Replace microsoft-foundry skill agent root / azd discovery (Step 1) with a script

## Summary

Copilot has identified a portion of a skill that is a good candidate for replacement with a script.

The candidate is the **agent root / azd discovery (Step 1)** in the `microsoft-foundry` skill (`SKILL.md`, Common Project Context Resolution).

## Candidate description

**Agent root / azd discovery (Step 1)**

This step parses `azure.yaml` for services with `host: azure.ai.agent`; if there are none, it globs the workspace for `.foundry/` folders containing `agent-metadata.yaml` / `agent-metadata..yaml`. This is deterministic file discovery with small output (a list of candidate agent roots). The branching (one / multiple / none) does not block scripting — the script can emit the candidate list and let the agent make the selection. It pairs naturally with the azd context resolution step into a single "resolve context" helper.

## Affected file and lines

- [`SKILL.md` — Step 1: Discover Agent Roots and azd Context (L107–L118)](https://github.com/microsoft/GitHub-Copilot-for-Azure/blob/164e0cda7b9d75d6e0d64b235d17bd7ff5e2909e/plugin/skills/microsoft-foundry/SKILL.md#L107-L118)

## Next steps

1. **Evaluate the candidate** — confirm the steps are stable and parameterizable, and that the script captures everything the skill needs.
2. **Create both a bash _and_ a PowerShell version** of the script so the skill works across platforms.
3. **Run integration tests** to verify the scripts behave correctly and the skill still completes end-to-end.

## Background Information

### Why replace regular steps with scripts

Replacing a regular, well-defined series of steps with a script can:

- **Reduce token usage** — the skill no longer needs to spell out each command and parse large command output inline; the agent invokes one script and reads a compact result.
- **Improve reliability** — the logic is written and tested once, instead of being re-derived by the agent on every run.
- **Improve determinism** — the same inputs always produce the same steps and output, removing run-to-run variation.
- **Improve speed of execution** — a single script call replaces multiple round-trips of command generation, execution, and large-output parsing.

### Authoring notes for the scripts

- **Reference scripts with markdown links**, not just a bare path to the script file.
- **Include examples** in the skill showing how to run each script (sample invocation with arguments).
- **Briefly explain what each script does** where it is referenced.
- **The script output should explain what it did**, so the agent and user can understand the result without re-inspecting raw command output.

Start with plugin/skills/microsoft-foundry/SKILL.md lines 107–118 and inspect the existing agent-root and azd discovery behavior. Define matching bash and PowerShell scripts, reference them with examples in SKILL.md, and run integration tests. Done means both scripts capture the required candidates and the skill completes end-to-end.

Written by the indexing model from the issue text.