Salesforce data operations with 130-point scoring. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, or needs data factory patterns for Apex tests. DO NOT TRIGGER when: SOQL query writing only (use sf-soql), Apex test execution (use sf-testing), or metadata deployment (use sf-deploy).
Use this skill when the user needs Salesforce data work: record CRUD, bulk import/export, test data generation, cleanup scripts, or data factory patterns for validating Apex, Flow, or integration behavior.
Use sf-data when the work involves:
sf data CLI commandsDelegate elsewhere when the user is:
Confirm which mode the user wants:
| Mode | Use when |
|---|---|
| Script generation | they want reusable .apex, CSV, or JSON assets without touching an org yet |
| Remote execution | they want records created / changed in a real org now |
Do not assume remote execution if the user may only want scripts.
Ask for or infer:
sf-data acts on remote org data unless the user explicitly wants local script generation.If metadata is missing, stop and hand off to:
Confirm object / field availability, org auth, and required parent records.
| Need | Default approach |
|---|---|
| small one-off CRUD | sf data single-record commands |
| large import/export | Bulk API 2.0 via sf data ... bulk |
| parent-child seed set | tree import/export |
| reusable test dataset | factory / anonymous Apex script |
| reversible experiment | cleanup script or savepoint-based approach |
Use the built-in templates under assets/ when they fit:
assets/factories/assets/bulk/assets/cleanup/assets/soql/assets/csv/assets/json/Check counts, relationships, and record IDs after creation or update.
Provide exact cleanup commands or rollback assets whenever data was created.
Prefer one of:
| Error | Likely cause | Default fix direction |
|---|---|---|
INVALID_FIELD | wrong field API name or FLS issue | verify schema and access |
REQUIRED_FIELD_MISSING | mandatory field omitted | include required values |
INVALID_CROSS_REFERENCE_KEY | bad parent ID | create / verify parent first |
FIELD_CUSTOM_VALIDATION_EXCEPTION | validation rule blocked the record | use valid test data or adjust setup |
DUPLICATE_VALUE | unique-field conflict | query existing data first |
| bulk limits / timeouts | wrong tool for the volume | switch to bulk / staged import |
When finishing, report in this order:
Suggested shape:
Data operation: <create / update / delete / export / seed>
Objects: <object + counts>
Target: <org alias or local path>
Artifacts: <record ids / csv / apex / json files>
Verification: <passed / partial / failed>
Cleanup: <exact delete or rollback guidance>
| Need | Delegate to | Reason |
|---|---|---|
| discover object / field structure | sf-metadata | accurate schema grounding |
| run bulk-sensitive Apex validation | sf-testing | test execution and coverage |
| deploy missing schema first | sf-deploy | metadata readiness |
| implement production logic consuming the data | sf-apex or sf-flow | behavior implementation |
| Score | Meaning |
|---|---|
| 117+ | strong production-safe data workflow |
| 104–116 | good operation with minor improvements possible |
| 91–103 | acceptable but review advised |
| 78–90 | partial / risky patterns present |
| < 78 | blocked until corrected |