Claude Skills by PranavNagrecha

Decide whether an existing Apex trigger should be rewritten as a Flow, and execute the migration safely. Covers the decision criteria (complexity, ownership, performance), side-by-side rollout, test-coverage. NOT for migrating Process Builder / Workflow Rule to Flow (use those migration skills) — use flow/process-builder-to-flow-migration.

Use when a Screen Flow needs to send the user to another page — the native Open a Page action (Summer '26) that opens a Salesforce record or an external URL directly from a flow. NOT for launching or embedding a flow — use flow/screen-flows. NOT for a custom navigation LWC — use flow/flow-screen-lwc-components.

Flow Orchestration design patterns — multi-stage, multi-step flows where each step is itself an autolaunched flow or a screen flow assigned to a user / queue, with Work Items appearing in users' inboxes for interactive steps. Covers the stage / step model, interactive vs background steps, evaluation flows that gate stage transitions, work-item assignment (running user / queue / formula-derived user), and the persistence model (orchestrations survive across days / weeks). NOT for a standard Ap...

Tune Flow runtime performance: pick Before-Save over After-Save, consolidate Get Records, eliminate loop-DML, cache lookups, split with Scheduled Paths, and measure actual runtime. Covers benchmarking methodology, profiling tools, and the 80/20 wins. NOT for governor-limit math — use flow/flow-governor-limits-deep-dive. NOT for LDV strategy — use flow/flow-large-data-volume-patterns.

Use when Flow is a Platform Event publisher, subscriber, or both. Triggers: 'publish platform event from flow', 'platform-event-triggered flow', 'high-volume platform event', 'publish after commit vs immediate', 'PE subscriber error handling', 'integration fan-out from save'. NOT for Change Data Capture — use integration/change-data-capture-integration. NOT for async work that needs no pub/sub — use flow/scheduled-flows.

Build reactive Flow screens where one component updates another without navigation using reactive formulas and component outputs. NOT for Aura-based screens — use flow/flow-screen-input-validation-patterns.

Diagnose and prevent UNABLE_TO_LOCK_ROW + parent-record contention in record-triggered, scheduled, and screen flows by mapping the implicit lock chain and applying decouple patterns (Platform Events, Queueable handoff, Scheduled Paths). NOT for general flow bulkification — see flow-bulkification — use apex/record-locking-and-contention.

Reason about how record-triggered flows interleave with the Salesforce Save Order (validation, before-save flows, before triggers, duplicate rules, after-save flows, workflow, after triggers, assignment, auto-response, escalation). Trigger keywords: save order, before-save flow, after-save flow, dml order, trigger vs flow order, order of execution step, recursive save, triggerOrder, doesRequireRecordChangedToMeetCriteria, AsyncAfterCommit, FLOW_START_INTERVIEW_BEGIN, stale field after save. N...

Flow resource types and when to use each: Variables, Collection Variables, Constants, Formulas, Text Templates, Choices, Stages, Picklist Choice Sets, Record Choice Sets. Covers scope, data types, and reuse patterns. Triggers: 'which Flow resource type', 'record choice set or picklist choice set', 'choice collection from records in a Flow' (the choice-set wiring itself is flow/flow-dynamic-choices). NOT for decision elements. NOT for custom metadata (use admin/custom-metadata-types).

Use the Flow Rollback Records element to undo DML inside the current transaction. Covers when rollback is appropriate vs catastrophic, how to combine with fault paths, partial-commit pitfalls, and the interaction with publish-after-commit. NOT for external-system rollback (use compensation patterns) — use apex/apex-savepoint-and-rollback.

Flow runtime sharing context — run in user vs system mode, record access in Flow. Triggers: Flow sharing, run in system mode, Flow user context. NOT for Apex sharing declarations — use apex/apex-with-without-sharing-decision.

Use when a Salesforce Flow throws a runtime error, sends an unhandled fault email, or produces unexpected results in production or sandbox. Triggers: 'Flow error email', 'Flow failed at element', 'null reference in Flow', 'Flow SOQL limit error', 'Flow DML in loop error'. NOT for changing who receives fault emails or suppressing noisy ones — use flow/flow-error-notification-patterns. NOT for designing fault paths before anything fails — use flow/fault-handling. NOT for org-wide error alerting...

Design input validation inside Screen Flow screens using component-level <validationRule> (formula + errorMessage), isRequired, cross-field rules on the second field, reactive components, and screen-level Decision fallbacks for cross-screen checks. Trigger keywords: screen flow validation rule, EndDate after StartDate validation in flow screen, block Next button until input valid. NOT for record-level Validation Rules — use admin/validation-rules. NOT for choosing screen components or overall...

Design custom Lightning Web Components that render inside Screen Flow steps — covers the lightning__FlowScreen target, @api properties as Flow inputs/outputs, FlowAttributeChangeEvent propagation, FlowNavigationNext/Back/Finish/Pause events, the @api validate() hook, and design-time targetConfig wiring. NOT for the Flow Builder design-time editor that configures it — use flow/flow-custom-property-editors. NOT for the LWC-side implementation deep-dive — use lwc/lwc-in-flow-screens.

Use when defining or reviewing test strategy for Salesforce Flow, including Flow Tests, debug runs, path coverage, test data, and explicit validation of fault paths and custom component behavior. Triggers: 'flow test tool', 'how do i test a flow', 'flow fault path testing', 'flow debug interview'. NOT for Apex unit testing or manual QA planning that is unrelated to Flow behavior — use flow/flow-debugging. Also covers: FlowTest metadata, flowtest-meta.xml, testPoints, Flow.Interview, sf flow r...

Time-based execution in Salesforce Flow — Scheduled Paths in record-triggered flows (delays measured against a record date or trigger fire time), the Wait element in autolaunched / orchestration flows, scheduled flows on a cron-like cadence, the offset semantics (`+N` days vs `-N` days from a date field), requeueing when the source record changes, the time-zone rules that decide when 'tomorrow at 9 AM' actually fires, and the workflow-rule-time-based-action replacement playbook. NOT for tunin...

Use when a Flow needs to do work that must survive the triggering transaction — post-commit notifications, callouts, audit rows, or compensating actions. Covers Flow Transaction Control element, scheduled paths, Platform Event + finalizer. NOT for general Flow async decisions (see async-selection) — use apex/apex-transaction-finalizers.

Reason about when a Flow is inside the caller's transaction vs starts its own. Pick Before-Save vs After-Save vs Async Path vs Pause + Resume when transaction boundaries matter. Covers governor-limit sharing, DML sequencing, recoverability, and the limits that reset when a new transaction starts. NOT for choosing Flow vs Apex (use admin/process-automation-selection) or record-triggered design — use flow/record-triggered-flow-patterns.

Manage Flow versions: activation policy, paused interview compatibility, cleanup cadence, and breaking-change detection. Trigger keywords: flow version management, activate flow version, paused interview, flow cleanup, flow breaking change, flow rollback. NOT for the deploy-time activation order of FlowDefinition metadata — use devops/flow-deployment-activation-ordering. NOT for moving a flow from sandbox to production — use flow/flow-deployment-and-packaging.

Use when designing or reviewing Flow Orchestration for long-running, multi-user, or asynchronous business processes with stages, steps, work items, and monitoring needs. Triggers: 'flow orchestration', 'work item', 'stages and steps', 'multi-user process', 'long-running flow'. NOT for stage gating, work-item assignment and the cancel pathway — use flow/flow-orchestration-patterns. NOT for lightweight approval routing that needs no orchestration — use admin/approval-processes.

Use this skill when designing or troubleshooting flows that need to suspend execution and wait for an external signal — either a time-based alarm or a platform event. Trigger keywords: pause element, wait element, paused flow interview. NOT for flows that recur on a fixed schedule (use flow/scheduled-flows) or scheduled-path setup — use flow/flow-time-based-patterns.

Migrate Process Builder processes to record-triggered Flows using the native Migrate to Flow tool or manual rebuild. Covers conversion tool usage, pattern mapping, order-of-execution changes, testing migrated flows, and bulk behavior improvements. NOT for Workflow Rule migration — use flow/workflow-rule-to-flow-migration. NOT for designing net-new automation — use admin/process-automation-selection.

Use when designing or reviewing Salesforce record-triggered Flows, especially before-save vs after-save behavior, entry criteria, recursion avoidance, and when to escalate to Apex. Triggers: 'before save vs after save', '$Record__Prior', 'record-triggered flow', 'order of execution', 'flow recursion', 'triggerOrder', 'doesRequireRecordChangedToMeetCriteria', 'scheduled path', 'RecordBeforeDelete', 'flow-meta.xml', 'FlowTest'. NOT for tracing save order against triggers — use flow/flow-record-...

Use when a record-triggered Flow re-fires on the same record because its own DML (or a downstream Flow's DML) re-satisfies the entry criteria — causing CPU-limit failures, duplicated side effects, or 'Maximum Trigger Depth Exceeded' errors. Triggers: 'flow infinite loop', 'flow re-firing on same record', 'flow updates field then runs again', 'flow A and flow B keep updating each other', 'maximum trigger depth exceeded record-triggered flow', 'flow recursion limit hit'. NOT for Apex trigger re...

Use when a Schedule-Triggered Flow is configured but is not firing at the expected time, or appears active in Setup → Flows but never produces output. Covers where scheduled flows actually surface (Setup → Scheduled Jobs, NOT Setup → Apex Jobs), the AsyncApexJob / CronTrigger evidence trail, top causes (deactivated scheduling user, daylight-savings transitions, time-zone mismatches between scheduling user and org, fault-paths that quietly stop the schedule, daily async-Apex limit pressure), a...

Use when designing or reviewing schedule-triggered flows for recurring automation, replacement of time-based workflow patterns, bounded record selection, idempotent processing, and escalation to Apex when volume is too high. Triggers: 'scheduled flow design', 'nightly flow job', 'time based workflow replacement', 'schedule triggered flow limits'. NOT for record-triggered scheduled paths — use flow/flow-time-based-patterns. NOT for large-scale batch processing — use apex/batch-apex-patterns.

Screen Flow accessibility — WCAG 2.2 AA, labels, keyboard, error announcements. Triggers: accessible Screen Flow, Flow WCAG, screen reader Flow. NOT for LWC component a11y inside screens — use lwc/lwc-accessibility.

Use when picking which Screen Flow component collects a choice from users — Picklist, Radio Buttons, Radio Button Group (Summer '26), Multi-Select Picklist, Checkbox Group, Choice Lookup, Dependent Picklists, or Data Table — and which Choice resource (Choice, Record Choice Set, Picklist Choice Set) populates it. Covers single- vs multi-select semantics, the Loop/Transform incompatibility of the multi-select components, and set-size/searchability tradeoffs. NOT for building the choice-set reso...

Use when adding or configuring the Summer '26 Radio Button Group screen component in a Screen Flow — the compact choice input that lays options out as horizontal boxes on desktop and vertical boxes on mobile, single-select by default with a 'Let Users Select Multiple Options' setting that makes it behave as a Checkbox Group. Covers choosing it over traditional Radio Buttons / Picklist / Checkbox Group, wiring its options to a Choice resource or dynamic choice set, and the single-value-vs-coll...

Use when designing or reviewing interactive Flow screen experiences, including navigation, validation, screen component choice, custom LWC screen components, and user-safe commit timing. Triggers: 'screen flow validation', 'back button behavior in flow', 'custom flow screen component', 'screen flow UX'. NOT for building the custom LWC that renders on a screen — use flow/flow-screen-lwc-components. NOT for per-field validation that blocks Next — use flow/flow-screen-input-validation-patterns.

Use when extracting reusable Flow logic into subflows, defining input and output variables, keeping parent flows maintainable, and sharing common automation contracts across multiple flows. Triggers: 'reuse this flow logic', 'how should subflow variables work', 'too much duplicated flow logic', 'subflow contract design'. NOT for Apex-called Flow execution — use flow/auto-launched-flow-patterns. NOT for Flow Orchestration process design — use flow/flow-orchestration-patterns.

Migrate Workflow Rules to record-triggered Flows: field update mapping, email alert migration, outbound message alternatives using Flow Core Actions, time-based workflow replacement with Scheduled Paths. NOT for Process Builder migration — use flow/process-builder-to-flow-migration. NOT for building the replacement flow from scratch — use flow/record-triggered-flow-patterns.

Designing HTTP error classification, RFC 7807-style error payload structure, and client-side error parsing for Salesforce REST/SOAP integrations and custom Apex REST endpoints. Use when deciding which HTTP status codes an endpoint returns and how callers classify them. NOT for retry mechanics or circuit breakers (use integration/retry-and-backoff-patterns) — use architect/integration-framework-design.

Monitor and govern Salesforce API consumption: per-user limits, org allocation, lightning-rest limits, and backoff. NOT for designing new endpoints — use security/api-security-and-rate-limiting.

Use when designing a multi-system integration architecture on the three-layer API-led connectivity pattern (System, Process, Experience APIs), deciding how many layers to apply, mapping Salesforce as a system-layer endpoint or experience-layer consumer, or how Agentforce and MuleSoft Agent Fabric use API-led patterns. Triggers: 'API-led connectivity', 'system API process API experience API', 'MuleSoft integration layers', 'application network'. NOT for governing the API platform itself — cata...

Design versioning for custom Apex REST endpoints: URI versioning, backward compatibility, deprecation sunset. NOT for consuming external APIs — use apex/apex-rest-services.

Use this skill when setting up or extending Salesforce Automotive Cloud — including the Vehicle / VehicleDefinition data model, dealer-OEM relationship modeling via AccountAccountRelation, ActionableEvent orchestration. NOT for general Sales Cloud opportunity work on a vehicle product (use admin/opportunity-management) — use architect/industries-data-model.

AWS integration patterns for Salesforce — pick between Amazon AppFlow, Event Relay → EventBridge, Amazon S3 ingestion paths, and direct Apex → Lambda callouts. Decision matrix + AppFlow deep dive (Salesforce as source / destination, OAuth Authorization-Code vs JWT, REST vs Bulk 2.0 API, 15 GB / run cap). NOT for Azure — use integration/azure-salesforce-patterns. NOT for Event Relay setup steps — use integration/event-relay-configuration.

Azure integration patterns for Salesforce — pick between the native Azure Service Bus Connector, Azure Functions / API Management as the callout target, Data 360 (Data Cloud) Azure Blob Storage ingestion, Azure AD as IdP via SAML/OIDC, and the Power Platform Salesforce connector. Decision matrix + auth model guidance (Named Credentials with External Credentials, OAuth 2.0 client-credentials, JWT Bearer, SAML). NOT for AWS — use integration/aws-salesforce-patterns. NOT for point-to-point vs hu...

Use when designing or hardening external-to-Salesforce integrations that orchestrate Bulk API 2.0 ingest or query jobs: OAuth-backed job lifecycle, mandatory UploadComplete, polling JobComplete/Failed, CSV upload sizing, locator pagination for query results, partial-failure retry, and ordered multi-job loads (parent before child). Trigger keywords: bulk ingest job stuck in Open, retry only failed bulk rows, poll Bulk API 2 job status, Sforce-Locator pagination, multipart bulk ingest vs CSV up...

Use when designing or troubleshooting Apex callouts that approach governor limits: choosing between synchronous callouts, @future, Queueable, Continuation, or async chaining strategies. NOT for the @future rules themselves — primitive-only parameters, no chaining, the 50-per-transaction cap — use apex/apex-future-method-patterns. NOT for building the HttpRequest, handling the response, or mocking the callout in tests — use apex/callouts-and-http-integrations. NOT for configuring the Named Cre...

Use this skill when setting up CDC to stream Salesforce record changes to external systems via CometD or Pub/Sub API. Covers change event channels, entity selection, event structure, replay ID management, gap events, and subscriber management. NOT for Apex CDC trigger subscribers (see apex/platform-events-apex). NOT for publishing custom business events (use integration/platform-events-integration).

Use when designing, implementing, or troubleshooting Salesforce Composite API requests — covering the /composite/ resource with cross-subrequest referenceId wiring, /composite/sobjects/ bulk CRUD, /composite/tree/ hierarchical inserts, and /composite/batch/ independent subrequest bundling. Triggers: 'composite API', 'sObject Tree', 'sObject Collection', 'composite batch', 'subrequest', 'referenceId', 'allOrNone', 'parent child insert one call', 'bulk CRUD same object', 'batch API requests'. N...

Use Connect REST API for Chatter, feeds, communities, and CMS content instead of querying underlying SObjects. NOT for custom business object CRUD — use integration/graphql-api-patterns.

Use this skill when building developer-driven Data Cloud activation surfaces: webhook Data Action Targets with HMAC-SHA256 signing, Salesforce Platform Event data actions, Data Cloud-Triggered Flows on DMO insert. NOT for standard admin-level Activation Targets (SFTP, ad platform segment publishing) — use admin/data-cloud-segmentation. NOT for receiving webhooks into Salesforce — use integration/webhook-inbound-patterns.

Use when implementing or troubleshooting the Salesforce Data Cloud Ingestion API — covers streaming ingestion (near-real-time micro-batches), bulk ingestion (CSV-based full-replace jobs), schema management in OpenAPI. NOT for standard Salesforce Bulk API, CRM Analytics data import, or Data Cloud data stre — use integration/bulk-api-2-patterns.

Use this skill when designing or troubleshooting the data pipeline strategy for connecting source systems to Data Cloud — including ingestion API pattern selection (streaming vs. batch), connector type decisions. NOT for standard Salesforce integration patterns (use integration-patterns skill), not f — use data/data-cloud-data-streams.

Use this skill when querying unified profile data, calculated insights, or Data Lake Objects from Data Cloud using ANSI SQL via the Query V2 or Query Connect APIs. Triggers on: SQL queries against Data Cloud, querying. NOT for SOQL against standard objects, Data Cloud segment filtering in the UI, or vector search — use data/data-cloud-data-streams.

Use this skill when configuring or troubleshooting Data Cloud Zero Copy / Lakehouse Federation against Snowflake, Databricks, BigQuery, or Redshift — including external Data Lake Object setup, query semantics, refresh/cache behavior, and federation versus physical ingestion. NOT for physical Ingestion API streaming/bulk — use integration/data-cloud-integration-strategy. NOT for CRM Analytics external connectors — use data/analytics-external-data. NOT for outbound Data Cloud activation — use i...

Use when transforming structured data inside Apex — CSV → JSON, XML → SObject list, JSON → flattened CSV, or schema-mapping a third-party payload to a Salesforce model — and the existing options (`JSON.deserialize`, `Dom.Document` traversal) are too fragile. NOT for MuleSoft Anypoint DataWeave running off-platform (use architect/mulesoft-anypoint-architecture) — use apex/apex-json-serialization.