Build with microsoft ai

Skill hiteshbandhu/skills-i-use/skills/ai-engineer-talks/build-with-microsoft-ai

Runs workflows for Microsoft agent stacks — agent observability gaps, eval-driven alignment, and local vs background vs cloud agents in VS Code/Copilot. Use when the user builds on Azure Foundry, GitHub Copilot agents, agent evals, or says "mind the gap observability", "Copilot worktrees", "background agent".From its SKILL.md

Install

npx -y skills add hiteshbandhu/skills-i-use --skill build-with-microsoft-ai

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

0.7 KB, 90 tokens by cl100k_base, as published. Nobody here has run it

Build with Microsoft AI

Two Microsoft AI Engineer talks. workflows.md.

├─ Close observability/eval gap                 → A
├─ Safety + monitoring guardrails               → B
├─ Pick local / background / cloud agent        → C
└─ Parallel agents with worktrees               → D

Source: playlists/microsoft-ai-engineer/.

What ships with it: 3 files

2.6 KB alongside SKILL.md

Gives 0 of the 12 instructions most evals benchmarks skills give in 90 tokens

Counted across 499 of the 513 authors here whose files we hold, read 2026-09-06

Spawn with-skill and baseline runs in the same turnin 31 of 499, across 24 files
Keep SKILL.md under 500 linesin 31 of 499, across 24 files
Draft assertions while test runs are in progressin 31 of 499, across 24 files
Compare against the baseline after changesin 31 of 499, across 13 files
Define evals before codingin 26 of 499, across 17 files
Run evals frequently during developmentin 25 of 499, across 16 files
Keep evals fastin 24 of 499, across 15 files
Version evals with codein 24 of 499, across 15 files
Generate the eval viewer before evaluating outputs yourselfin 24 of 499, across 17 files
Generate an eval report after runsin 24 of 499, across 15 files
Track pass@k metrics over timein 22 of 499, across 14 files
Save a baseline before making changesin 21 of 499, across 9 files

Said here and by no other author read

use workflow A for observability and eval gaps
use workflow B for safety and monitoring guardrails
use workflow C to pick local, background, or cloud agent
use workflow D for parallel agents with worktrees

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.