cja-segment-performance-comparator

Name: cja-segment-performance-comparator
Author: adobe

136installs65forks

How to install cja-segment-performance-comparator?

adobe/skills/cja-segment-performance-comparator

$npx -y skills add adobe/skills --skill cja-segment-performance-comparator

Installs into the current project.

Summary

Compares the performance of two or more audience segments across key metrics side by side. Use this skill when someone wants to compare audiences, cohorts, or groups — for example, "how do mobile users compare to desktop users on conversion," "compare new vs. returning visitors,"

Files · 1

View on GitHub

SKILL.md

1	# Segment Performance Comparator (Customer Journey Analytics)
2
3	Compare 2–5 audience segments across a set of key metrics in a side-by-side
4	matrix. The output tells the user not just what each segment looks like in
5	isolation, but which segment wins or loses on each metric — and which
6	differences are large enough to act on.
7
8	This skill answers the question "which audience should we focus on?" with data.
9	Segment comparisons drive product decisions, personalization strategy, and
10	budget allocation — so clarity and actionability matter more than exhaustive data.
11
12	---
13
14	## CJA MCP Tools Used
15
16	- `findSegments` — search for segments by name or keyword
17	- `describeSegment` — understand the logic of candidate segments before using them
18	- `findMetrics` — resolve base metric IDs
19	- `findCalculatedMetrics` — include custom KPIs in the comparison
20	- `listComponentUsage` — identify the most-used metrics as default comparison set
21	- `runReport` (with `segmentIds` or `adhocSegments`) — pull metric values per segment
22
23	---
24
25	## Phase 0 — Setup
26
27	1. Call `findDataViews` to list available data views.
28	2. If the user hasn't specified a data view, present the list and ask which to use.
29	3. Call `setDefaultSessionDataViewId` with the chosen ID.
30	4. Ask the user which segments to compare if not already specified. Confirm the metrics to compare them on.
31
32	---
33
34	## Phase 1 — Identify Segments to Compare
35
36	### 1.1 From user description
37
38	If the user named specific segments, resolve them:
39	```
40	findSegments(search: "<segment name>")
41	```
42
43	For each match, call `describeSegment` to verify it is the correct one:
44	```
45	describeSegment(segmentId: "<id>")
46	```
47
48	Show the segment definition summary to the user if there is ambiguity:
49	> "I found two segments matching 'mobile users': Mobile Visitors (All Devices)
50	> and Mobile App Users. Which do you want to compare?"
51
52	### 1.2 From plain-English descriptions
53
54	If the user says "compare mobile vs desktop users" but there are no matching
55	segments, offer to create ad hoc segments inline for the comparison:
56	> "I don't see pre-built segments for mobile and desktop. I can create
57	> temporary ad hoc segments for this comparison using device type. Should I
58	> proceed with ad hoc segments, or would you like to create permanent segments
59	> first?"
60
61	Ad hoc segments are constructed using `adhocSegments` in `runReport` — no
62	save required for the comparison itself.
63
64	### 1.3 Segment count limit
65
66	Maximum 5 segments for a single comparison. More than 5 creates a matrix
67	that is too wide to read meaningfully. If the user requests more, say:
68	> "I'll limit to the 5 most relevant segments for readability. Would you like
69	> me to prioritize by usage count or stick with your list order?"
70
71	---
72
73	## Phase 2 — Identify Metrics to Compare
74
75	### 2.1 From user specification
76
77	Resolve named metrics via `findMetrics` and `findCalculatedMetrics`.
78
79	### 2.2 Default metric discovery
80
81	If the user did not specify metrics, pull the top metrics by usage. The
82	`listComponentUsage` tool does not support a `limit` parameter — it returns all
83	components ranked by usage count; take the top 6–8 from the result:
84	```
85	listComponentUsage(componentType: "metric")
86	listComponentUsage(componentType: "calculatedMetric")
87	```
88
89	Prefer calculated metrics over raw base metrics when they measure the same
90	thing — calculated metrics reflect intentional KPI definitions.
91
92	### 2.3 Metric selection for a comparison
93
94	Good comparison metrics should be meaningful across all segments. For example,
95	"Revenue" is meaningful for both mobile and desktop users; "App Installs" is
96	only meaningful for mobile. Remove metrics that would be trivially zero for
97	one segment.
98
99	If unsure, ask: "Should I use your standard KPI set, or focus on specific
100	metrics like conversion rate, revenue, and engagement?"
101
102	---
103
104	## Phase 3 — Run the Comparison
105
106	For each segment, run a `runReport` with that segment applied and all
107	comparison metrics included. Note that `runReport` takes `metricIds` as a
108	comma-separated string, `startDate`/`endDate` (not `dateRange`), and a
109	`dimensionIds` (required even for summary-only reports — use a low-cardinality
110	dimension like `variables/daterangeday` or `variables/web.webPageDetails.name`).
111	The summary totals for all metrics are in `summaryData.filteredTotals`:
112
113	```
114	runReport(
115	dimensionIds: "variables/web.webPageDetails.name",
116	metricIds: "metrics/visits,met

People who liked this also viewed

6 picks

Type

cja-segment-performance-comparator

136installs65forks

View on GitHub

How to install cja-segment-performance-comparator?

adobe/skills/cja-segment-performance-comparator

$npx -y skills add adobe/skills --skill cja-segment-performance-comparator

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Segment Performance Comparator (Customer Journey Analytics)
2
3	Compare 2–5 audience segments across a set of key metrics in a side-by-side
4	matrix. The output tells the user not just what each segment looks like in
5	isolation, but which segment wins or loses on each metric — and which
6	differences are large enough to act on.
7
8	This skill answers the question "which audience should we focus on?" with data.
9	Segment comparisons drive product decisions, personalization strategy, and
10	budget allocation — so clarity and actionability matter more than exhaustive data.
11
12	---
13
14	## CJA MCP Tools Used
15
16	- `findSegments` — search for segments by name or keyword
17	- `describeSegment` — understand the logic of candidate segments before using them
18	- `findMetrics` — resolve base metric IDs
19	- `findCalculatedMetrics` — include custom KPIs in the comparison
20	- `listComponentUsage` — identify the most-used metrics as default comparison set
21	- `runReport` (with `segmentIds` or `adhocSegments`) — pull metric values per segment
22
23	---
24
25	## Phase 0 — Setup
26
27	1. Call `findDataViews` to list available data views.
28	2. If the user hasn't specified a data view, present the list and ask which to use.
29	3. Call `setDefaultSessionDataViewId` with the chosen ID.
30	4. Ask the user which segments to compare if not already specified. Confirm the metrics to compare them on.
31
32	---
33
34	## Phase 1 — Identify Segments to Compare
35
36	### 1.1 From user description
37
38	If the user named specific segments, resolve them:
39	```
40	findSegments(search: "<segment name>")
41	```
42
43	For each match, call `describeSegment` to verify it is the correct one:
44	```
45	describeSegment(segmentId: "<id>")
46	```
47
48	Show the segment definition summary to the user if there is ambiguity:
49	> "I found two segments matching 'mobile users': Mobile Visitors (All Devices)
50	> and Mobile App Users. Which do you want to compare?"
51
52	### 1.2 From plain-English descriptions
53
54	If the user says "compare mobile vs desktop users" but there are no matching
55	segments, offer to create ad hoc segments inline for the comparison:
56	> "I don't see pre-built segments for mobile and desktop. I can create
57	> temporary ad hoc segments for this comparison using device type. Should I
58	> proceed with ad hoc segments, or would you like to create permanent segments
59	> first?"
60
61	Ad hoc segments are constructed using `adhocSegments` in `runReport` — no
62	save required for the comparison itself.
63
64	### 1.3 Segment count limit
65
66	Maximum 5 segments for a single comparison. More than 5 creates a matrix
67	that is too wide to read meaningfully. If the user requests more, say:
68	> "I'll limit to the 5 most relevant segments for readability. Would you like
69	> me to prioritize by usage count or stick with your list order?"
70
71	---
72
73	## Phase 2 — Identify Metrics to Compare
74
75	### 2.1 From user specification
76
77	Resolve named metrics via `findMetrics` and `findCalculatedMetrics`.
78
79	### 2.2 Default metric discovery
80
81	If the user did not specify metrics, pull the top metrics by usage. The
82	`listComponentUsage` tool does not support a `limit` parameter — it returns all
83	components ranked by usage count; take the top 6–8 from the result:
84	```
85	listComponentUsage(componentType: "metric")
86	listComponentUsage(componentType: "calculatedMetric")
87	```
88
89	Prefer calculated metrics over raw base metrics when they measure the same
90	thing — calculated metrics reflect intentional KPI definitions.
91
92	### 2.3 Metric selection for a comparison
93
94	Good comparison metrics should be meaningful across all segments. For example,
95	"Revenue" is meaningful for both mobile and desktop users; "App Installs" is
96	only meaningful for mobile. Remove metrics that would be trivially zero for
97	one segment.
98
99	If unsure, ask: "Should I use your standard KPI set, or focus on specific
100	metrics like conversion rate, revenue, and engagement?"
101
102	---
103
104	## Phase 3 — Run the Comparison
105
106	For each segment, run a `runReport` with that segment applied and all
107	comparison metrics included. Note that `runReport` takes `metricIds` as a
108	comma-separated string, `startDate`/`endDate` (not `dateRange`), and a
109	`dimensionIds` (required even for summary-only reports — use a low-cardinality
110	dimension like `variables/daterangeday` or `variables/web.webPageDetails.name`).
111	The summary totals for all metrics are in `summaryData.filteredTotals`:
112
113	```
114	runReport(
115	dimensionIds: "variables/web.webPageDetails.name",
116	metricIds: "metrics/visits,met

People who liked this also viewed

6 picks

Type