, mutable action references, over-scoped GITHUB_TOKEN permissions, unsafe GITHUB_ENV/GITHUB_OUTPUT writes, secret exposure, OIDC misuse, and self-hosted runner risk. Use for .github/workflows/*.yml, secure my CI, pull_request_target danger, SHA pinning, or permissions lockdown.

Apply JUnit 5 best practices for Java tests, including Maven or Gradle setup, standard and parameterized tests, lifecycle hooks, assertions, Mockito isolation, tags, nested tests, and test commands. Use when asked for JUnit 5+ guidance or to write Java unit tests.

Apply Spring Boot best practices for project structure, dependency injection, configuration, REST controllers, DTO validation, services, transactions, Spring Data JPA, logging, testing, and security. Use when asked for Spring Boot guidance or to implement Java backend code.

Extract cited business-rule cards from legacy code, batch jobs, database definitions, screens, and process documents while separating observed behavior from inferred intent. Use when requirements, target design, or behavior-preserving modernization need an evidence-backed rule catalog.

Design and implement characterization, differential, golden-master, and behavior-equivalence tests that pin observable legacy behavior before modernization. Use when a legacy slice needs a trustworthy behavior oracle, regression baseline, or intentional-change record.

Preview, publish, update, inspect, or uninstall managed modernization repository customizations with conflict detection, ownership hashes, transactional rollback, and safe archives. Use when installing a mainframe modernization track's context, stage agents, prompts, instructions, or automation into a target repository.

Analyze Software AG Natural programs, maps, data areas, copycodes, JCL, Adabas DDMs, FDTs, descriptors, MU/PE fields, and call or data dependencies with source citations. Use when reading or inventorying a Natural/Adabas legacy system before modernization.

Review existing PostgreSQL SQL, schema, migrations, functions, triggers, indexes, JSONB, arrays, custom types, domains, extensions, privileges, and Row Level Security for PostgreSQL-specific anti-patterns. Use when asked to audit or critique PostgreSQL code, database migrations, PL/pgSQL, RLS policies, or schema design.

Design, tune, and modernize PostgreSQL SQL, schemas, indexes, functions, and maintenance workflows using PostgreSQL-specific capabilities. Use this skill when the user asks for PostgreSQL optimization, query tuning, JSONB or array design, EXPLAIN ANALYZE interpretation, index strategy, full-text search, custom types, range/geometric types, pg_stat_statements, VACUUM, ANALYZE, partitioning, or secure parameterized database development.

Elicits, normalizes, validates, and traces requirements through a complete Spec-Driven Development workflow using EARS. Use when converting notes, PRDs, legacy evidence, or design inputs into FRD/NFRD, SPECIFICATION.md, architecture and task artifacts, traceability matrices, quality gates, or an implementation-ready SDD handoff.

Run each SIFAP modernization phase as a bounded correction loop with observable exit gates, an iteration ledger, upstream defect escalation, and a Natural/Adabas engineering graph that proves legacy-to-target coverage. Use when opening or closing a SIFAP phase loop, deciding whether a phase gate passes, routing a defect to the phase that owns its root cause, or building, querying, and gating the modernization graph.

Load the SIFAP Natural/Adabas workshop profile, source-evidence boundaries, target stack, traceability contract, and sensitive-data rules. Use when analyzing, specifying, designing, implementing, testing, or operationalizing the SIFAP modernization.

Author and validate SIFAP EARS requirements with unique REQ-NNN identifiers, real source_legacy evidence, Given/When/Then acceptance criteria, and test lineage. Use when creating, reviewing, synchronizing, or gating SIFAP specifications and requirement-backed tests.

Coordinate the SIFAP modernization workshop through archaeology, architecture, build, quality, and operations stages with evidence gates, role handoffs, branch intent, and observable completion criteria. Use when starting a stage, checking readiness, or handing work to the next SIFAP stage agent.

Build and debug C#/.NET MCP servers and clients with current ModelContextProtocol 2.x packages. Use when the user mentions ModelContextProtocol, McpServerTool, MapMcp, WithStdioServerTransport, Streamable HTTP, STDIO, prompts, resources, tools, completions, elicitation, MCP Apps, Tasks, OAuth, reverse proxy deployment, or .NET MCP errors.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Use the MCP CLI to discover Model Context Protocol servers, inspect tool schemas, grep tool names, and call MCP tools with JSON, raw text, or stdin arguments. Use when the user asks to list MCP servers, inspect a server/tool schema, call an MCP tool from the command line, or script MCP access with --json or --raw output.

Review MCP server, client, and tool-handler source code for security. Use when asked to review an MCP server before release, audit Model Context Protocol implementation controls MCP-01 through MCP-05, check OWASP MCP Top 10, inspect auth, sessions, rate limiting, input-schema validation, official SDK use, or RCE vectors with file and line evidence.

Verify an MCP server before release by exercising a real protocol session, comparing runtime capabilities with source and documentation, testing failure paths, and recording reproducible evidence. Use when shipping or reviewing an MCP server, tool, resource, prompt, catalog, or install path.

Audits MCP server configurations such as .mcp.json for hardcoded secrets, dangerous shell patterns, unpinned dependencies, unsafe npx usage, unapproved servers, and governance risks. Use this skill when asked to check MCP security, audit MCP servers, review .mcp.json, validate server args, detect shell injection, or verify environment-variable based credentials.

Make a web app agent-ready with WebMCP by detecting app actions, building a manifest, integrating document.modelContext tools, verifying in a real browser, healing failures, and auditing diffs. Use when the user says "webmcpify", "add WebMCP", "expose app actions to AI agents", or asks to make a browser app controllable through WebMCP tools.

Create Adaptive Card response templates and response_semantics for MCP-based API plugins in Microsoft 365 Copilot. Use when presenting MCP tool or API data with visual Adaptive Cards, citation mappings, static or dynamic card templates, JSONPath data paths, or responsive card layouts.

Create a Microsoft 365 Copilot declarative agent backed by a Model Context Protocol server. Use when asked to scaffold or configure an MCP-based declarative agent, choose imported tools, configure OAuth 2.0 or SSO, set response semantics, or produce appPackage files for Microsoft 365 Agents Toolkit.

Guide deployment, governance, assignment, lifecycle, approval, blocking, monitoring, and distribution for MCP-based declarative agents in Microsoft 365 admin center. Use when asked to publish, deploy, approve, block, assign, govern, monitor, troubleshoot, or manage Microsoft 365 agents, shared agents, Microsoft agents, external partner agents, or frontier agents.

Build, validate, and optimize Microsoft 365 Copilot declarative agents with v1.5 schema, TypeSpec, Microsoft 365 Agents Toolkit, capabilities, conversation starters, localization, and Agents Playground testing. Use when the user asks for Microsoft 365 declarative agents development, manifest design, TypeSpec migration, or validation.

Explain, design, build, and optimize Microsoft Fabric Lakehouse solutions using OneLake, Delta tables, Files, SQL analytics endpoints, semantic models, shortcuts, schemas, materialized views, Spark views, security, lineage, ingestion, and table optimization. Use when the user asks about Fabric Lakehouse concepts, architecture, data layout, shortcuts, PySpark, loading data, or Lakehouse best practices.

Integrate Microsoft Graph SDK in .NET, TypeScript/JavaScript, or Python applications using correct authentication, permissions, SDK clients, pagination, batching, delta queries, change notifications, throttling, and Microsoft 365 resource paths. Use when accessing users, mail, calendar, Teams, OneDrive, SharePoint, groups, search, or other Microsoft 365 data through Graph.

Guide Power BI semantic model design and optimization for well-documented models with star schema checks, DAX measures, relationships, RLS, naming, descriptions, calculation groups, performance tuning, and model validation. Use when working with Power BI semantic models, creating measures, adding relationships, configuring cardinality or cross-filter direction, documenting models, or optimizing DAX and model performance.

Use the WorkIQ `CLI/MCP` server to query Microsoft 365 work data such as emails, meetings, documents, Teams messages, people, and projects for live organizational context. Use when the user asks for agenda summaries, follow-ups, document lookup, stakeholder or project context, blockers, recommendations, or Microsoft 365 work intelligence.

Open and read a browser-based visual whiteboard for GitHub Copilot CLI collaboration. Use when the user says "let's napkin", "open a napkin", "start a whiteboard", "check the napkin", "look at the napkin", or asks GitHub Copilot to interpret sketches, sticky notes, diagrams, and shared napkin snapshots.

Translate GitHub Copilot CLI approvals, command output, errors, jargon, and completion summaries into plain English for non-technical users. Use this skill when the user says "turn on noob mode", asks for jargon-free explanations, wants risk explained before actions, or needs terminal output translated.

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.

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.

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.

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.

Analyzes Azure IaC and current Azure cost or utilization evidence to identify, quantify, and prioritize savings. Use when reviewing Azure spend, right-sizing resources, reducing waste, or preparing evidence-based cost optimization issues.

Creates and validates professional, accessible, editable draw.io diagrams with official Microsoft, Azure, and GitHub product or service icons plus recorded provenance. Use when generating or updating architecture, deployment, network, flow, sequence, ER, UML, trust-boundary, or branded product diagrams as self-contained .drawio source with optional SVG export.