Agent Performance Triage

Diagnose a live Microsoft Copilot Studio agent from its analytics and transcripts, find why it is underperforming, and produce a prioritized improvement backlog tied to specific topics, knowledge sources and tools. Use when an agent is already in production and someone asks why resolution or engagement is low, why users escalate or abandon, what the top unanswered questions are, how to improve an agent's containment or CSAT, or wants a post-launch review, health check or optimization sprint for a deployed agent.

110 stars 122 forksAI, LLMs & AgentsOfficial

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add microsoft/cat-agent-skills --skill agent-performance-triage
Manual install
git clone --depth 1 https://github.com/microsoft/cat-agent-skills.git /tmp/cat-agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/cat-agent-skills/submissions/agent-performance-triage ~/.claude/skills/agent-performance-triage

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Agent Performance Triage

An agent that passed its test plan can still fail in production, and the failure modes
look nothing like test failures. Analytics tell you *that* something is wrong; this skill
works out *what* and *where*, and hands back a backlog an owner can actually execute.

Run it two weeks after launch, then monthly.

## Scope

**In scope:** metric interpretation, root-cause diagnosis, unanswered-question mining,
topic and knowledge gap analysis, prioritized backlog, trend tracking across runs,
stakeholder readout.

**Out of scope:** editing the agent, publishing changes, reading production transcripts
that have not been de-identified or that the user is not authorized to share, cost
analysis (a separate concern), pre-launch test design.

## Step 1 — Collect the evidence

Ask for whatever is available. The skill degrades gracefully — say which conclusions are
weakened by missing inputs rather than guessing.

**Minimum viable input:** the Copilot Studio analytics summary for a stated period
(engagement rate, resolution rate, escalation rate, abandon rate, total sessions, CSAT if
collected) plus the top unresolved or unanswered queries list.

**Better input, in order of value:**

1. Session transcripts export for the period — the single highest-value input
2. Per-topic breakdown: sessions, resolution, escalation, abandonment by topic
3. The agent's topic list with trigger phrases, and the knowledge source inventory
4. Tool and action failure telemetry
Read the full skill on GitHub

Details

Skill name
agent-performance-triage
Path
submissions/agent-performance-triage/SKILL.md
License
MIT
Repo updated
15 November 2026

FAQ

What does the Agent Performance Triage skill do?

Diagnose a live Microsoft Copilot Studio agent from its analytics and transcripts, find why it is underperforming, and produce a prioritized improvement backlog tied to specific topics, knowledge sources and tools. Use when an agent is already in production and someone asks why resolution or engagement is low, why users escalate or abandon, what the top unanswered questions are, how to improve an agent's containment or CSAT, or wants a post-launch review, health check or optimization sprint for a deployed agent.

How do I install the Agent Performance Triage skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add microsoft/cat-agent-skills --skill agent-performance-triage. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Agent Performance Triage popular?

It lives in microsoft/cat-agent-skills, which has 110 GitHub stars and 122 forks.

Related skills

3 Statements

110

microsoft/cat-agent-skills

Completes existing income statement, balance sheet and cash flow templates while preserving layout, grounding historical inputs and linking forecast formulas with reconciliation checks. Use for "fill in a 3-statement template", "complete an IS/BS/CF framework", "populate my integrated financial model", "link statements in this template", or "finish the forecasts in my three-statement workbook". Do NOT use for blank-slate models or general workbook edits (use xlsx), DCF valuation (use dcf-valuation), or buyout modeling (use lbo-model).

AI, LLMs & Agents122

Accessibility Pass

110

microsoft/cat-agent-skills

Use this skill whenever the user asks to check, review, or fix the accessibility of a PowerPoint deck, Word document, HTML page, or Markdown file, and before handing over any deck or document this agent just generated, so it does not ship with missing alt text, untitled slides, or unreadable colour contrast.

Frontend & Design122

Accessible Learning Materials

110

microsoft/cat-agent-skills

Maintains instructionally equivalent, accessible variants of a set of learning materials — lessons, readings, slides, and handouts — with parity checks against the original learning goals and recorded approvals. Use when the user asks to "make these materials accessible", "audit this lesson set for accessibility", "create an accessible version of this reading", "check reading level and alt text", or "keep my accessible variants in sync". Do NOT use for individual student accommodation or support-plan decisions (IEP, EHCP, or local equivalent), and do NOT use for generic document formatting (us

Learning & Education122

Agent Rai Impact Assessment

110

microsoft/cat-agent-skills

Use this skill whenever the user asks for a Responsible AI (RAI) impact assessment, RAI review, harms or impact analysis, or pilot/release-readiness review of an AI agent, or to reassess an agent after material changes to its tools, data, memory, or users. Works from the agent's use case, design, tools, data flows, and evaluation evidence to identify affected people, benefits, harm scenarios, authority boundaries, mitigations, residual uncertainty, and the human decisions still required. Not a generic security audit, automatic compliance certification, or authority to approve deployment.

AI, LLMs & Agents122

Agent Harness Explorer

110

microsoft/cat-agent-skills

Use this skill whenever the user wants to inspect, understand, snapshot, compare, or document the capabilities of the current agent harness — for example "what can this harness do?", "which Python libraries are installed?", "what should I use to create Word documents?", "capture/remember a snapshot", "compare with my baseline", or "what changed since last week?". Prefer this skill BEFORE guessing what the runtime supports.

AI, LLMs & Agents122

AI Demo Assistant

110

microsoft/cat-agent-skills

Builds a scenario-driven content pack for a Microsoft 365 Copilot customer demo. From a customer name, line of business, and target personas, it proposes demo scenarios for operator approval, then generates fictional Word/PowerPoint/Excel example files plus an AI Demo Delivery Plan (persona roster with tenant-account mapping, email and Teams chat scripts, calendar meetings with agendas, a meeting transcript, and app-tagged Copilot prompt workflows grounded in the generated content). After approval it can OPTIONALLY seed the Office files into a customer-named OneDrive folder and optionally post

AI, LLMs & Agents122

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.