Works with the AI Agents you already use
Salesforce Data360 Governance
Enforce naming conventions, source-to-target mapping, and change discipline for Salesforce Data Cloud.
Free
Salesforce Data360 Governance
Example session with this skill installed
Review the current DLO mappings for the S3_Customer_Data stream against our STTM and report any drift or naming violations before I update the transform logic.
- Read your context and instructions
- Compiled the salesforce data360 governance
I have audited the S3_Customer_Data Data Lake Object (DLO) against the project naming conventions and the latest Source-to-Target Mapping (STTM) document. I detected two naming violations and one mapping discrepancy between the live environment and the repository configuration.
Data 360 Governance Audit: S3_Customer_Data
| Component | Found Value | Expected Value | Status |
|---|---|---|---|
| DLO Developer Name | S3_Cust_Data_Internal | S3_Customer_Data_DLO | FAIL (Naming) |
| Primary Key Field | cust_id_pk | customer_id_key | FAIL (Contract) |
| Field: Email_Address | Email_Address | Email_Address | PASS |
| Field: Phone_Home | Phone_Home | Phone_Home | PASS |
| Source Path | s3://bucket/raw/ | s3://bucket/v2/raw/ | DRIFT (Live) |
Analysis
- Naming Violation: The DLO developer name does not match the project convention
[Source]_[Object]_DLO.
Key Stability: The primary key in the live org (cust_id_pk) differs from the STTM (customer_id_key). Changing this key will create duplicate records rather than updating existing ones.
3.
Drift Detected: The live Data Stream is consuming from a legacy S3 path (/raw/) while the repository manifest points to /v2/raw/.
Next steps
- Update the local
project-conventions.mdto confirm ifcust_id_pkwas an intentional override. - Execute the project naming validator to generate the corrected metadata manifest.
- Request authorization to update the S3 source path in the live org to resolve drift.
Connects securely to your tools. The creator never sees your data.
About this skill
Data 360 Governance enforces strict naming conventions, source-of-truth alignment, and change discipline for Salesforce Data Cloud environments. It prevents common implementation failures by requiring preflight checks and drift analysis before any metadata mutation.
What it does
- Enforce naming conventions by running project-specific validators before asset creation.
- Maintain source-of-truth by aligning Data Streams and mappings with approved STTM documents.
- Perform drift analysis between repository configurations and the live org state to prevent silent overwrites.
- Manage idempotent changes by skipping exact matches and halting on incompatible definitions.
- Automate post-change hooks to refresh affected dependencies and verify runtime usability.
How it works
- Inventory phase: Inspect the active repository for naming guides, STTMs, and deployment manifests.
- State verification: Query the live org via MCP or Salesforce CLI to compare observed state against desired configuration.
- Plan and Diff: Generate a field-level diff and read-only inventory before proposing mutations.
- Execution: Apply changes using authenticated clients, respecting API limits and identity rules.
- Validation: Verify runtime status and trigger authorized post-hooks for downstream dependencies.
Frameworks & tools
Specific to Salesforce Data Cloud (Data 360). Integrates with Salesforce CLI, Data 360 MCP, and standard Connect APIs. Uses project-specific project-conventions.md and STTM artifacts.
Why this beats prompting it yourself
Standard prompting often ignores the nuance of primary key immutability and the specific refresh behaviors of Data Cloud. This skill enforces a hard requirement for preflight verification, preventing broken identity rules and accidental record duplication that occur when primary keys are modified without discipline.
Use cases
- Safe metadata deployment by checking for naming violations before pushing new Data Streams.
- Identity resolution auditing to ensure source keys remain stable across updates.
- Environment synchronization by identifying drift between Git configurations and the live Data Space.
- Dependency management to automate the refresh of Calculated Insights after mapping changes.
Known limitations
Does not support automatic deletion of live assets without explicit authorization. Requires a pre-existing authenticated session or MCP configuration. UI-only steps must be verified manually.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.
Requires authenticated Salesforce CLI or MCP. Cannot auto-delete assets. UI-only configurations require manual verification. Does not support retrying validation failures.
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