forcedotcom/sf-skills

platform-custom-lightning-type-generate

Use this skill when users need to create Custom Lightning Types (CLTs) for Einstein Agent actions or structured input/output schemas.

查看源码
仓库原始内容

按源仓库内容呈现,保留标题、案例、代码、表格、链接以及原文引用的演示图片。

When to Use This Skill

Use this skill when you need to:

  • Create Custom Lightning Types (CLTs) for structured inputs/outputs
  • Generate JSON Schema-based type definitions for Lightning Platform
  • Configure CLTs for Einstein Agent actions
  • Set up editor and renderer configurations for custom UI
  • Troubleshoot deployment errors related to Custom Lightning Types

Specification

CustomLightningType Metadata Specification

Overview & Purpose

Custom Lightning Types (CLTs) are JSON Schema-based type definitions used by the Lightning Platform (including Einstein Agent actions) to describe structured inputs/outputs and drive editor/renderer experiences.

Configuration

  • Choose referenced CLT pattern for nested objects - When you need a reusable or separately deployed nested type, create a CLT for that shape and reference it with "lightning:type": "c__<CLTName>". That string is the referenced type’s `lightning:type` value / FQN / registered identifier — not the JSON Schema title.
  • Choose standard Lightning types when the structure is simple and can be expressed with properties and supported primitive lightning:type identifiers.
  • Choose Apex class types (@apexClassType/...) when the structure already exists server-side and you want the Apex class to define the shape.
  • Include editor/renderer config only when you need custom UI behavior (custom LWC input/output components). Otherwise, omit.

Critical Rules (Read First)

  • CRITICAL: NEVER include the `"$schema"` field in schema.json
  • Salesforce CLT validator WILL REJECT schemas with this field, even if it's a valid JSON Schema $schema declaration.
  • Root object schemas MUST include:
  • "type": "object"
  • "title"
  • "lightning:type": "lightning__objectType"
  • "unevaluatedProperties": false
  • "unevaluatedProperties" is enforced as false by the CLT metaschema. Do not set it to true.
  • Root object schemas MUST NOT include "examples" when "unevaluatedProperties": false is set.
  • Nested objects (inside `properties`) MUST NOT set "lightning:type": "lightning__objectType".
  • Nested objects can be: references to other CLTs using c__<CLTName> syntax.
  • List/array properties are highly restricted by the CLT metaschema:
  • CRITICAL LIMITATION: the CLT metaschema may reject the items keyword entirely. Treat items as disallowed by default.
  • Root-level arrays (direct children of the root properties):
  • MUST include "lightning:type": "lightning__listType"
  • MUST NOT include "items"
  • OPTIONAL "type": "array"
  • Nested arrays (arrays inside nested objects) are the most common failure:
  • MUST include "type": "array"
  • MUST NOT include "lightning:type": "lightning__listType"
  • MUST NOT include "items"
  • When `"unevaluatedProperties": false` is set, any unknown keyword will fail validation. Prefer removing keywords over relaxing strictness.
  • Apex class CLTs are minimal:
  • Include only title, description (optional), and lightning:type set to @apexClassType/....
  • Do not add type, properties, required, or unevaluatedProperties.
  • Custom LWC renderers/editors on an Apex class CLT MUST NOT use `attributes` in the root override — this overrides any prompt wording to the contrary. Since the schema has no properties block, there is nothing for {!$attrs.<name>} to resolve against — unevaluatedProperties: false will reject any attribute key (e.g. "You can't add the flightId property ... because the unevaluatedProperties keyword value is set to false"). Use "componentOverrides": { "$": { "definition": "c/<yourComponent>" } } with no `attributes` key at all. If the user's prompt explicitly asks for attribute mappings to specific fields (e.g. "with attribute mappings for fieldA, fieldB") on an Apex-class CLT renderer/editor, do NOT comply literally — omit attributes from the root override anyway, and say so in your response (e.g. "Note: attribute mappings were omitted because the backing type is an Apex-class CLT, which has no properties block to bind against").
  • No shell metacharacters that trigger the Vibes safe-shell filter. In any Bash tool call emitted by this skill, do NOT use command substitution ($(…) or backticks), process substitution (<(…), >(…)), brace expansion ({a,b,c} or {1..N}), or eval / exec. Vibes forces manual approval on these patterns even under Bypass mode and stalls the eval. Emit separate commands (mkdir -p a && mkdir -p b) or print each value with its own command and reason about the output rather than capturing it in a shell variable.

Additional CLT Metaschema Validations

  • Org namespace validation: titles/descriptions and other string fields may be validated to ensure you are not using an org namespace in places that are disallowed.
  • Lightning type validation: CLTs are validated to prevent referencing internal namespaces (for example, disallowing types from internal namespaces like sfdc_cms where not permitted).
  • Object type validation: the CLT root is validated to ensure lightning:type is exactly lightning__objectType.

Primitive Types & Constraints

When you need the full list of supported primitive lightning:type identifiers, their constraints, and the allowed property-level keywords, read assets/primitive-types-and-constraints.md in this skill's directory.

Generation Workflow

  1. Confirm the CLT approach
  • If referencing Apex: capture the exact class reference (@apexClassType/namespace__ClassName$InnerClass).
  • If using standard primitives: list the fields, their Lightning primitive types, and which fields are required.
  1. Draft `schema.json`
  • DO NOT include `"$schema"` at the top
  • Start with the root object structure (required root fields).
  • Add properties using valid primitive lightning:type identifiers.
  • For nested-object properties, use CLT Reference pattern:
  • "lightning:type": "c__<CLTName>" to reference another CLT
  • The referenced CLT must be deployed to the org before the parent CLT.
  • For Apex-based nested objects: Use @apexClassType/... when structure exists server-side.
  • If the prompt explicitly requires true nested object output, prefer an Apex-based CLT (@apexClassType/...) for deploy-safe nested structures.
  • For arrays: follow the strict list rules (avoid items; avoid lightning:type on nested arrays).
  • Before deployment, verify exact lightning:type spellings (for example, use lightning__richTextType, not misspelled variants).
  1. (Optional) Draft `editor.json` (only if custom UI is required)
  • Supported shape: Top-level editor object with editor.componentOverrides and editor.layout.
  • Top-level editor object.
  • Use editor.componentOverrides for component overrides.
  • Use editor.layout for layout.
  • DEPRECATED: Do NOT use propertyRenderers or view — these are legacy keys. Always use componentOverrides and layout instead.
  • Root override pattern (most common for fully custom editing UI):
  • editor.componentOverrides["$"] = { "definition": "c/<yourEditorComponent>", "attributes": { ... } }
  • When passing schema data into a custom LWC, use attribute mapping with the {!$attrs.<name>} syntax: e.g. "attributes": { "myField": "{!$attrs.value}" } so the runtime binds schema values to your component's attributes.
  • CRITICAL: The <name> in {!$attrs.<name>} must be a property defined in your type schema. For example, if your schema has a property called temperature, use {!$attrs.temperature}, not {!$attrs.value} unless value is an actual property.
  • Property-level override pattern (for individual fields):
  • editor.componentOverrides["<propertyName>"] = { "definition": "es_property_editors/<...>" }
  • Valid editor components (examples): es_property_editors/inputText, es_property_editors/inputNumber, es_property_editors/inputRichText, es_property_editors/inputImage, es_property_editors/inputTextarea. Do not use es_property_editors/inputList.
  • Collection editor (for root-level lightning__listType properties): Use a collection-level override so the list is edited by a custom component: collection.editor.componentOverrides["$"] = { "definition": "c/<yourCollectionEditorComponent>" }. Alternatively, use editor.layout with lightning/propertyLayout and attributes.property = "<listPropertyName>" for default list editing.
  • Layout pattern:
  • editor.layout.definition = "lightning/verticalLayout"
  • editor.layout.children[*].definition = "lightning/propertyLayout" with attributes.property = "<propertyName>"
  • CRITICAL: lightning/propertyLayout only accepts the property attribute. Do NOT add label, title, or any other attributes — these will fail validation with additionalProperties: false errors.
  • Avoid known-invalid patterns:
  • Do not use es_property_editors/inputList.
  • Do not use itemSchema attributes.
  1. (Optional) Draft `renderer.json` (only if custom UI or widget rendition is required)
  • Supported shape: Top-level renderer object with renderer.componentOverrides and renderer.layout.
  • Top-level renderer object.
  • Use renderer.componentOverrides for component overrides.
  • Use renderer.layout for layout.
  • DEPRECATED: Do NOT use propertyRenderers or view — these are legacy keys. Always use componentOverrides and layout instead.
  • Widget rendition pattern (reference an existing WidgetBundle as the root renderer): the renderer file is a thin wrapper that points at the widget by developer name ("definition": "@widget/c/<widgetDeveloperName>") and maps CLT schema properties to widget attributes via {!$attrs.<schemaPropertyName>}. Do NOT duplicate the widget body inside renderer.json. See references/widget-rendition.md for the full shape, binding rules, and constraints. For the full Apex → Lightning Type → Widget pipeline, use the platform-lightning-type-widget-coordinate orchestrator instead of this skill.
  • Root override pattern (most common for fully custom rendering UI with a custom LWC):
  • renderer.componentOverrides["$"] = { "definition": "c/<yourRendererComponent>", "attributes": { ... } }
  • Use {!$attrs.<name>} in attribute mappings when binding schema data to custom renderer component attributes.
  • CRITICAL: Attribute mappings like {!$attrs.propertyName} must reference properties that actually exist in your type schema. Referencing non-existent properties will fail validation.
  • Type matching: Attribute values must match the expected type for the component. For example, if a component expects a string attribute, passing an integer will fail validation.
  • Property-level override pattern:
  • renderer.componentOverrides["<propertyName>"] = { "definition": "es_property_editors/outputText" | "es_property_editors/outputNumber" | "es_property_editors/outputImage" | ... }. Valid renderer components (examples): es_property_editors/outputText, es_property_editors/outputNumber, es_property_editors/outputImage. Avoid input-style components in the renderer.
  • Layout pattern for renderer:
  • renderer.layout.definition = "lightning/verticalLayout"
  • renderer.layout.children[*].definition = "lightning/propertyLayout" with attributes.property = "<propertyName>"
  • CRITICAL: Same as editor layouts, lightning/propertyLayout only accepts the property attribute. Do NOT add label, title, or any other attributes.
  • Collection renderer (for root-level lightning__listType properties): Use collection.renderer.componentOverrides["$"] = { "definition": "c/<yourListRendererComponent>" } or es_property_editors/genericListTypeRenderer to render the list.
  1. Place files in the correct bundle structure
  • lightningTypes/<TypeName>/schema.json
  • (Optional) lightningTypes/<TypeName>/lightningDesktopGenAi/editor.json
  • (Optional) lightningTypes/<TypeName>/lightningDesktopGenAi/renderer.json

For Gen AI / Copilot the standard path is lightningDesktopGenAi/. Other targets (e.g. Experience Builder, Mobile Copilot, Enhanced Web Chat) use different subfolders when supported: experienceBuilder/, lightningMobileGenAi/, enhancedWebChat/.

  • (Optional - for widget rendition only) lightningTypes/<TypeName>/renderer.json
  1. Configure custom LWC components (if using custom components)
  • CRITICAL: Custom LWC components referenced in editor/renderer configs MUST have the correct target configuration in their -meta.xml files:
  • For editor components (c/<componentName> used in editor.json): The LWC's -meta.xml file must include <target>lightning__AgentforceInput</target>
  • For renderer components (c/<componentName> used in renderer.json): The LWC's -meta.xml file must include <target>lightning__AgentforceOutput</target>
  • Without the correct target, deployment will fail with: Invalid target configuration. To use 'c/componentName' as a renderer/editor, your js-meta.xml file must include valid target 'lightning__AgentforceOutput/Input'.
  • Example -meta.xml for a renderer component:
xml
     <?xml version="1.0" encoding="UTF-8"?>
     <LightningComponentBundle xmlns="http://soap.sforce.com/2006/04/metadata">
         <apiVersion>60.0</apiVersion>
         <isExposed>true</isExposed>
         <targets>
             <target>lightning__AgentforceOutput</target>
         </targets>
     </LightningComponentBundle>

Common Deployment Errors

Error / SymptomLikely CauseFix
Schema validation fails due to unknown keywordunevaluatedProperties: false + disallowed keyword (commonly examples, items)Remove the offending keyword; keep schema minimal
Nested object validation failureOrg/channel validation rejects nested object typing in LightningTypeBundleUse CLT reference (c__<CLTName>) or Apex class types
Invalid CLT referenceReferenced CLT doesn't exist in org or incorrect syntaxDeploy the referenced CLT first; c__<CLTName> must match the referenced type’s `lightning:type` value / FQN / registered identifier, not title
Invalid or misspelled lightning:type (for example, lightning__richtextType instead of lightning__richTextType)Incorrect generated type nameCross-check all lightning:type values against supported type names and correct them before deployment
Array property rejectedUse of items (or lightning:type in nested arrays) rejected by validatorFor nested arrays: keep only type: "array". For root arrays: use minimal structure; remove items if rejected
Apex-based CLT rejectedExtra fields added (e.g., type, properties)Use only title, optional description, and lightning:type
Editor config rejectedUse of invalid patterns (es_property_editors/inputList, itemSchema) or unrecognized top-level keysUse editor.componentOverrides and editor.layout; keep config minimal
additionalProperties error on layout attributesAdding label or other attributes to lightning/propertyLayoutOnly use property attribute in lightning/propertyLayout. Remove label, title, or any other attributes
Invalid target configuration for custom LWCCustom LWC component's -meta.xml missing required target (lightning__AgentforceInput or lightning__AgentforceOutput)Add correct target to LWC's -meta.xml: use lightning__AgentforceInput for editors, lightning__AgentforceOutput for renderers
Attribute mapping doesn't exist in type schemaUsing {!$attrs.propertyName} where propertyName is not defined in schemaEnsure all attribute mappings reference actual properties in your type schema's properties section
unevaluatedProperties error on custom LWC renderer for an Apex class CLTRoot override attributes mapping used on an Apex class CLT, which has no properties block to validate againstRemove attributes entirely from the root override; use "componentOverrides": { "$": { "definition": "c/<component>" } } only
additionalProperties error with deprecated keysUsing propertyRenderers or view in editor/renderer configReplace deprecated propertyRenderers with componentOverrides and view with layout
Type mismatch in component attributesPassing wrong type for component attribute (e.g., integer instead of string)Ensure attribute values match the expected type defined by the component

Verification Checklist

  • [ ] Root schema has type: "object", title, lightning:type: "lightning__objectType", and unevaluatedProperties: false
  • [ ] Root schema does not include examples when strict validation is enabled
  • [ ] No nested object includes lightning:type: "lightning__objectType"
  • [ ] Arrays are defined minimally (especially nested arrays)
  • [ ] Only supported primitive lightning:type identifiers are used for leaf properties
  • [ ] Apex class CLTs contain only title/description and lightning:type: "@apexClassType/..."
  • [ ] Bundle structure and filenames match Lightning Types requirements
  • [ ] Editor config uses only allowed patterns (no es_property_editors/inputList, no itemSchema); use valid components (e.g. es_property_editors/inputText, es_property_editors/inputNumber) or custom c/ components
  • [ ] Renderer config uses output-style components (e.g. es_property_editors/outputText, es_property_editors/outputNumber) where applicable, not input editors
  • [ ] Layout configurations use lightning/propertyLayout with ONLY the property attribute (no label, title, or other attributes)
  • [ ] All attribute mappings ({!$attrs.propertyName}) reference properties that exist in the type schema
  • [ ] Custom LWC components have correct targets in -meta.xml: lightning__AgentforceInput for editors, lightning__AgentforceOutput for renderers
  • [ ] Root schema does NOT include "$schema" field
来自同一仓库

更多 Skills

全部 Skills
forcedotcom
社区

agentforce-d360-analyze

Data Cloud 360° view of a single Agentforce session. TRIGGER when user asks to trace, inspect, summarize, or describe a specific Agentforce session by session id (Agent Session UUID 019d… or MessagingSession id 0Mw…). Also triggers on session discovery — find/list/search sessions by time, agent, channel, outcome, or conversation text — when the user has no session id yet. DO NOT TRIGGER for design-time architecture questions (use agentforce-architecture-analyze instead) or for runtime perf/latency/SLO questions that require platform telemetry beyond Data Cloud.

安装量
1
GitHub Stars
972
最近更新
9月7日
forcedotcom
社区

agentforce-generate

Build, modify, audit, repair, optimize, debug, and deploy agents with Agentforce Agent Script. TRIGGER when: user creates, reviews, or changes .agent files or aiAuthoringBundle metadata; asks to fix AgentScript, audit an existing agent, run an AgentScript health check, common-pitfall review, or baseline-versus-candidate repair loop; changes a response, action, subagent, route, state flow, or Agent Spec; previews, debugs, deploys, publishes, or tests agents; uses sf agent generate/preview/publish/test; or manages Agentforce MCP servers, tools, assets, or authentication. DO NOT TRIGGER when: Apex, Flow, Prompt Template, Experience Cloud, or general Salesforce CLI work is unrelated to Agent Script; or the primary input is a production session or trace ID rather than an agent artifact.

安装量
1
GitHub Stars
972
最近更新
9月7日
forcedotcom
社区

platform-quick-deploy

Deploy validated metadata to a Production Salesforce org without re-running tests. TRIGGER when the user wants to deploy to production, says 'quick deploy', 'promote', 'ship to prod', or has just validated and wants to push the change live. REQUIRES a recent sf project deploy validate job ID (≤10 days old, ≤3 days for --use-most-recent). DO NOT TRIGGER for sandbox/scratch deploys (use platform-metadata-deploy) or unvalidated deploys (use platform-deploy-validate first).

安装量
1
GitHub Stars
972
最近更新
9月7日
forcedotcom
社区

agentforce-test

Write, run, and analyze structured test suites for Agentforce agents — functional AND security. TRIGGER when: user writes or modifies test spec YAML (AiEvaluationDefinition); runs sf agent test create, run, run-eval, or results commands; asks about test coverage strategy, metric selection, or custom evaluations; interprets test results or diagnoses test failures; asks about batch testing, regression suites, or CI/CD test integration; requests security testing, OWASP LLM Top 10, red-teaming, penetration testing, prompt-injection tests, a security grade, or a vulnerability assessment of an agent. DO NOT TRIGGER when: user creates, modifies, previews, or debugs .agent files (use agentforce-generate); deploys or publishes agents; writes Agent Script code; uses sf agent preview for development iteration; analyzes production session traces (use agentforce-observe); performs a static safety review of .agent file content (use agentforce-generate Section 15).

安装量
3
GitHub Stars
972
最近更新
9月7日