Skip to content
Agentmart
Submit a tool

foundry-observability

Trace, monitor, evaluate, and continuously improve Microsoft AI Foundry agents.

Skill by Microsoft (curated)

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/jspoelstra-foundry-observability

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Trace, monitor, evaluate, and continuously improve Microsoft AI Foundry agents. Includes batch evaluation, prompt optimization, trace analysis, regression detection, and production monitoring setup.

Use cases: agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/foundry-observability

What's inside

Skill name
foundry-observability
Description
Trace, monitor, evaluate, and continuously improve Microsoft AI Foundry agents. Includes batch evaluation, prompt optimization, trace analysis, regression detection, and production monitoring setup.
License
MIT
Metadata
author: Microsoft (curated) · source: https://github.com/microsoft/skills
Instructions
15 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Foundry Observability & Evaluation

Focuses on the full evaluation and monitoring lifecycle for Foundry agents.

Key areas:
- Batch and continuous evaluation
- Prompt and agent instruction optimization
- Trace analysis and correlation with evals
- Dataset curation from production traces
- CI/CD monitoring and regression detection

**Recommended:** Load `microsoft-foundry` first for the best workflow guidance (especially the `observe` sub-skill).

This skill is particularly powerful when combined with hosted agents for production-grade agent development.

From jspoelstra/foundry-hosted-agents, MIT.

More from jspoelstra/foundry-hosted-agents

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jul 15, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/jspoelstra/foundry-hosted-agents
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from Microsoft (curated)

Cite this page

foundry-observability skill. Agent Mart. https://agentmart.dev/skills/jspoelstra-foundry-observability (last updated 2026-10-24)