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
/plugin marketplace add microsoft/power-platform-skills
/plugin install process-intelligence@power-platform-skillsWhat 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-skillsThis 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-code3Manually: put the files in place
~/.claude/skills/analyze-performance/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/analyze-performance/
1Skills CLI (Vercel)
npx skills add microsoft/power-platform-skills --skill analyze-performance -a codex2Manually: put the files in place
.agents/skills/analyze-performance/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add microsoft/power-platform-skills --skill analyze-performance -a cursor2Manually: put the files in place
.cursor/skills/analyze-performance/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install microsoft/power-platform-skills plugins/process-intelligence/skills/analyze-performance2Manually: put the files in place
.github/skills/analyze-performance/SKILL.md1Skills CLI (Vercel)
npx skills add microsoft/power-platform-skills --skill analyze-performance -a gemini-cli2Platform CLI
gemini skills install https://github.com/microsoft/power-platform-skills --path plugins/process-intelligence/skills/analyze-performanceManually: put the files in place
.devin/skills/analyze-performance/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
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.