eval-guide is an AI agent evaluation toolkit for Copilot Studio that helps users plan evaluations, create test cases, interpret results, and diagnose failures. It is used with Claude Code or GitHub Copilot to assess single-response and multi-turn agent behavior using Microsoft’s evaluation guidance.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/microsoft/eval-guide/eval-triage-and-improvementnpx skills add microsoft/eval-guide --skill eval-triage-and-improvementgit clone --depth 1 https://github.com/microsoft/eval-guideWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/microsoft/eval-guide/eval-triage-and-improvement)<a href="https://agentmods.dev/skills/microsoft/eval-guide/eval-triage-and-improvement"><img src="https://agentmods.dev/badge/skills/microsoft/eval-guide/eval-triage-and-improvement.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00121 | $0.05058 |
| Opus 5 | $0.00060 | $0.02529 |
| Sonnet 5 | $0.00024 | $0.01012 |
| Haiku 4.5 | $0.00012 | $0.00506 |
Grade A, and why
eval-triage-and-improvement scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eval Triage & Improvement
You help users interpret their agent evaluation results and find actionable next steps to improve. Follow the hybrid workflow: gather eval results first, then generate a structured triage report with Step 7 root buckets, owners, and recommended fixes.
This skill is grounded in skills/eval-guide/playbook.md, the canonical Practical Guidance on Agent Evaluation: 10-step playbook. It is the deep-dive for Step 7 — Iterate to Diagnose Failures and seeds Step 9 — Optimization Loop for production feedback. MS Learn pages and the Eval Guidance Kit remain supporting sources for Copilot Studio mechanics, lifecycle cadence, and checklist artifacts.
When to use this skill vs. eval-result-interpreter
These two skills share the same triage framework but serve different modes of work:
| Use eval-triage-and-improvement when… | Use eval-result-interpreter when… |
|---|---|
| You want interactive guidance walking through diagnosis step by step | You have a CSV file or concrete results and want a one-shot structured report |
| You are in an ongoing improvement loop — fixing, re-running, and re-triaging | This is your first look at results — you need a verdict and top actions fast |
| You need detailed remediation help for specific eval-set failure patterns (e.g., "wrong tool fires — now what?") | You want a customer-deliverable artifact (the .docx triage report) |
| You have many failures (15+) and need help prioritizing which to investigate | The eval run is relatively straightforward (<20 failures) |
| You need the playbook worked examples and deeper diagnostic walkthroughs | You need the activity map / result comparison tool recommendations inline |
If in doubt: Start with eval-result-interpreter to get the structured report, then switch to eval-triage-and-improvement if you need interactive help implementing the fixes.
Workflow
Step 1: Gather Eval Results
Ask the user to share:
- Which eval sets ran and their pass rates (e.g., "Faithfulness: 71%, Prompt injection: 95%")
- Methodology manifest metadata from the companion
.docxreport orstage-N-data.json:set_type,category/capability dimension,method,gate(hard/soft),target,regression_class, human-review flag, and source/ground-truth provenance - Specific failing test cases — the test case ID, sample input, expected value, actual agent response, and eval method assigned in Copilot Studio
- How many times they've run — is this the first baseline run (Step 6) or a re-run after fixes?
- What they've already tried — any eval, agent, knowledge, or tool changes attempted so far?
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 336 lines · 121 tokens per session scan A 8996fd0fda28
eval-triage-and-improvement is a skill published in the GitHub repository microsoft/eval-guide (128 stars, last pushed 2mo ago), licensed MIT. It adds 121 tokens to every session and 5,058 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…