thiagofernandes1987-create/APEX - Page 48

azure-upgrade

'Assess and upgrade Azure workloads between plans, tiers, or SKUs within Azure. Generates assessment reports

Langue du texte source : anglais

azure-validate

Deploy — Pre-deployment validation for Azure readiness. Run deep checks on configuration, infrastructure (Bicep or Terraform), RBAC role assignments, managed identity permissions, and prere

Langue du texte source : anglais

capacity

"Analyze — Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares"

Langue du texte source : anglais

cloud-security

"Use — Use when assessing cloud infrastructure for security misconfigurations, IAM privilege escalation paths, S3 public"

Langue du texte source : anglais

copilot-sdk

Build applications powered by GitHub Copilot using the Copilot SDK. Use when creating programmatic integrations with Copilot across Node.js/TypeScript, Python, Go, or .NET. Covers session management,

Langue du texte source : anglais

customize

"Deploy — Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection"

Langue du texte source : anglais

deploy-model

"Deploy — Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments,"

Langue du texte source : anglais

entra-app-registration

"Create — Guides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create"

Langue du texte source : anglais

hosted-agents-v2-py

"Build hosted agents using Azure AI Projects SDK with ImageBasedHostedAgentDefinition.\nUse when creating container-based agents that run custom code in Azure AI Foundry.\nTriggers: \'ImageBasedHostedA"

Langue du texte source : anglais

mcp-builder

"Use — Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external"

Langue du texte source : anglais

microsoft-azure-webjobs-extensions-authentication-events-dotnet

"Use — Microsoft Entra Authentication Events SDK for .NET. Azure Functions triggers for custom authentication extensions."

Langue du texte source : anglais

microsoft-docs

"Use — Understand Microsoft technologies by querying official documentation. Use whenever the user asks how something"

Langue du texte source : anglais

microsoft-foundry

'Deploy, evaluate, and manage Foundry agents end-to-end: Docker build, ACR push, hosted/prompt agent create,

Langue du texte source : anglais

ms365-tenant-manager

"Automate — Microsoft 365 tenant administration for Global Administrators. Automate M365 tenant setup, Office 365 admin tasks,"

Langue du texte source : anglais

podcast-generation

Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creation f

Langue du texte source : anglais

preset

"Deploy — Intelligently deploys Azure OpenAI models to optimal regions by analyzing capacity across all available regions."

Langue du texte source : anglais

secrets-vault-manager

"Use — Use when the user asks to set up secret management infrastructure, integrate HashiCorp Vault, configure cloud"

Langue du texte source : anglais

senior-devops

"Use — Comprehensive DevOps skill for CI/CD, infrastructure automation, containerization, and cloud platforms (AWS,"

Langue du texte source : anglais

skill-creator

"Use — Guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services."

Langue du texte source : anglais

wiki-ado-convert

"Generate — Converts VitePress/GFM wiki markdown to Azure DevOps Wiki-compatible format. Generates a Node.js build script"

Langue du texte source : anglais

googlebigquery-automation

'Automate Google BigQuery tasks via Rube MCP (Composio): run SQL queries, explore datasets and metadata, execute

Langue du texte source : anglais

gcp-cloud-architect

Design GCP architectures for startups and enterprises. Use when asked to design Google Cloud infrastructure, deploy to GKE or Cloud Run, configure BigQuery pipelines, optimize GCP costs, or migrate to

Langue du texte source : anglais

gcp-cloud-run

Implement — Specialized skill for building production-ready serverless

Langue du texte source : anglais

wordpress-theme-development

"Implement — "

Langue du texte source : anglais

wordpress-woocommerce-development

"Implement — "

Langue du texte source : anglais

agent-designer

Implement — Use when the user asks to design multi-agent systems, create agent architectures, define agent communication patterns, or build autonomous agent workflows.

Langue du texte source : anglais

board

Implement — Read, write, and browse the AgentHub message board for agent coordination.

Langue du texte source : anglais

eval

Evaluate and rank agent results by metric or LLM judge for an AgentHub session.

Langue du texte source : anglais

init

Create a new AgentHub collaboration session with task, agent count, and evaluation criteria.

Langue du texte source : anglais

run

Implement — One-shot lifecycle command that chains init → baseline → spawn → eval → merge in a single invocation.

Langue du texte source : anglais

spawn

Implement — Launch N parallel subagents in isolated git worktrees to compete on the session task.

Langue du texte source : anglais

status

Implement — Show DAG state, agent progress, and branch status for an AgentHub session.

Langue du texte source : anglais

api-test-suite-builder

Implement — Use when the user asks to generate API tests, create integration test suites, test REST endpoints, or build contract tests.

Langue du texte source : anglais

autoresearch-agent

Implement — Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy

Langue du texte source : anglais

loop

Implement — Start an autonomous experiment loop with user-selected interval (10min, 1h, daily, weekly, monthly). Uses CronCreate for scheduling.

Langue du texte source : anglais

resume

Implement — Resume a paused experiment. Checkout the experiment branch, read results history, continue iterating.

Langue du texte source : anglais

run

Run a single experiment iteration. Edit the target file, evaluate, keep or discard.

Langue du texte source : anglais

setup

Set up a new autoresearch experiment interactively. Collects domain, target file, eval command, metric, direction, and evaluator.

Langue du texte source : anglais

status

Implement — Show experiment dashboard with results, active loops, and progress.

Langue du texte source : anglais

behuman

Implement — Use when the user wants more human-like AI responses — less robotic, less listy, more authentic. Triggers:

Langue du texte source : anglais