- 01
/plugin marketplace add microsoft/power-platform-skills - 02
/plugin install process-intelligence@power-platform-skills
Finds the slow parts of a process in Power Automate Process Mining: activities with the longest average duration, activities that take the most time in total, slow hand-offs between steps, and the cases that waited longest. It keeps averages and totals apart, because the slowest step isn't always the biggest cost.
WHEN TO USE
USE FOR
- Find the slowest activities in a process.
- See which activities take the most time in total.
- Spot slow hand-offs between steps.
- List the cases that waited longest.
NOT FOR
- Promising time savings: a long duration is a lead to investigate, not proof that fixing it saves that time.
This is a saved copy of the skill's SKILL.md instructions. It may differ from the upstream file or the version you install.
Performance: averages are not total impact
Use the shared contract and units/filter semantics. 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:
- Slow activities by mean:
get_bottleneck_analysis_v2 {S,itemsPerPage:5,itemsToSkip:0,mcpFilterOptions:F}. Omit absent F.Durationis average activity duration, already ranked descending. Do not passattributeName,metrics,aggregationorlimit. - 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_v2suffix. 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. - Only for unresolved evidence, choose a targeted drilldown:
get_edges_with_metrics_v2 {S,filterOptions:F,itemsPerPage:20,itemsToSkip:0}for handoffs, orget_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 to label observations and tested findings, retain counterevidence and identify a discriminating next check.
Account or credentials required
3 FOR YOUItems without a tag are required.
- 01Install with the process-intelligence plugin, then run setup
Install it with Microsoft's process-intelligence plugin. It works through the plugin's Process Mining MCP server and shared analysis guides, which come only with the plugin.
- 02Node.js 22 or 24, Azure CLI 2.54+, Process Mining access
Node.js 22 or 24, the Azure CLI 2.54 or later, and an authorised Power Automate Process Mining account and environment. GCC, GCC High, DoD and Mooncake clouds aren't supported yet.
- 03Note Results reach your AI assistant unredacted
Analysis results, which can include personal and business data, are passed unredacted to the AI assistant you use. Check your organisation's rules for that assistant before you connect.
This skill ships inside the Power Platform Skills plugin. Listed package contents include 25 agents, hooks and an MCP server. Installed components and skill versions may vary by AI tool.
Install as a Claude Code plugin
Typed inside the agent's own prompt, not in a terminal. This skill uses files kept elsewhere in its plugin, so install the whole plugin — on its own the skill would be missing them.
The repository is licensed under MIT — use, modification, and redistribution are allowed under that license’s terms.
View the repository’s license file on GitHub →