Skip to main content
skill CX Codex

analyze-performance · microsoft, process-intelligence — Claude Code skill: what it does, how to install

analyze-performance guides analysis of slow process activities, handoff delays, waiting times, and total workload without distorting statistical metrics.

MIT ★ 1,167 updated 2026-10-29

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add microsoft/power-platform-skills
/plugin install process-intelligence@power-platform-skills
Open on GitHub

What analyze-performance does

This skill defines an ordered recipe to inspect process performance. Instead of ad-hoc queries, the assistant queries mean activity durations using get_bottleneck_analysis_v2 and cumulative workload with get_attribute_statistics. For unresolved issues, it drills into handoffs via get_edges_with_metrics_v2 and slow cases via get_cases_with_metrics_v2.

The instructions enforce strict metric boundaries: multiplying mean activity duration by case count does not yield total workload. Edge sorting is strictly page-local unless all pages are fetched, so incomplete coverage must never produce a faux global ranking.

What it helps with

  • identify the slowest process activities by mean duration
  • calculate cumulative workload using TotalDuration metrics
  • detect handoff delays between sequential activities
  • extract process cases ranked by descending waiting time

Example prompts for the agent

  • Find the top five bottleneck activities by average duration
  • Check handoff delays between steps using edge metrics
  • Analyze total activity workload without assuming cases equal events

How to install analyze-performance

1Plugin marketplace

/plugin marketplace add microsoft/power-platform-skills
/plugin install process-intelligence@power-platform-skills

This installs the whole process-intelligence plugin with all its skills

2Skills CLI (Vercel)

npx skills add microsoft/power-platform-skills --skill analyze-performance -a claude-code

3Manually: put the files in place

~/.claude/skills/analyze-performance/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/analyze-performance/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about analyze-performance

How to install analyze-performance in Claude Code?

Register the catalog via /plugin marketplace add microsoft/power-platform-skills and install the package with /plugin install process-intelligence@power-platform-skills.

What does analyze-performance do?

It guides the assistant through querying bottleneck tools, calculating cumulative durations accurately, and tracing handoff delays in process intelligence datasets.

How does the skill handle edge metric rankings?

Because edge endpoints do not accept sort inputs, single-page ordering is page-local; the agent must fetch all pages before presenting a global edge order.

Source text

SKILL.md · MIT
---
name: analyze-performance
description: Use when investigating slow activities, waiting, handoff duration, bottlenecks or cumulative activity workload.
allowed-tools: Read, AskUserQuestion
---

# Performance: averages are not total impact

Use the [shared contract](../../references/analysis-contract.md) and
[units/filter semantics](../../references/filters-and-units.md).
Reuse S, baseline F and metadata; do not request a baseline overview for an exact top-bottleneck question.

## Ordered recipe

Choose the smallest entry branch:

1. **Slow activities by mean:**
   `get_bottleneck_analysis_v2 {S,itemsPerPage:5,itemsToSkip:0,mcpFilterOptions:F}`.
   Omit absent F. `Duration` is **average activity duration**, already ranked descending.
   Do not pass `attributeName`, `metrics`, `aggregation` or `limit`.
2. **Cumulative activity duration:** skip step 1 if this alone was requested.
   From metadata take the exact Activity import attribute A; never assume its name is "Activity".
   If advertised, call
   `get_attribute_statistics {S,attributeName:A,filterOptions:F,itemsPerPage:5,itemsToSkip:0,metricToSortBy:"TotalDuration",sortOrder:"Descending"}`.
   There is **no `_v2` suffix**. For an event-level Activity, TotalDuration sums matching
   events; AvgDuration is their mean. Keep EventFrequency and CaseFrequency distinct.
   RelativeCaseFrequency is a ratio; overlapping activity groups' case counts are not additive.
3. Only for unresolved evidence, choose a targeted drilldown:
   `get_edges_with_metrics_v2 {S,filterOptions:F,itemsPerPage:20,itemsToSkip:0}` for handoffs,
   or `get_cases_with_metrics_v2 {S,filterOptions:F,itemsPerPage:5,itemsToSkip:0,metricToSortBy:"WaitingTime",sortOrder:"Descending"}`.
   Reuse earlier compatible results. Continue relevant drilldowns/pages without fixed call or
   total-row ceilings; each query must resolve missing evidence, not repeat an answered question.

## Boundaries and stopping

Missing statistics: report the cumulative-measure gap, optionally average-only bottleneck evidence.
Never derive population totals from top-five averages or call a hidden statistics tool.
Edges expose no sort input: local ranking of one incomplete page is **page-local**, not global.
Report the native edge Duration mean; do not relabel it as an independently established waiting metric.
For a requested global edge ranking, retrieve necessary pages to complete coverage before ranking;
if coverage is incomplete, explicitly leave the global result unresolved.
Event/attribute filters retain whole cases, not just matching events.
Check timestamp imports before interpreting utilization: zero-duration conventions with
start-only data can produce nonzero ratios without measured active work. Keep raw values
and use same-scope cohort evidence; see the unit reference.

Stop once answered or evidence/capability is exhausted. Show at most five headline rows with separate
mean, total and frequency columns only when returned, scope/units and coverage.
High duration is an investigation lead, not proof of cause or a guaranteed time saving.
Mean activity duration times process case count is not total workload: cases are not activity
occurrences. Even known workload is not an intervention's removable delay.
Use the [investigation method](../../references/investigation-method.md) to label observations
and tested findings, retain counterevidence and identify a discriminating next check.

© Microsoft · MIT · microsoft/power-platform-skills

Similar skills

All skills for Data and databases →

analyze-performance by other authors comes first.

analyze-performance Microsoft analyze-performance is a Claude Code skill that scans local Power Pages code for performance anti-patterns and suggests AI-assisted fixes for offline review. CX Codex +1 ★ 1,167repo stars performance-optimization addyosmani performance-optimization — an agent skill that measures before it changes code: Core Web Vitals budgets, N+1 queries, missing indexes and slow endpoints. CX Codex +1 82,600installs power-bi-performance-troubleshooting official github The power-bi-performance-troubleshooting skill guides troubleshooting across Power BI models, reports, and queries. Use it to trace slowdowns and decide what to inspect next. CX Codex +1 8,900installs performance-analysis ruvnet performance-analysis detects bottlenecks in Claude Flow swarms, profiles agent operations, and generates reports with actionable optimization recommendations. CX Codex +1 1,200installs weekly-performance-digest tradermonty weekly-performance-digest is a Claude Code skill that calculates weekly results from closed trading theses. It groups wins and losses by several recorded attributes. CX Codex +1 3,000installs performance cognitedata performance is a Claude Code skill that finds and fixes performance issues in Flows apps. It activates for requests about slow pages, re-renders, CDF queries, bundles, or memory leaks. CX Codex +1 1,900installs qdrant-performance-optimization qdrant qdrant-performance-optimization — a routing skill for Qdrant tuning: it matches your symptom to the right sub-skill for search speed, indexing or memory. CX Codex +1 1,700installs

From the same set157

The whole set →
add-datasource add-datasource — a router skill that asks what your Power Apps code app should do, then hands the job to the right connector skill. Useful when you need data but aren't sure which connector fits. CX Codex +1 ★ 1,167repo stars manage-desktop-flows manage-desktop-flows manages Power Automate Desktop RPA flows and machine groups in Claude Code. Triggers attended or unattended tasks directly from chat. CX Codex +1 ★ 1,167repo stars investigate-process investigate-process investigates broad Process Mining questions through hypotheses, comparisons, and specialist analysis. Use it when one metric cannot explain the finding. CX Codex +1 ★ 1,167repo stars analyze-variants analyze-variants — a skill for investigating business process execution variants: common and slow paths, rework cases, specific instances. CX Codex +1 ★ 1,167repo stars analyze-drivers analyze-drivers — a skill to identify what drives differences in process duration, wait times, resource utilization, and rework. Frames testable hypotheses and distinguishes competing explanations through attribute correlation. CX Codex +1 ★ 1,167repo stars compare-cohorts compare-cohorts — a skill for comparing process cohorts, departments, periods or before-and-after results under matched metric definitions. CX Codex +1 ★ 1,167repo stars add-azuredevops add-azuredevops attaches the Azure DevOps connector to a Power Apps code app to query work items, create bugs, and trigger build pipelines. CX Codex +1 ★ 1,167repo stars analyze-objects analyze-objects is a Claude Code skill for studying processes with interacting object types and delays across objects. It activates for questions about leading-object executions or process paths. CX Codex +1 ★ 1,167repo stars

Project sponsors

Companies that keep this analytics open