compare-cohorts — Claude Code skill: process cohort comparison
compare-cohorts — a skill for comparing process cohorts, departments, periods or before-and-after results under matched metric definitions.
MIT ★ 1,167 updated 2026-10-29
/plugin marketplace add microsoft/power-platform-skills
/plugin install process-intelligence@power-platform-skillsWhat compare-cohorts does
The skill fixes outcome definition, metric, aggregation and units, then copies the baseline filter set twice and changes only one cohort condition. For attributes it appends value A to one filter and B to the other, then calls get_process_overall_metrics_v2 with each set. If grouping is needed, it requests get_attribute_statistics with the same filters.
For periods it changes one timeframeFilters pair; case windows are interpreted as Contained. If the process version changed between requests, the skill marks the result as **inconclusive** and stops or reruns both calls. The skill relies on the Process Intelligence API and has no external dependencies beyond that.
It reports case counts, mean metrics, absolute delta and relative change for a nonzero baseline. An empty cohort means insufficient evidence, not zero duration.
What it helps with
- compare departments by mean case duration
- check the effect of process changes across two periods
- spot metric differences between attribute cohorts
Example prompts for the agent
- Compare case duration for department A and department B in the last quarter
- Show the difference in waiting time before and after the rollout
- Match the top five Region groups by TotalDuration for two cohorts
How to install compare-cohorts
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 compare-cohorts -a claude-code3Manually: put the files in place
~/.claude/skills/compare-cohorts/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/compare-cohorts/
1Skills CLI (Vercel)
npx skills add microsoft/power-platform-skills --skill compare-cohorts -a codex2Manually: put the files in place
.agents/skills/compare-cohorts/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add microsoft/power-platform-skills --skill compare-cohorts -a cursor2Manually: put the files in place
.cursor/skills/compare-cohorts/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install microsoft/power-platform-skills plugins/process-intelligence/skills/compare-cohorts2Manually: put the files in place
.github/skills/compare-cohorts/SKILL.md1Skills CLI (Vercel)
npx skills add microsoft/power-platform-skills --skill compare-cohorts -a gemini-cli2Platform CLI
gemini skills install https://github.com/microsoft/power-platform-skills --path plugins/process-intelligence/skills/compare-cohortsManually: put the files in place
.devin/skills/compare-cohorts/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 compare-cohorts
How to install compare-cohorts in Claude Code?
Run /plugin marketplace add microsoft/power-platform-skills, then /plugin install process-intelligence@power-platform-skills, then npx skills add microsoft/power-platform-skills --skill compare-cohorts -a claude-code. The skill file appears at ~/.claude/skills/compare-cohorts/SKILL.md.
What does compare-cohorts do?
The skill compares process cohorts, periods or departments under fixed metric definitions by copying the baseline filter set and changing one cohort condition per request.
What does inconclusive mean in compare-cohorts?
If the process version changed between the two cohort requests, the skill marks the comparison as inconclusive because the data is no longer aligned.
Source text
SKILL.md · MIT
---
name: compare-cohorts
description: Use when comparing process cohorts, departments, periods or before-and-after results under matched definitions.
allowed-tools: Read, AskUserQuestion
---
# Matched cohort comparisons
Use the [shared contract](../../references/analysis-contract.md) and
[filters/units](../../references/filters-and-units.md).
Fix the outcome definition/provenance, metric, aggregation, units, timezone and one selector S.
Freeze the user's agreed baseline F, separately from current exploratory filters.
Reuse metadata versions and exact typed cohort values. Use the
[investigation method](../../references/investigation-method.md) for findings/status.
## Ordered trace
1. Copy baseline F twice. For attribute cohorts append
`{attributeName:A,dataType:T,attributeValues:[X],isInclusive:true}` to
`attributeValueFilters` for A's cohort value, and the same shape with Y for B.
Preserve other agreed baseline conditions; retain rework restrictions only if part of that
baseline. Do not leak an exploratory/outcome-only subset into a full-population comparison.
Change only the intended cohort condition. If values are unknown, request
`get_attribute_values_v2 {S,attributeName:A,itemsPerPage:20,itemsToSkip:0,filterOptions:F}`;
it returns values, not frequencies.
2. `get_process_overall_metrics_v2 {S,filterOptions:F_A}` ->
`get_process_overall_metrics_v2 {S,filterOptions:F_B}`.
No `metrics`, `groupBy` or aggregation parameter exists. Use the same returned metric definitions;
native `CaseDuration`/`CaseWaitingTime` are means.
3. Only if a grouped explanation is needed and statistics is advertised, make a **matched pair**:
`get_attribute_statistics {S,attributeName:A,filterOptions:F_A,itemsPerPage:5,itemsToSkip:0,metricToSortBy:"TotalDuration",sortOrder:"Descending"}`,
then exactly the same call with F_B. Do not treat independent top-five pages as a complete aligned population.
Continue relevant value/group pages or matched follow-ups when needed, without fixed call quotas.
Stop at sufficient evidence, no new information or a capability/error boundary; no blind sweeps.
Do not create views or use two inclusive timeframes in one query as an A/B comparison.
## Time and reproducibility
For periods, change only one explicit `timeframeFilters` start/end pair in each copied F.
Case windows mean **Contained**, not cases Started/Completed/Intersecting or all events during the period.
If completed-only membership including earlier starts is essential, stop/reframe or route
to derive-metric/a user-confirmed existing matching view. Never invent a date-mode field
or promise unknown end-boundary behavior.
If refresh is reported or reproducibility is at risk, recheck details.
Changed PV/PMV invalidates the pair: mark **inconclusive**, stop or deliberately rerun both,
not just the second.
Process selection resolves latest; no direct version selector or atomic comparison snapshot exists.
Views pin version context but their configuration is mutable/cached.
Report A/B counts, mean metrics, absolute delta and relative change only for a nonzero baseline.
Empty cohorts mean insufficient evidence, not zero duration/infinite improvement.
State scope/version and unmatched-group coverage; at most five headline rows.
Recorded means do not establish closure, equal maturity or complete lifecycles. Report those
as unknown unless supported; qualify the comparison, not an assumed causal improvement.
Retain baseline/cohort filters, evidence references, status and alternatives. Overlapping groups
cannot be added as unique-case totals.
Object-centric comparisons belong in analyze-objects, not case-filter fallbacks.
© Microsoft · MIT · microsoft/power-platform-skills