---
id: post/gerardorenteria-blog/13993
type: post
title: "🧠 Agent Skills + MCPs: check your BC extension health in VS Code 🔍"
summary: Agent Skills are reusable instruction packages in VS Code that orchestrate external tools like YAMPI and BC Telemetry Buddy to analyze Business Central extension health across environments. A three-level loading model activates only relevant skills without penalizing context, enabling developers to check extension status, versions, deployments, and lifecycle events in production through a single chat message.
tier: community
language: en
tags:
  - agent skills
  - mcps
  - extension health
  - vs code
  - copilot
  - telemetry
  - orchestration
system: development
review:
  state: reviewed
  by: opus
  at: "2026-10-08T01:56:14.110Z"
  flags: []
generated:
  at: "2026-10-08T01:26:53.141Z"
  pipeline: 0.2.0
  prompts:
    extract-post: 1
  input_hash: 7f8c5cedc7555b2ac5753d5943309e7dfd41d5137204d57c9bc609fdbe9b3d6e
evidence:
  - kind: blog
    url: https://gerardorenteria.blog/2026/03/07/%f0%9f%a7%a0-agent-skills-mcps-check-your-bc-extension-health-in-vs-code-%f0%9f%94%8d/
    title: "🧠 Agent Skills + MCPs: check your BC extension health in VS Code 🔍"
    date: "2026-03-07"
    commit: null
    t: null
    quote: null
  - kind: blog
    url: https://gerardorenteria.blog/2026/03/07/%f0%9f%a7%a0-agent-skills-mcps-check-your-bc-extension-health-in-vs-code-%f0%9f%94%8d/
    title: "🧠 Agent Skills + MCPs: check your BC extension health in VS Code 🔍"
    date: "2026-03-07"
    commit: null
    t: null
    quote: The description is critical because it's what Copilot reads at Level 1 to decide if the skill is relevant.
  - kind: blog
    url: https://gerardorenteria.blog/2026/03/07/%f0%9f%a7%a0-agent-skills-mcps-check-your-bc-extension-health-in-vs-code-%f0%9f%94%8d/
    title: "🧠 Agent Skills + MCPs: check your BC extension health in VS Code 🔍"
    date: "2026-03-07"
    commit: null
    t: null
    quote: You can have many skills installed without penalizing the context, so Copilot only loads what is relevant for each requirement.
links:
  learn: []
  objects: []
  features: []
  topics: []
  localizations: []
  videos: []
  posts: []
  guidelines: []
post_id: "13993"
source_id: gerardorenteria-blog
source_name: Gerardo Renteria
url: https://gerardorenteria.blog/2026/03/07/%f0%9f%a7%a0-agent-skills-mcps-check-your-bc-extension-health-in-vs-code-%f0%9f%94%8d/
published_at: "2026-03-07T19:06:06.000Z"
author: Gerardo Renteria
full_text: false
words: 1410
quotes:
  - text: The description is critical because it's what Copilot reads at Level 1 to decide if the skill is relevant.
    why_it_matters: Explains why proper skill documentation is essential for activation and why poorly described use cases will prevent skill loading
  - text: You can have many skills installed without penalizing the context, so Copilot only loads what is relevant for each requirement.
    why_it_matters: Highlights the efficiency advantage of the three-level loading model for managing multiple skills in development environments
code_objects_mentioned: []
systems:
  - development
  - integration
  - copilot
versions_mentioned: []
preview:
  embeddable: true
  frame_url: https://gerardorenteria.blog/2026/03/07/%f0%9f%a7%a0-agent-skills-mcps-check-your-bc-extension-health-in-vs-code-%f0%9f%94%8d/embed/
  image: https://i0.wp.com/gerardorenteria.blog/wp-content/uploads/2026/03/chatgpt-image-7-mar-2026-17_23_16.png?fit=1200%2C800&ssl=1
  image_alt: null
  image_w: 1200
  image_h: 800
  site_name: Gerardo Rentería Blog
  favicon: https://gerardorenteria.blog/wp-content/uploads/2020/11/cropped-wolficon.jpg?w=32
  probed_at: "2026-10-07T11:51:04.046Z"
---

# 🧠 Agent Skills + MCPs: check your BC extension health in VS Code 🔍

[Read the post](https://gerardorenteria.blog/2026/03/07/%f0%9f%a7%a0-agent-skills-mcps-check-your-bc-extension-health-in-vs-code-%f0%9f%94%8d/) · Gerardo Renteria (Gerardo Renteria) · 2026-03-07 · 1410 words · tier community · reviewed (checked by Opus)

> Agent Skills are reusable instruction packages in VS Code that orchestrate external tools like YAMPI and BC Telemetry Buddy to analyze Business Central extension health across environments. A three-level loading model activates only relevant skills without penalizing context, enabling developers to check extension status, versions, deployments, and lifecycle events in production through a single chat message.

## Key points

- An Agent Skill is a folder under .github/skills/ with a required SKILL.md and optional reference files, loaded by Copilot through a three-level model only when relevant.
- The description in the SKILL.md frontmatter is what Copilot reads first to decide relevance; vague use cases mean the skill will not activate.
- The bc-extension-health skill reads app.json, calls YAMPI for active environments, installed versions and available updates, and uses BC Telemetry Buddy to run a KQL query over six lifecycle events (LC0010, LC0011, LC0016, LC0017, LC0022, LC0023).
- Results from parallel tool calls are consolidated into two Markdown tables showing extension status per environment in the tenant.
- The skill runs no code of its own; it only tells Copilot what tools to use, in what order, and how to present results.

## Quotes

- "The description is critical because it's what Copilot reads at Level 1 to decide if the skill is relevant." (Explains why proper skill documentation is essential for activation and why poorly described use cases will prevent skill loading)
- "You can have many skills installed without penalizing the context, so Copilot only loads what is relevant for each requirement." (Highlights the efficiency advantage of the three-level loading model for managing multiple skills in development environments)

## Context

- Features: Agent Skills, Extension lifecycle event analysis, Telemetry query integration, Multi-environment extension status, YAMPI integration, BC Telemetry Buddy integration

Source: Gerardo Renteria, community blog. Summary, key points and quotes are derived (CONTENT-NOTICE.md); read the original for the full text.