Loading...
Loading...
Found 115 Skills
Official Salesforce documentation retrieval skill. Use when you need authoritative Salesforce docs from developer.salesforce.com, help.salesforce.com, architect.salesforce.com, admin.salesforce.com, or lightningdesignsystem.com, especially when pages are JS-heavy, shell-rendered, or hard to extract with naive fetching. Use to ground answers in official Salesforce sources instead of third-party blogs or summaries. TRIGGER when: user asks for official Salesforce documentation, Apex or API reference, LWC docs, Agentforce docs, setup or help articles, or any doc from a Salesforce-owned domain. DO NOT TRIGGER when: user is asking for a code change, deployment task, or anything not requiring documentation retrieval — use the appropriate sf-* skill instead.
Custom Apex adapter generation for Salesforce Connect — connects any external REST API to Salesforce as live, queryable External Objects without ETL or data copying. TRIGGER when: user wants to connect a non-standard external API to Salesforce, asks to write a DataSource.Provider or DataSource.Connection, wants to surface external data as Salesforce records, says "connect my API to Salesforce without copying data", or asks whether custom Apex is the right approach for any system. Also trigger on: "custom adapter", "ExternalId field", "DataSource namespace". DO NOT TRIGGER when: user is configuring a standard adapter they already have and is NOT asking about custom Apex (e.g., OData endpoint setup, Snowflake connector config). DO NOT TRIGGER when: user wants to copy or bulk-sync data — use platform-data-manage. DO NOT TRIGGER for Apex callouts outside Connect — use platform-apex-generate or integration-connectivity-generate.
Use when developing Salesforce applications, Apex code, Lightning Web Components, SOQL queries, triggers, integrations, or CRM customizations. Invoke for governor limits, bulk processing, platform events, Salesforce DX.
Use to create N Omni-Channel supervisor users on a Salesforce org via Anonymous Apex, using the supervisor{i}.<suffix>@example.com pattern with SOQL-based idempotency (re-runs skip existing usernames). Passwords are set via System.setPassword and handled fail-closed: the wrapper proves no active debug TraceFlag before setting a password, and otherwise leaves the user ACTIVE and reset_required. Triggers: create supervisor users, provision supervisor accounts, scaffold supervisor personas. Do not use on production customer orgs (blocked by the safe_to_write guard), to bind supervisors to OmniSupervisorConfig (service-omni-supervisor-config-deploy), or to assign the ContactCenterSupervisor permission set (service-omni-supervisor-permset-assign).
SOQL query generation, optimization, and analysis with 100-point scoring. Use this skill when the user needs SOQL/SOSL authoring or optimization: natural-language-to-query generation, relationship queries, aggregates, query-plan analysis, and performance or safety improvements for Salesforce queries. TRIGGER when: user writes, optimizes, or debugs SOQL/SOSL queries, touches .soql files, or asks about relationship queries, aggregates, or query performance. DO NOT TRIGGER when: bulk data operations (use handling-sf-data), Apex DML logic (use generating-apex), or report/dashboard queries.
Reference for how to call the Salesforce LSP MCP tools and what to do when they are unavailable. Use when the user asks how to use the Salesforce LSP, which LSP/MCP tools exist, what apex.diagnostics / validate_soql / complete_soql do, why an LSP tool returned an error like lsp_disabled or no_apex_workspace or no_org_connected, how to debug the LSP host, or how to turn the LSP off. Also the contract other skills follow when they call an LSP tool: which tool to prefer, how to read its result, and the fallback when the LSP host is absent. DO NOT TRIGGER for generating or editing Apex/LWC/metadata (use platform-apex-generate), running deploys (use platform-metadata-deploy), or SOQL authoring (use platform-soql-query); this skill is a reference and contract document — use it only when the question is specifically about the LSP layer or its MCP tools.
Lightning Web Components development skill with PICKLES architecture methodology, component scaffolding, wire service patterns, event handling, Apex integration, GraphQL support, and Jest test generation. Build modern Salesforce UIs with proper reactivity, accessibility, dark mode compatibility, and performance patterns.
Query and manage Salesforce CRM data via the Salesforce CLI (`sf`). Run SOQL/SOSL queries, inspect object schemas, create/update/delete records, bulk import/export, execute Apex, deploy metadata, and make raw REST API calls.
Salesforce Metadata API reference for creating, understanding, or modifying metadata XML files (.object-meta.xml, .flow-meta.xml, etc.) and any of 604 metadata types (CustomObject, Flow, ApexClass, ApexTrigger, Profile, PermissionSet, Layout, ValidationRule, RecordType, EmailTemplate, ...). Use for questions about a type's fields or XML format, or Salesforce DX project structure (force-app/main/default). TRIGGER when: authoring or editing any *-meta.xml file, asking what fields/format a metadata type has, or whenever 'Salesforce metadata' or 'sfdx project' is mentioned. DO NOT TRIGGER when: SOQL/DML/runtime sObject access (use the Enterprise API skill), Tooling API developer records (ApexExecutionOverlayAction, TraceFlag), or non-XML logic (Apex code, LWC JS, Visualforce controllers).
Use this skill when users need to create, generate, or validate Salesforce Custom Metadata Type metadata — the __mdt object, its fields, and its deployable records. Trigger when users mention custom metadata types, CMDT, __mdt objects, custom metadata records, .md-meta.xml files, or reference/config data that must ship between orgs. Also trigger for admin-maintained mapping, lookup, or crosswalk tables and field mappings ("map fields from A to B", code lookups) — config admins change without a code deploy belongs in a CMDT, never hardcoded in Apex or Flow — and when troubleshooting CMDT record/type deploy errors. DO NOT TRIGGER for Custom Settings — route to platform-custom-setting-generate; for regular custom objects holding business records — use platform-custom-object-generate; or for secrets and API keys — recommend a Named Credential, which this skill never generates.
OmniStudio Integration Procedure creation and validation with 110-point scoring. Use when building server-side process orchestrations that combine Data Mapper actions, Apex Remote Actions, HTTP callouts, and conditional logic. TRIGGER when: user creates Integration Procedures, adds Data Mapper steps, configures Remote Actions, or reviews existing IP configurations. DO NOT TRIGGER when: building OmniScripts (use sf-omniscript), creating Data Mappers directly (use sf-datamapper), or analyzing cross-component dependencies (use sf-omnistudio-analyze).
Use when reviewing or implementing Lightning Data Service best practices in an LWC (.js, .html, .js-meta.xml) — UIAPI vs Apex, refreshApex / notifyRecordUpdateAvailable, @salesforce/schema imports, LDS record-form data patterns. TRIGGER on "apply LDS best practices to this LWC", "review this LWC for LDS best-practice issues", "review this component for Lightning Data Service issues", "UIAPI or Apex for this data?", "fix stale data after record save", "sync LDS cache", "use @salesforce/schema for field names", "choose between getRecord and Apex". DO NOT TRIGGER when building a new LWC (use experience-lwc-generate), applying SLDS design tokens (use design-systems-slds-apply), picking or wiring a `lightning-*` base component's props/events/slots generically (use experience-lwc-base-components-integrate — this skill covers only the LDS data-layer rationale, even when the fix involves a base record form), or for security / RTL / accessibility reviews (separate passes).