paulasilvatech
- 1.8k skills
- 0 followers
- 1 day ago last updated
- ▌ Build Evidence Map · paulasilvatech bundleBuild auditable evidence maps for contested technical choices, research synthesis, proposal review, and consequential decisions. Use this skill when GitHub Copilot must preserve supporting, contradicting, qualifying, and missing evidence with exact source regions instead of collapsing disagreement into prose.
- ▌ Cobol Db2 Analysis · paulasilvatechAnalyze COBOL programs, copybooks, PERFORM and CALL structure, file and VSAM access, embedded EXEC SQL and EXEC CICS, DB2 DDL, DCLGEN structures, cursors, and JCL job steps with source citations. Use when reading or inventorying a COBOL/DB2 legacy system before modernization.
- ▌ Code Modernization · paulasilvatechUse 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.
- ▌ Convert Word To Md · paulasilvatech bundleConvert Word .docx documents into Markdown with extracted images using the bundled script. Use this skill when a user asks to read, summarize, review, compare, analyze, extract data from, or batch-process Word documents, resumes, reports, contracts, or proposals, including mixed folders that also require sibling PDF or Excel conversion skills.
- ▌ Declarative Agents · paulasilvatechBuild, 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.
- ▌ Dotnet MCP Builder · paulasilvatech bundleBuild 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.
- ▌ Foundry Agent Sync · paulasilvatechCreate, 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.
- ▌ Markstream Install · paulasilvatech bundleInstall and configure Markstream streaming Markdown renderers for Vue, React, Svelte, Angular, Nuxt, Next.js, and Vue 2 applications. Use when adding streaming Markdown to AI chat or document interfaces, repairing Markstream styles or SSR, or choosing static, smooth-streaming, or externally parsed AST input.
- ▌ MCP Security Audit · paulasilvatechAudits 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.
- ▌ Mini Context Graph · paulasilvatech bundleA persistent, compounding knowledge base combining Karpathy's LLM Wiki pattern with a structured knowledge graph. Ingest documents once — the LLM writes wiki pages, extracts entities/relations into the graph, and stores raw content for evidence retrieval. Knowledge accumulates and cross-references; it is never re-derived from scratch. Use this skill when |--------|---------|-------------|; | `skill.ingest_with_content(doc_id, title, source, raw_content, entities, relations)` | Full RAG ingest: raw docs + graph + provenance |; | `skill.add_node(name, node_type)` | Add single entity (no provenance) | Quick additions without a source doc |.
- ▌ Penpot Uiux Design · paulasilvatech bundleCreate, review, and improve professional UI/UX designs in Penpot using penpot/penpot-mcp tools, design systems, component patterns, accessibility checks, and platform guidelines. Use when asked to design a UI, create interface, build layout, design dashboard, create form, design landing page, make it accessible, design system, component library, or improve an existing Penpot file.
- ▌ Qdrant Clients Sdk · paulasilvatechSelect and use official Qdrant client SDKs, REST API, gRPC API, and curated snippet search. Use this skill when the user asks for Qdrant API reference, client installation commands, SDK language choice, upload point examples, FastEmbed setup, or REST versus gRPC guidance.
- ▌ Ruff Recursive Fix · paulasilvatechRun Ruff checks with optional scope and rule overrides, apply safe and unsafe autofixes iteratively, review each change, and resolve remaining findings with targeted edits or user decisions. Use this skill when the user asks for inputs.
- ▌ Azure Cloud Migrate · paulasilvatech bundleAssess 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.
- ▌ Azure Developer CLI · paulasilvatech bundleDesign, create, review, migrate, or troubleshoot Azure Developer CLI azd projects using azure.yaml, infra Bicep or Terraform, environments, secrets, hooks, deployment workflows, and azd-managed CI/CD. Use this skill when the user asks for azd project structure, Azure Developer CLI best practices, azd templates, or azure.yaml guidance.
- ▌ Azure Role Selector · paulasilvatech bundleSelect the least-privilege Azure RBAC role for an identity, compare built-in and custom role options, and produce assignment commands or Bicep snippets. Use this skill when the user asks which Azure role to assign for permissions, scopes, identities, data-plane access, control-plane access, custom roles, or access requirements.
- ▌ Azure Terraform CLI · paulasilvatechTerraform CLI operations manage Azure infrastructure as code through Terraform formatting, validation, initialization, planning, apply workflows, destroy workflows, state inspection, import workflows, module development, provider lock files, tfvars, and security scanning. Use this skill when working with terraform init, plan, apply, destroy, validate, fmt, state, import, or tfsec workflows.
- ▌ Breakdown Epic Arch · paulasilvatechCreate a high-level epic architecture specification from an Epic PRD, including system diagrams, technical enablers, stack choices, technical value, and t-shirt sizing. Use when asked to write an epic architecture spec, turn a PRD into architecture, or produce docs/ways-of-work arch.md.
- ▌ Centos Linux Triage · paulasilvatechDiagnose and remediate CentOS Linux incidents with RHEL-compatible systemd, journal, dnf/yum, SELinux, firewalld, and rollback practices. Use when the user asks to triage CentOS service failures, package issues, boot problems, networking/firewall symptoms, or security-policy denials.
- ▌ Codebase Memory MCP · paulasilvatechUse a configured Codebase Memory MCP graph for architecture orientation, symbol lookup, callers and callees, dependency or data-flow tracing, impact analysis, and unfamiliar module discovery. Use this skill when a codebase-memory-mcp server is available or the user explicitly requests Codebase Memory.
- ▌ Conventional Branch · paulasilvatechCreate, normalize, validate, and check out Git branches following the Conventional Branch specification with feature/, bugfix/, hotfix/, release/, and chore/ prefixes. Use when creating a new branch, naming a branch, or checking branch-name compliance.
- ▌ Convert Excel To Md · paulasilvatech bundleConvert Excel .xlsx workbooks to Markdown with the bundled script so spreadsheet contents can be read, summarized, searched, extracted, compared, charted, or analyzed. Use whenever the user references a spreadsheet, workbook, budget, export, tracker, .xlsx file, or a folder of workbooks; invoke sibling converters for mixed .pdf, .docx, and .xlsx sets.
- ▌ Debian Linux Triage · paulasilvatechDiagnose and remediate Debian Linux incidents with apt, dpkg, systemd, journal analysis, AppArmor-aware checks, firewall review, and rollback practices. Use when the user asks to triage Debian service failures, package issues, boot problems, network symptoms, or security-profile denials.
- ▌ Devops Rollout Plan · paulasilvatechGenerate production-ready DevOps rollout plans for infrastructure, application, configuration, and data changes, including preflight checks, phased deployment, verification signals, rollback procedures, communication plan, contingency handling, and post-deployment tasks. Use when the user asks for a rollout plan, deployment plan, release plan, production change plan, or go/no-go checklist.
- ▌ Fedora Linux Triage · paulasilvatechDiagnose and remediate Fedora Linux incidents with dnf, systemd, journal analysis, SELinux, firewalld, release-upgrade awareness, and rollback practices. Use when the user asks to triage Fedora service failures, package issues, boot problems, network/firewall symptoms, or SELinux denials.
- ▌ Gen Specs As Issues · paulasilvatechIdentify missing features, prioritize implementation gaps, write practical MVP specifications, and create GitHub issues with dependencies and acceptance criteria. Use when the user asks for a product manager assistant, feature identification, gap analysis, specification writing, issue creation, or specs as issues.
- ▌ Harness Engineering · paulasilvatechAdopt or review repository-level harness engineering for GitHub Copilot and coding agents. Use when users want durable agent instructions, guardrails, regression checks, drift checks, failure memory, or adoption reports that prevent repeated AI coding-agent mistakes in a target repository.
- ▌ Incident Postmortem · paulasilvatechUse when an outage, production incident, or significant service degradation has occurred and the team needs to write a structured blameless post-mortem. Triggers on phrases like "write a post-mortem", "incident review", "what went wrong", "outage report", "root cause analysis", or "RCA". Covers timeline reconstruction, contributing factor analysis, impact quantification, and action item generation with owners.
- ▌ Mkdocs Translations · paulasilvatechTranslate an MkDocs documentation stack from docs/docs/en and docs/docs/includes/en into a target ISO 639-1 or locale folder, preserving Markdown structure and updating mkdocs.yml i18n locale, nav_translations, and admonition_translations. Use when the user asks for mkdocs ai translator, MkDocs translation, docs localization, or adding a new documentation locale.
- ▌ Premium Frontend UI · paulasilvatechCraft immersive, high-performance web interfaces with advanced motion, typography, scroll-driven interactions, responsive polish, and product-specific visual direction. Use this skill when the user asks for premium frontend UI, sophisticated animations, Awwwards-style components, high-end landing pages, layout polish, or high-end visual design implementation.
- ▌ React18 String Refs · paulasilvatech bundleMigrate React string refs, ref="name" assignments, and this.refs.name access to React.createRef(), callback refs, or child ref forwarding. Use this skill when migrating React 18.3.1 warnings or React 19 removals involving single refs, multiple refs, list refs, callback refs, or refs passed to child components.
- ▌ Review And Refactor · paulasilvatechReview project code against repository instructions, identify maintainability issues, make focused refactorings without splitting existing files, and validate tests when available. Use this skill when the user asks for code cleanup, maintainability review, best-practice refactoring, standards-driven improvements, or a senior engineering pass over existing code.