- Home
- Skills
- Data & Databases
- Salesforce Data360 Audience QA
Works with the AI Agents you already use
Salesforce Data360 Audience QA
Validate Salesforce Data 360 segment membership, identity joins, and activation payloads against business contracts.
Free
Salesforce Data360 Audience QA
Example session with this skill installed
Validate Segment 'High_Value_Loyalty_v2' against the v3 audience contract. The population count is 12,500 but expected 13k. Check inclusion for ID 'IND_998'.
- Read your context and instructions
- Compiled the salesforce data360 audience
I have completed the QA validation for segment
High_Value_Loyalty_v2 against the
v3 Audience Contract. The analysis identified a 4% population variance and one specific predicate failure for identity resolution.
Audience QA Validation Report
| Check Category | Attribute | Status | Detail/Evidence |
|---|---|---|---|
| Metadata | Segment Version | PASS | v2 (Match) |
| Metadata | Root DMO | PASS | Unified Individual |
| Data Freshness | CI Run Time | WARN | Run completed 4h ago; Source 'Sales_Order' is pending refresh. |
| Membership | Total Count | FAIL | Observed: 12,500 |
| Identity | IND_998 Inclusion | FAIL | Excluded. Predicate LTV > 500 returned NULL due to stale CI. |
| Activation | Contact Key | PASS | Using PartyId alias. |
| Activation | One-to-Many | WARN | 120 members produced 2+ rows due to multiple Email addresses. |
Discrepancy Analysis
The 500-member shortfall is primarily attributed to the stale
Sales_Order source. Profiles relying on recent transactions to cross the LTV threshold are currently failing the inclusion predicate. Specifically, for
IND_998, the relationship path Individual -> Unified_Link -> Calculated_Insight returned a null value for the Total_Revenue attribute.
Next steps
- Re-run the
LTV_Calculated_Insightafter the 'Sales_Order' data stream refresh completes. - Update the Activation configuration to use 'Most Recent' contact point selection to resolve row duplication.
- Re-verify segment population once the CI status is 'Success'.
Connects securely to your tools. The creator never sees your data.
About this skill
Audience segments often fail due to stale data, incorrect identity joins, or unexpected one-to-many relationships. This skill validates Salesforce Data 360 segment membership and activation payloads against business contracts to ensure accuracy before delivery.
What it does
- Segment Validation verifies publication time, member counts, root DMOs, and identity rulesets against expected values.
- Inclusion/Exclusion Analysis evaluates specific predicates and relationship paths to explain why specific IDs are present or missing.
- Activation Auditing inspects contact keys, channel contact points, and output aliases to ensure they match destination requirements.
- Row Count Resolution identifies one-to-many duplicates caused by multiple holdings, addresses, or contact points per member.
- Dependency Tracking reports stale upstream inputs or pending CI runs that invalidate current segment results.
How it works
- Input Collection provides the segment definition, population results, and the approved audience contract.
- Predicate Evaluation runs inclusion and exclusion test cases using stable synthetic or approved identities.
- Discrepancy Mapping generates set differences to isolate expected-but-absent and present-but-unexpected members.
- Payload Verification checks the final export for consent rules, suppression, and data types.
Frameworks & tools
Specifically designed for Salesforce Data Cloud (Data 360), focusing on Data Model Objects (DMO), Calculated Insights (CI), and Activation Targets.
Why this beats prompting it yourself
Generic prompts often overlook the complexity of identity resolution rules and one-to-many relationship cardinality. This skill enforces a structured comparison of set differences and predicate evidence, preventing "black box" segment errors.
Use cases
- Validate a new high-value marketing segment before scheduled activation.
- Debug why specific test profiles are missing from a published audience.
- Audit activation payloads for correct contact point selection and suppression.
- Verify that upstream CI runs and source refreshes are current before QA.
Known limitations
Read-only QA only. It cannot authorize segment publishing or activation delivery. Test endpoints must be pre-approved; do not include PII in reports.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Data & Databases.
Read-only validation. Cannot trigger segment publishing or activation. Requires pre-approved test identities. Does not handle PII data in reporting.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 5 days ago
- Free with an Agensi account
- Accounts
Salesforce
- Software
Node.jssalesforce cli
Permissions
Allowed Hosts