paulasilvatech
- 2.4k skills
- 0 followers
- 21 repo stars
- 6 days ago last updated
- ▌ Flowstudio Power Automate Governance 4 · paulasilvatechGovern Power Automate flows and Power Apps at scale with the FlowStudio MCP cached store by classifying business impact, detecting orphaned resources, auditing connectors, enforcing compliance metadata, configuring notification rules, and computing archive or governance scores. Use when asked to tag flows, assign governance ownership, offboard makers, review compliance, audit security, or write governance metadata to FlowStudio.
- ▌ Flowstudio Power Automate Monitoring 4 · paulasilvatechMonitor tenant-wide Power Automate health through the FlowStudio MCP cached store. Use when users ask for aggregate failure rates, run-health trends, maker/app inventory, inactive owners, compliance/health reports, monitored flows, or tenant governance summaries. Requires FlowStudio for Teams or MCP Pro+.
- ▌ Microsoft Code Reference 5 · paulasilvatechLook up official Microsoft API references, SDK signatures, packages, and working code samples before writing or fixing Azure SDK, .NET, Microsoft Graph, or Microsoft API code. Use when verifying method names, overloads, parameters, authentication patterns, package names, deprecations, RBAC errors, or suspected hallucinated Microsoft SDK calls.
- ▌ Python Feature Lifecycle 3 · paulasilvatechGuidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next. Use when changing API lifecycle stages or feature annotations.
- ▌ Backstage External Integrations 3 · paulasilvatech bundleConfigure, secure, and validate Backstage technical integrations with GitHub, Azure and Azure DevOps, and ServiceNow across catalog discovery, events, software templates, CI/CD views, incidents, and provider credentials. Use when setting up or troubleshooting integrations outside user sign-in.
- ▌ Azure Managed Redis Cache 5 · paulasilvatech bundleUse 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 semantic cache", "provision Azure Managed Redis", "add vector memory".
- ▌ Azure Observability Stack 7 · paulasilvatech bundleDeploys and operates Prometheus, Grafana, Loki, and Alertmanager for Open Horizons observability. Use this skill when deploying the monitoring stack, configuring dashboards, validating alert rules, checking metrics, reviewing SLO signals, or troubleshooting observability behavior.
- ▌ Microsoft Agent Framework 7 · paulasilvatech bundleCreate, 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.
- ▌ Python Package Management 3 · paulasilvatechGuide for managing packages in the Agent Framework Python monorepo, including creating new connector packages, versioning, and the lazy-loading pattern. Use when adding, modifying, or releasing packages.
- ▌ Sdd Requirements Engineer 10 · paulasilvatech bundleElicits, 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.
- ▌ Remember Interactive Programming 4 · paulasilvatechRemind the agent to work as an interactive programmer against a live system or REPL, using evaluated behavior as the source of truth, explaining hidden evaluations to the human, preferring structural editing, and maintaining a todo list. Use when a user wants REPL-driven programming guidance, especially for Clojure or Backseat Driver workflows.
- ▌ Create Architectural Decision Record 7 · paulasilvatechCreate 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.
- ▌ Openapi To Application Code 8 · paulasilvatechGenerate complete production-ready application code from an OpenAPI specification, including project structure, models, controllers, services, repositories, validation, error handling, tests, documentation, and environment files. Use this skill when the user asks to generate an application from an OpenAPI spec, scaffold an API server from OpenAPI, or turn an OpenAPI URL, file, or pasted spec into runnable code.
- ▌ React Container Presentation Component 4 · paulasilvatech bundleCreate a React Container/Presentation component under src/components with TypeScript, Storybook, SCSS module, ui/features classification, optional Mantine replacement, and validation. Use when explicitly asked for a Container/Presentation component or when running /react-container-presentation-component.
- ▌ Backstage Catalog DB Performance 3 · paulasilvatech bundleRun and compare the Backstage catalog query performance battery against a safe database replica, capture PostgreSQL plans and buffers, detect regressions, and update the baseline. Use when changing catalog queries, indexes, schemas, or database performance behavior.
- ▌ Plugin Analytics Instrumentation 4 · paulasilvatechInstrument Backstage frontend plugins with meaningful Analytics API events and tests while avoiding duplicate BUI navigation events or UI noise. Use when adding or reviewing captureEvent, AnalyticsContext, event taxonomy, noTrack overrides, or analytics behavior.
- ▌ Qdrant Tenant Scaling 2 · paulasilvatechGuides Qdrant multi-tenant scaling. Use when someone asks 'how to scale tenants', 'one collection per tenant?', 'tenant isolation', 'dedicated shards', or reports tenant performance issues. Also use when multi-tenant workloads outgrow shared infrastructure.
- ▌ Azure Kubernetes Automatic Readiness 4 · paulasilvatech bundleAssess Kubernetes workloads and cluster configuration for AKS Automatic compatibility, identify incompatibilities, generate fixes, and guide migration from AKS Standard to AKS Automatic. Use when the user wants to migrate to AKS Automatic, check AKS Automatic readiness, validate manifests for Automatic, assess a cluster for Automatic compatibility, fix a deployment for Automatic, or identify AKS Automatic migration blockers.
- ▌ Project Workflow Analysis Blueprint Generator 4 · paulasilvatechGenerate technology-agnostic project workflow analysis blueprints that document end-to-end application flows, files, classes, entry points, service layers, data access, error handling, async processing, sequence diagrams, testing patterns, and implementation templates. Use this skill when the user asks to list all files/classes in a workflow, document representative workflows, map an API-to-database flow, or create an implementation-ready workflow blueprint.
- ▌ Github Pipeline Diagnostics 3 · paulasilvatechPipeline diagnostics analyzes GitHub Actions CI/CD failures and remediation patterns. Use this skill when diagnosing workflow failures, build errors, deploy failures, failed jobs or steps, logs triage, actions permissions, OIDC failures, dependency cache issues, and CI/CD debugging.
- ▌ Open Horizons Ears Validate 3 · paulasilvatechUse when validating requirements against EARS notation patterns. Triggers include "EARS", "requirement review", "requirement quality", "shall statement", and "REQ-ID".
- ▌ Open Horizons Orchestration 3 · paulasilvatechClassifies and coordinates repository work across Open Horizons agents with bounded delegation, validation, review, and approval gates. Use when handling cross-domain maintenance, feature, improvement, modernization, incident, review, or explicitly requested greenfield workflows.
- ▌ Open Horizons Prerequisites 3 · paulasilvatech bundleValidates and sets up local CLI tools and access needed before Open Horizons deployment. Use this skill when checking required tool availability, verifying minimum versions, preparing Azure login readiness, validating CI/CD runner prerequisites, or producing a prerequisite checklist.
- ▌ Open Horizons Workspace Kit 3 · paulasilvatech bundlePlans, applies, inspects, or uninstalls Open Horizons repository customizations with conflict detection and managed-file state. Use when publishing the AEG feature, the full toolkit, instructions, VS Code prompts, safety hooks, MCP configuration, workflows, or issue templates to a target repository.
- ▌ Plugin New Frontend System Support 4 · paulasilvatechAdd new frontend-system support to an existing Backstage plugin while retaining its legacy entry point. Use when published or shared plugins need dual compatibility, alpha exports, PageBlueprint extensions, route reuse, and both old and new app consumers.
- ▌ Github Copilot Usage Metrics 3 · paulasilvatech bundleRetrieve and display GitHub Copilot usage metrics for organizations and enterprises using the GitHub CLI, REST API, and bundled scripts. Use when the user asks about Copilot usage, adoption, active users, acceptance rates, suggestions, chat interactions, per-user breakdowns, organization metrics, enterprise metrics, or usage on a specific date.
- ▌ Qdrant Vertical Scaling 2 · paulasilvatechGuides Qdrant vertical scaling decisions. Use when someone asks 'how to scale up a node', 'need more RAM', 'upgrade node size', 'vertical scaling', 'resize cluster', 'scale up vs scale out', or when memory/CPU is insufficient on current nodes. Also use when someone wants to avoid the complexity of horizontal scaling.
- ▌ Create Github Action Workflow Specification 4 · paulasilvatechCreates formal, AI-optimized specifications for existing GitHub Actions CI/CD workflows by extracting triggers, jobs, dependencies, contracts, quality gates, error paths, environments, governance, and change rules. Use this skill when asked to document a workflow, create a CI/CD workflow specification, summarize a GitHub Actions file for maintenance, or produce spec/spec-process-cicd-[workflow-name].md.
- ▌ Azure Well Architected Review 7 · paulasilvatechReviews Azure workload IaC and current resource evidence against all five Azure Well-Architected Framework pillars. Use when assessing reliability, security, cost optimization, operational excellence, or performance efficiency and preparing prioritized findings.
- ▌ Open Horizons Azure Readiness 3 · paulasilvatechAssesses read-only Azure readiness for one Open Horizons deployment scope using current subscription, provider, quota, SKU, identity, network, and resource evidence. Use when needed before Terraform planning or deployment when Azure prerequisites may block the requested components.
- ▌ Open Horizons Security Review 3 · paulasilvatechPerforms an independent, read-only security review of one Open Horizons change or surface with severity-ranked, evidence-backed findings and verification criteria. Use when reviewing code, Terraform, Kubernetes, identity, workflows, Backstage, MAF agents, MCP tools, secrets, or policy review.
- ▌ Azure Resource Health Diagnose 8 · paulasilvatechAnalyze 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.
- ▌ Backstage Mui To Bui Migration 3 · paulasilvatech bundleMigrate Backstage app or plugin UI from Material-UI to Backstage UI with version-checked component mappings, CSS setup, accessibility, analytics, styling, and visual validation. Use when replacing @material-ui imports, MUI icons, makeStyles, or adopting BUI.
- ▌ Github Codespaces Golden Paths 3 · paulasilvatech bundleConfigures GitHub Codespaces devcontainer environments for Backstage Golden Path templates. Use this skill when creating or validating devcontainer.json, Codespaces setup, Python FastAPI templates, Node app templates, Terraform templates, Java templates, AI/ML pipelines, data pipelines, container features, SDK pre-installation, or template mapping.
- ▌ Open Horizons Backstage Search 3 · paulasilvatechInstall, configure, extend, operate, and troubleshoot Backstage Search frontends, engines, collators, indices, result extensions, filters, schedules, and permissions. Use when working with search pages, Catalog or TechDocs indexing, custom collators, Postgres or Elasticsearch, or missing results.
- ▌ Open Horizons Terraform Change 3 · paulasilvatech bundleImplements and validates one bounded Open Horizons Terraform change in terraform/modules or an isolated terraform/environments root. Use when changing a module, environment root, provider constraint, backend declaration, import block, or state-aware Terraform contract without applying infrastructure.
- ▌ Qdrant Horizontal Scaling 2 · paulasilvatechDiagnoses and guides Qdrant horizontal scaling decisions. Use when someone asks 'vertical or horizontal?', 'how many nodes?', 'how many shards?', 'how to add nodes', 'resharding', 'data doesn't fit', or 'need more capacity'. Also use when data growth outpaces current deployment.
- ▌ Github Actions Runtime Upgrade Conventions 4 · paulasilvatechUpgrade GitHub Actions workflow dependencies to supported runtimes while preserving behavior. Use this skill when logs report deprecated Node.js action runtimes, when editing `.github/workflows/*.yml` or `.github/workflows/*.yaml`, or when choosing pinned action versions and validating upgraded workflow runs.
- ▌ Plugin Full Frontend System Migration 4 · paulasilvatechFully migrate a Backstage frontend plugin to the new frontend system and remove legacy support. Use when performing internal or intentionally breaking migrations from createPlugin to createFrontendPlugin, new route refs, blueprints, PageLayout, and legacy dependency removal.
- ▌ Azure Draw Io Diagram Generator 4 · paulasilvatech bundleCreates 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.
- ▌ Foundry Hosted Agent Copilotkit 7 · paulasilvatech bundleGuide 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.
- ▌ Open Horizons Backstage Catalog 3 · paulasilvatechModel, register, discover, validate, and troubleshoot Backstage Software Catalog entities, providers, processors, ownership, relations, locations, and lifecycle. Use when handling catalog-info YAML, entity ingestion, org discovery, duplicate entities, or catalog governance.
- ▌ Open Horizons Backstage Upgrade 3 · paulasilvatechPlan, execute, and validate Backstage application or plugin dependency upgrades with release-aware package alignment, migrations, config review, changesets, and rollback. Use when bumping Backstage versions, resolving package skew, adopting new systems, or preparing an upgrade PR.
- ▌ Open Horizons Sre Investigation 3 · paulasilvatechInvestigates one Open Horizons reliability symptom or incident through read-only telemetry, timeline construction, causal hypothesis testing, ownership assignment, and verification planning. Use when investigating outages, latency, errors, unhealthy workloads, alerts, SLO breaches, or deployment regressions.
- ▌ Qdrant Sliding Time Window 2 · paulasilvatechGuides sliding time window scaling in Qdrant. Use when someone asks 'only recent data matters', 'how to expire old vectors', 'time-based data rotation', 'delete old data efficiently', 'social media feed search', 'news search', 'log search with retention', or 'how to keep only last N months of data'.
- ▌ Create Github Issues Feature From Implementation Plan 4 · paulasilvatechCreate or update GitHub issues from implementation-plan phases using feature_request.yml or chore_request.yml templates when available. Use when the user asks to turn an implementation plan into GitHub issues, file one issue per phase, or deduplicate planned feature/chore work against existing issues.
- ▌ Create Github Issue Feature From Specification 4 · paulasilvatechCreate or update one GitHub feature issue from a specification file using a feature_request.yml template when available. Use when the user asks to create a GitHub issue from a specification, turn a spec into a feature request, or file one issue that captures a complete specification.
- ▌ Open Horizons Backstage Techdocs 3 · paulasilvatechConfigure, build, preview, publish, migrate, and troubleshoot Backstage TechDocs and MkDocs content. Use when handling techdocs-ref annotations, mkdocs.yml, local or external builders, object-storage publishers, CI generation, broken docs, or wiki-to-TechDocs migration.
- ▌ Open Horizons Portal Integration 3 · paulasilvatech bundleImplements and validates one product-specific integration in the existing Open Horizons Backstage portal and agent services. Use when wiring routes, plugins, catalog entities, app configuration, AI Chat SSE behavior, runtime APIs, or Backstage Kubernetes manifests without provisioning Azure or deploying live workloads.
- ▌ Azure Appinsights Instrumentation 3 · paulasilvatech bundleInstrument 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.
- ▌ Azure Postgre Database Management 7 · paulasilvatechPerforms database operations and health monitoring for Open Horizons platform data services. Use this skill when checking PostgreSQL health, validating connections, reviewing backup settings, monitoring database size or active sessions, checking migrations, or troubleshooting database behavior.
- ▌ Open Horizons Backstage Framework 3 · paulasilvatechChoose and implement Backstage framework extension points, core backend services, frontend blueprints, service refs, modules, lifecycle, auth, permissions, schedulers, tracing, metrics, and generated API references. Use when designing plugin architecture or selecting supported framework APIs.
- ▌ Mui To Bui Migration 5 · paulasilvatechMigrate Backstage plugins from Material-UI (MUI) to Backstage UI (BUI). Use this skill when migrating components, updating imports, replacing styling patterns, or converting MUI components to their BUI equivalents.
- ▌ Foundry Agent Framework Py Release 3 · paulasilvatechUse when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle tiers (alpha, beta, rc, released) with CHANGELOG-driven selective bumps, floor bound checks, and post-bump validation.
- ▌ Github Copilot Harness Engineering 3 · 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.
- ▌ Open Horizons Backstage AI Catalog 3 · paulasilvatechInstall and use Backstage's AI catalog model for AiResource skills and rules plus mcp-server API entities, ownership, lifecycle, relationships, and source locations. Use when cataloging AI skills, governance rules, agents, or MCP servers.
- ▌ Open Horizons Backstage Kubernetes 3 · paulasilvatechInstall, configure, authorize, and troubleshoot Backstage Kubernetes frontend and backend plugins, cluster discovery, entity annotations, authentication, permissions, proxies, custom resources, and service-owner views. Use when working with Kubernetes tabs, clusters, pods, or integration errors.
- ▌ Open Horizons Backstage Operations 3 · paulasilvatechOperate, monitor, troubleshoot, and harden production Backstage services, databases, schedulers, integrations, health endpoints, logs, and deployments. Use when handling startup failures, readiness problems, database errors, provider refresh issues, performance incidents, or production runbooks.
- ▌ Open Horizons Deploy Orchestration 3 · paulasilvatech bundleCoordinates end-to-end Open Horizons platform deployment across prerequisites, Terraform, Kubernetes, GitOps, and verification. Use this skill when planning or executing full platform deployment, dry-run deployment, horizon enablement, deployment sequence, post-deploy verification, or deployment troubleshooting.
- ▌ Open Horizons Deployment Operation 3 · paulasilvatechExecutes one approval-gated Open Horizons deployment, rollout, rollback, or verification from an immutable change package. Use when the exact environment, artifact, command, expected actions, approval, validation, and rollback are already known.
- ▌ Qdrant Memory Usage Optimization 2 · paulasilvatechDiagnoses and reduces Qdrant memory usage. Use when someone reports 'memory too high', 'RAM keeps growing', 'node crashed', 'out of memory', 'memory leak', or asks 'why is memory usage so high?', 'how to reduce RAM?'. Also use when memory doesn't match calculations, quantization didn't help, or nodes crash during recovery.
- ▌ Qdrant Search Speed Optimization 2 · paulasilvatechDiagnoses and fixes slow Qdrant search. Use when someone reports 'search is slow', 'high latency', 'queries take too long', 'low QPS', 'throughput too low', 'filtered search is slow', or 'search was fast but now it's slow'. Also use when search performance degrades after config changes or data growth.
- ▌ Spark CLI 2 · paulasilvatech bundleAuthor, run and diagnose Fabric Spark: notebook cell code (%%configure, %%sql, PySpark, notebookutils), named notebook runs, Livy-session ad-hoc calculations, Spark failure triage, and the whole Materialized Lake View lifecycle -- definition, incremental-refresh readiness review, schedules, refresh jobs, run history and refresh-failure diagnosis. KQL materialized views are eventhouse-cli. Triggers:write notebook code,run notebook,notebookutils,create a Livy session,failed notebook,Spark OOM,create materialized lake view,schedule MLV,diagnose MLV refresh failure
- ▌ Sqldb CLI 2 · paulasilvatech bundleDesign, read and troubleshoot a Fabric SQL database item (OLTP, SQL Server engine): schema with constraints, indexes and vector columns; sqlcmd lookups including temporal and similarity search; Query Store, blocking and regressed-plan investigation. Warehouse items belong to sqldw-cli. Triggers:create sqldb table,sqldb foreign key,dacpac deploy,sqldb sys.tables,vector similarity sqldb,sqldb query store,sql database blocked sessions
- ▌ Sqldw CLI 2 · paulasilvatech bundleAuthor, query and diagnose Fabric Warehouse, Lakehouse SQL endpoints and Mirrored Databases: DDL/DML and COPY INTO ingestion, read-only T-SQL SELECT and row counts over lakehouse tables, and queryinsights performance triage. Fabric SQL database (OLTP) is sqldb-*-cli. Triggers:query warehouse,count rows lakehouse,SELECT lakehouse,create warehouse table,COPY INTO,warehouse MERGE,slowest warehouse queries,queryinsights CPU
- ▌ Azure Agentic Architecture Patterns 7 · paulasilvatech bundleProvides 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.
- ▌ Azure Import Infrastructure As Code 3 · paulasilvatechImports existing Azure resources into Terraform through read-only discovery, dependency mapping, Azure Verified Module selection, source-derived import addresses, and drift-safe plans. Use when reverse-engineering a subscription, resource group, or ARM resource ID into maintainable IaC.
- ▌ Backstage Onboard To Openapi Server 3 · paulasilvatech bundleMigrate a Backstage backend plugin from a hand-written Express router to the repository's typed OpenAPI server tooling while preserving routes, auth, permissions, errors, tests, and optional client generation. Use when onboarding createOpenApiRouter or modernizing a router with OpenAPI.
- ▌ Open Horizons Backstage Aeg Feature 3 · paulasilvatech bundleOperates and integrates the Open Horizons Agentic Engineering Graph (AEG) through Backstage with authenticated run management, G1/G2 decisions, traceability analytics, and golden-path harvesting. Use this skill when starting or inspecting AEG runs, reviewing gates, analyzing AEG evidence, proposing reusable profiles, or wiring the AEG feature into the Open Horizons portal.
- ▌ Skill Creator 5 · paulasilvatech bundleCreate, audit, repair, and improve GitHub Copilot Agent Skills for VS Code, GitHub Copilot CLI, and GitHub Copilot cloud agent. Use when a user asks to create a skill, generate a SKILL.md, convert a workflow into a reusable skill, audit an existing skill, fix skill loading issues, optimize a skill description, validate frontmatter, or add references/scripts/assets to a skill package.
- ▌ Napkin 4 · paulasilvatech bundleOpen 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.
- ▌ Eyeball 4 · paulasilvatech bundleAnalyze local documents or web pages with inline source screenshots in a Word document. Use when asked to use eyeball, run eyeball on a document, analyze a PDF, Word, RTF, or URL with visual proof, or produce a cited report where every factual claim is backed by highlighted source screenshots.
- ▌ Roundup 4 · paulasilvatechGenerate personalized status briefings from a configured Roundup profile and available data sources such as GitHub, email, Teams, Slack, and Google Workspace. Use when the user asks for a roundup, leadership briefing, team update, weekly status, audience-specific update, or draft in their communication style.
- ▌ Copilot Primitive Authoring 5 · paulasilvatechAuthor current GitHub Copilot agents, instructions, and VS Code prompts in this repository. Use when asked to create or update a known primitive type with repository governance, dated evidence, canonical sources, templates, synchronization, and type-specific validation.
- ▌ Arize Link 4 · paulasilvatech bundleGenerate 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.
- ▌ Noob Mode 4 · paulasilvatech bundleTranslate 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.
- ▌ Phoenix CLI 4 · paulasilvatech bundleDebug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review experiments, query annotation configs, and use the GraphQL API. Use when the user is analyzing traces or spans, investigating LLM/agent failures, deciding what to do after instrumenting an app, building failure taxonomies, choosing what evals to write, or asking "what's going wrong", "what kinds of mistakes", or "where do I focus" — even without naming a technique.
- ▌ Arize Trace 4 · paulasilvatech bundleDownload, 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.
- ▌ Phoenix Evals 4 · paulasilvatech bundleBuild, run, validate, and operationalize Phoenix evaluators for AI and LLM applications in Python or TypeScript, including code evaluators, LLM judges, RAG evals, experiments, datasets, tracing, sampling, error analysis, and production guardrails. Use when the user asks for Phoenix evals, evaluator design, judge validation, experiments, or AI quality monitoring.
- ▌ Roundup Setup 4 · paulasilvatech bundleRun conversational onboarding for Roundup status briefings and write the user style configuration. Use this skill when the user asks to set up roundup, calibrate status updates, configure briefings, personalize communication style, or change how this conversation should feel.
- ▌ Doc And Modernize 4 · paulasilvatech bundleTwo 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.
- ▌ Arize Dataset 4 · paulasilvatech bundleCreates, 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.
- ▌ Desk Open 4 · paulasilvatechCreate and open a new workshop desk with a journal and .signals directory. Use when the operator wants to start a new workstream, work does not belong to an existing desk, or a topic needs its own durable frame, history, priors, and signal trail.
- ▌ Copilot Sdk 4 · paulasilvatech bundleBuild agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or creating custom agents. Triggers on Copilot SDK, GitHub SDK, agentic app, embed Copilot, programmable agent, MCP server, custom agent.
- ▌ Doublecheck 4 · paulasilvatech bundleRuns a three-layer verification pipeline for AI output by extracting verifiable claims, checking web sources, applying adversarial hallucination review, and producing inline or full verification reports. Use this skill when the user asks to "doublecheck", "verify that", "run full verification", "fact-check this", or keep factual claim verification active.
- ▌ Daily Focus Board 4 · paulasilvatech bundleCreate a personal daily focus board in a browser canvas from a self-contained HTML template. Use when the user wants to plan their day, get organized, stay focused, kick off a work session, track task progress, add counters for pages/pomodoros/reps, use Focus mode, or save an end-of-day recap with localStorage persistence.
- ▌ Gtm AI Gtm 4 · paulasilvatech bundleCreate go-to-market strategy for AI products, including enterprise positioning, buyer readiness, trust sequencing, variable-cost pricing, and copilot/agent/teammate framing. Use this skill when positioning AI products, handling production-responsibility objections, pricing variable-cost AI, or selling autonomous tools into enterprises.
- ▌ MCP CLI 6 · paulasilvatechUse 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.
- ▌ Phoenix Tracing 4 · paulasilvatech bundleInstrument Python and TypeScript LLM applications with Phoenix AI observability using OpenInference semantic conventions, arize-phoenix-otel, @arizeai/phoenix-otel, spans, sessions, metadata, annotations, and production masking. Use when setting up Phoenix tracing, creating custom spans, adding OpenInference attributes, or deploying tracing to production.
- ▌ Bench Read 4 · paulasilvatechRead artifacts from a workshop bench where desks leave findings, verdicts, drafts, reports, journals, and cross-desk work products. Use this skill when starting a session, reviewing another desk's output, routing work, or answering "what's on the bench?".
- ▌ Arize Evaluator 4 · paulasilvatech bundleCreate, 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.
- ▌ Pr Screenshots 4 · paulasilvatechEmbed before/after screenshots and annotated images in pull request descriptions so reviewers can inspect visible changes quickly. Use this skill when a PR changes layout, styling, CSS, charts, dashboards, data visualizations, UI components, forms, modals, error messages, CLI output, or log formatting.
- ▌ UI Screenshots 4 · paulasilvatechCapture screenshots of web apps during development using Playwright and PIL. Use this skill when you need to; capture the current state of a running web app; document a UI before and after a code change.
- ▌ Arize Annotation 4 · paulasilvatech bundleCreate, 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".
- ▌ Arize Experiment 4 · paulasilvatech bundleCreate, 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.
- ▌ Azure AI 4 · paulasilvatech bundleBuild 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.
- ▌ Webmcpify 4 · paulasilvatech bundleMake 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.
- ▌ Drawio 4 · paulasilvatech bundleGenerate draw.io diagrams as native .drawio files and export them to PNG, SVG, or PDF with embedded XML. Use when the user asks for draw.io diagrams, diagrams.net XML, mxGraphModel, editable diagram source, or exporting .drawio files for documents.
- ▌ Desk Journal 4 · paulasilvatechRead, write, or append persistent desk journal entries that survive session boundaries and capture what was done, current state, next step, dead ends, artifacts, and desk closure handoffs. Use when the user asks to resume from a journal, write an end-of-session entry, add a mid-session checkpoint, or record a desk wind-down.
- ▌ Signal Write 4 · paulasilvatechEmit structured agent signals as JSON files under desk .signals directories and journal markers for dashboard consumption. Use when a desk needs hands-up or blocked operator attention, work is done and ready for review, significant progress needs a checkpoint, two desks disagree, or a TA reports partnership coordination quality.