@salesforce/afv-skills 1.37.0 → 1.38.0

package/skills/agentforce-generate/assets/agent-spec-template.md

@@ -101,8 +101,12 @@ For each action, decide how it gets invoked:
 **Modes:**
 - **`run @actions.X` in `instructions: ->`** — Deterministic. Fires every time the condition holds. Use only when regulation, authorization, confirmed consequence, external ordering, or a reproduced trace failure requires it.
 - **Planner slot-fill (`with param = ...` in `reasoning.actions:`)** — LLM decides when to invoke. Use for user-initiated actions where the LLM should judge intent.
-- **`@utils.setVariables`** — LLM captures a value and ends the turn. Use only
-  when a named later deterministic consumer needs the exact value and it cannot
+- **`@utils.setVariables`** — LLM captures a value through a model-selected
+  tool call. The call updates state but does not itself define a turn boundary.
+  Any later reasoning or response follows the runtime's normal tool-loop
+  behavior; do not use this action to force either an end or another
+  iteration. Prompt text asking for the call does not execute it. Use only when
+  a named later deterministic consumer needs the exact value and it cannot
   remain action-local. Do not use it to mirror conversational history.
 
 ## Deterministic Controls (When Needed)

package/skills/agentforce-generate/assets/agents/order-service.agent

@@ -102,11 +102,13 @@ subagent verification:
     reasoning:
         instructions: ->
             if @variables.customer_verified == True:
-                | Welcome back! How can I help you today?
+                | Welcome the verified customer and ask how you can help with
+                  their order.
 
             if @variables.customer_verified == False:
-                | To help you with your order, I need to verify your identity.
-                | What is the email address associated with your account?
+                | Explain that identity verification is required before order
+                  assistance. Ask for the email address associated with the
+                  account.
 
         actions:
             verify: @actions.verify_customer
@@ -151,12 +153,14 @@ subagent order_status:
     reasoning:
         instructions: ->
             if @variables.order_status != "":
-                | Order {!@variables.verified_order_id} status: {!@variables.order_status}
-                | Would you like to track your shipment or initiate a return?
+                | Report order {!@variables.verified_order_id} with exact status
+                  {!@variables.order_status}. Ask whether the customer wants to
+                  track the shipment or initiate a return.
 
             if @variables.order_status == "":
-                | What is your order number? You can find it in your confirmation email.
-                | Use the find_order action to look up order details.
+                | Ask for the order number and mention that it appears in the
+                  confirmation email. Use the find_order action after the user
+                  supplies it.
 
         actions:
             find_order: @actions.lookup_order
@@ -240,13 +244,13 @@ subagent returns:
     reasoning:
         instructions: ->
             if @variables.return_initiated == True:
-                | Your return has been initiated!
-                | Return label: {!@variables.return_label_url}
+                | Confirm that the return was initiated and provide the exact
+                  return-label URL: {!@variables.return_label_url}
 
             if @variables.return_initiated == False:
-                | I can help you with a return for order {!@variables.verified_order_id}.
-                | What is the reason for your return?
-                | Use the process_return action to start the return.
+                | Explain that you can help return order
+                  {!@variables.verified_order_id}. Ask for the reason, then use
+                  the process_return action to start the return.
 
         actions:
             process_return: @actions.initiate_return

package/skills/agentforce-generate/assets/agents/production-faq.agent

@@ -65,9 +65,9 @@ subagent faq_handler:
     reasoning:
         instructions: ->
             | Answer the user's question based on your knowledge.
-            | Be helpful, accurate, and concise. Keep responses under 3-4 sentences.
-            | If the question is outside your knowledge, acknowledge it and offer alternatives.
-            | Use the latest surviving conversation turns for follow-up context.
+              Be helpful, accurate, and concise. Keep responses under 3-4 sentences.
+              If the question is outside your knowledge, acknowledge it and offer alternatives.
+              Use the latest surviving conversation turns for follow-up context.
               Do not offer escalation merely because the user has asked several
               questions.
 
@@ -86,7 +86,7 @@ subagent farewell:
     reasoning:
         instructions: ->
             | Thank the user for their questions.
-            | Let them know they can return anytime for more help.
+              Let them know they can return anytime for more help.
 
 subagent escalation:
     label: "Escalation"

package/skills/agentforce-generate/assets/agents/router-first.agent

@@ -31,13 +31,13 @@ start_agent agent_router:
     label: "Request Router"
     description: "Routes the user's latest request without answering it"
 
+    model_config:
+        model: "model://sfdc_ai__DefaultEinsteinHyperClassifier"
+
     reasoning:
         instructions: ->
-            | Route only the user's latest request:
-            | - order status or tracking: order help;
-            | - return eligibility or an existing return: return help;
-            | - general questions: support.
-            | Do not answer the underlying request in this router.
+            | Route only the user's latest request. Choose exactly one route,
+              and do not answer the underlying request in this router.
         actions:
             check_order: @utils.transition to @subagent.orders
                 description: "Handle order status or tracking"

package/skills/agentforce-generate/assets/agents/template-single-subagent.agent

@@ -53,10 +53,10 @@ start_agent main:
     reasoning:
         instructions: ->
             | Handle only the focused objective described for this agent.
-            | Use the task action when the user supplies the required input.
-            | If required input is missing, ask one concise clarifying question.
-            | If the request is outside scope, redirect to the focused objective.
-            | If the user explicitly asks for a human, transfer without also
+              Use the task action when the user supplies the required input.
+              If required input is missing, ask one concise clarifying question.
+              If the request is outside scope, redirect to the focused objective.
+              If the user explicitly asks for a human, transfer without also
               attempting the underlying task.
 
         actions:

package/skills/agentforce-generate/assets/agents/verification-gate.agent

@@ -93,14 +93,17 @@ subagent identity_verification:
     reasoning:
         instructions: ->
             if @variables.failed_attempts >= 3:
-                | Too many failed attempts. Transferring to a human agent.
+                | Briefly explain that repeated verification attempts require
+                  a human handoff.
                 transition to @subagent.escalation
 
             if @variables.customer_verified == True:
-                | Identity verified! How can I help you today?
+                | Confirm successful identity verification and ask how you can
+                  help.
 
             if @variables.customer_verified == False:
-                | Please verify your identity by confirming your email address.
+                | Ask the user to verify their identity by confirming their
+                  email address.
 
         actions:
             check_email: @actions.verify_email
@@ -152,9 +155,8 @@ subagent account_management:
             if @variables.customer_verified == False:
                 transition to @subagent.identity_verification
 
-            | Welcome to account management.
-            | What would you like to do with your account?
-            | Use the update actions to make changes.
+            | Welcome the verified customer to account management and ask what
+              they want to change. Use the matching update action.
 
         actions:
             change_email: @actions.update_email

package/skills/agentforce-generate/assets/agents/voice-knowledge-grounded.agent

@@ -76,9 +76,9 @@ start_agent agent_router:
     reasoning:
         instructions: ->
             | Listen to what the caller needs and route them to the right topic.
-            | For questions about products, policies, procedures, or troubleshooting, go to knowledge answers.
-            | If the caller asks to speak with a person or you cannot help, escalate.
-            | Do NOT answer questions directly — route to the appropriate topic.
+              For questions about products, policies, procedures, or troubleshooting, go to knowledge answers.
+              If the caller asks to speak with a person or you cannot help, escalate.
+              Do NOT answer questions directly — route to the appropriate topic.
         actions:
             go_knowledge: @utils.transition to @subagent.knowledge_answers
                 description: "Route to knowledge answers for product, policy, or how-to questions"
@@ -90,15 +90,15 @@ subagent knowledge_answers:
     reasoning:
         instructions: ->
             | If the question is unclear, ask one short clarifying question first.
-            | For every substantive question, call AnswerQuestionsWithKnowledge
+              For every substantive question, call AnswerQuestionsWithKnowledge
               before answering.
-            | Answer only from the returned knowledge summary, using one or two
+              Answer only from the returned knowledge summary, using one or two
               spoken sentences.
-            | If the summary is empty, say the knowledge base has no answer and
+              If the summary is empty, say the knowledge base has no answer and
               use {!@actions.go_escalation}.
-            | Never speak URLs, citations, or list formatting. Offer to send
+              Never speak URLs, citations, or list formatting. Offer to send
               returned links instead.
-            | After answering, ask if there's anything else you can help with.
+              After answering, ask if there's anything else you can help with.
         actions:
             AnswerQuestionsWithKnowledge: @actions.AnswerQuestionsWithKnowledge
                 with query = ...
@@ -159,7 +159,7 @@ subagent escalation:
     reasoning:
         instructions: ->
             | The caller needs to speak with a human agent. Use {!@actions.escalate_to_human} to transfer them.
-            | Before transferring, briefly let them know you're connecting them.
+              Before transferring, briefly let them know you're connecting them.
         actions:
             escalate_to_human: @utils.escalate
                 description: "Transfer the caller to a live agent"

package/skills/agentforce-generate/assets/agents/voice-service-agent.agent

@@ -54,9 +54,9 @@ start_agent agent_router:
     reasoning:
         instructions: ->
             | Listen to what the caller needs and route them to the right topic.
-            | For order questions (tracking, status, delivery) go to order status.
-            | If the caller asks to speak with a person or you cannot help, escalate.
-            | Do NOT answer questions directly — route to the appropriate topic.
+              For order questions (tracking, status, delivery) go to order status.
+              If the caller asks to speak with a person or you cannot help, escalate.
+              Do NOT answer questions directly — route to the appropriate topic.
         actions:
             go_order_status: @utils.transition to @subagent.order_status
                 description: "Route to order status topic for tracking and delivery questions"
@@ -68,9 +68,9 @@ subagent order_status:
     reasoning:
         instructions: ->
             | Help the caller check their order status. Ask for their order number if not provided.
-            | Use {!@actions.get_order_status} to look up the order. Read back the status clearly and concisely.
-            | NEVER guess order details — only report what the action returns.
-            | After answering, ask if there's anything else you can help with.
+              Use {!@actions.get_order_status} to look up the order. Read back the status clearly and concisely.
+              NEVER guess order details — only report what the action returns.
+              After answering, ask if there's anything else you can help with.
         actions:
             get_order_status: @actions.get_order_status
                 description: "Look up order status by order number"
@@ -95,7 +95,7 @@ subagent escalation:
     reasoning:
         instructions: ->
             | The caller needs to speak with a human agent. Use {!@actions.escalate_to_human} to transfer them.
-            | Before transferring, briefly let them know you're connecting them.
+              Before transferring, briefly let them know you're connecting them.
         actions:
             escalate_to_human: @utils.escalate
                 description: "Transfer the caller to a live agent"

package/skills/agentforce-generate/assets/patterns/README.md

@@ -178,11 +178,11 @@ reasoning:
    instructions: ->
       if @variables.customer_tier == "vip":
          | PRIORITY CUSTOMER - Provide white-glove service.
-         | You have authority to offer 20% discounts.
+           You have authority to offer 20% discounts.
 
       if @variables.business_hours == False:
-         | We are outside business hours.
-         | Complex issues should be logged for follow-up.
+         | Explain that support is outside business hours and log complex
+           issues for follow-up.
 
       | Respond to the customer's inquiry.
 ```

package/skills/agentforce-generate/assets/patterns/action-callbacks.agent

@@ -81,9 +81,9 @@ start_agent shipment_status:
     reasoning:
         instructions: ->
             | Ask for a tracking number when none is present in the conversation.
-            | Use the shipment lookup for a supplied tracking number.
-            | Answer from the normalized result. If it says the shipment was
-            | not found or delivery is unavailable, say that directly.
+              Use the shipment lookup for a supplied tracking number.
+              Answer from the normalized result. If it says the shipment was
+              not found or delivery is unavailable, say that directly.
 
         actions:
             # The callback runs after the lookup returns normally. Every value
@@ -104,5 +104,5 @@ start_agent shipment_status:
 #         run @actions.third
 #
 # If a third deterministic step is required, redesign the backing automation
-# as one atomic action or use a supported lifecycle/sequence with explicit
-# inputs and failure semantics.
+# as one action that owns the complete sequence or use a supported lifecycle
+# with explicit inputs and failure semantics.

package/skills/agentforce-generate/assets/patterns/advanced-input-bindings.agent

@@ -106,14 +106,12 @@ start_agent order_processing:
     reasoning:
         instructions: ->
             | Help the customer process their order.
-            |
-            | INPUT BINDING EXAMPLES:
-            | 1. Slot filling (...) - LLM extracts from conversation
-            | 2. Fixed values - Always use a constant
-            | 3. Stored state - Use the available value
-            | 4. Output chaining - Use results from previous action
-            |
-            | Ask for order details and process appropriately.
+              INPUT BINDING EXAMPLES:
+              1. Slot filling (...) - LLM extracts from conversation
+              2. Fixed values - Always use a constant
+              3. Stored state - Use the available value
+              4. Output chaining - Use results from previous action
+              Ask for order details and process appropriately.
 
         actions:
             # Persist only a canonical action output that later bindings consume.

package/skills/agentforce-generate/assets/patterns/bidirectional-routing.agent

@@ -52,13 +52,11 @@ start_agent main_hub:
     reasoning:
         instructions: ->
             | You are the main coordinator.
-            | When user needs specialized help:
-            | - For pricing questions, consult the pricing specialist
-            | - For technical issues, consult the technical specialist
-            |
-            | After specialist returns, communicate their findings to the user.
-            |
-            | Current specialist result: {!@variables.specialist_result}
+              When user needs specialized help:
+              - For pricing questions, consult the pricing specialist
+              - For technical issues, consult the technical specialist
+              After specialist returns, communicate their findings to the user.
+              Current specialist result: {!@variables.specialist_result}
         actions:
             consult_pricing: @utils.transition to @subagent.pricing_specialist
 
@@ -90,9 +88,9 @@ subagent pricing_specialist:
     reasoning:
         instructions: ->
             | You are the pricing specialist.
-            | Focus ONLY on pricing questions.
-            | Calculate the price and prepare your findings.
-            | When done, return to the main hub with your results.
+              Focus ONLY on pricing questions.
+              Calculate the price and prepare your findings.
+              When done, return to the main hub with your results.
         actions:
             calculate: @actions.calculate_price
                 with product_id=...
@@ -123,9 +121,9 @@ subagent technical_specialist:
     reasoning:
         instructions: ->
             | You are the technical specialist.
-            | Focus ONLY on technical issues.
-            | Diagnose the problem and prepare your findings.
-            | When done, return to the main hub with your results.
+              Focus ONLY on technical issues.
+              Diagnose the problem and prepare your findings.
+              When done, return to the main hub with your results.
         actions:
             diagnose: @actions.diagnose_issue
                 with symptoms=...

package/skills/agentforce-generate/assets/patterns/critical-input-collection.agent

@@ -110,31 +110,27 @@ start_agent input_collector:
         # Tell the LLM its PRIMARY GOAL is to collect the input
         instructions: ->
             | YOUR PRIMARY GOAL: Collect the account ID from the user.
-            |
-            | CURRENT STATE:
+              CURRENT STATE:
             if @variables.account_id == "":
                 | ⚠️ Account ID NOT YET COLLECTED
-                | ASK the user for their Salesforce Account ID.
-                | The ID should be 18 characters and start with "001".
-                |
-                | Example prompt: "Please provide the Account ID you'd like me to research."
+                  ASK the user for their Salesforce Account ID.
+                  The ID should be 18 characters and start with "001".
+                  Example prompt: "Please provide the Account ID you'd like me to research."
 
             if @variables.account_id != "" and @variables.account_id_validated == False:
                 | 🔄 Account ID received: {!@variables.account_id}
-                | Attempting validation...
-                |
-                | Use {!@actions.capture_account_id} to validate this ID.
+                  Attempting validation...
+                  Use {!@actions.capture_account_id} to validate this ID.
 
             if @variables.account_id_validated == True:
                 | ✅ Account ID validated: {!@variables.account_id}
-                | Account Name: {!@variables.account_name}
-                |
-                | Continue to the research workflow.
+                  Account Name: {!@variables.account_name}
+                  Continue to the research workflow.
 
             if @variables.collection_attempts > 2 and @variables.account_id_validated == False:
                 | ❌ Multiple validation failures.
-                | Ask the user to verify their Account ID is correct.
-                | Suggest they check Salesforce for the correct ID format.
+                  Ask the user to verify their Account ID is correct.
+                  Suggest they check Salesforce for the correct ID format.
 
         actions:
             # ★ PATTERN 3: Single-Use Pattern
@@ -178,12 +174,11 @@ subagent research:
     reasoning:
         instructions: ->
             | Researching account: {!@variables.account_name} ({!@variables.account_id})
-            |
             if @variables.research_summary == "":
                 | Use {!@actions.research_account} to analyze this account.
             if @variables.research_summary != "":
                 | Research complete!
-                | {!@variables.research_summary}
+                  {!@variables.research_summary}
 
         actions:
             # ★ PATTERN 4: Null Guard - Uses variable binding, NOT slot filling

package/skills/agentforce-generate/assets/patterns/lifecycle-events.agent

@@ -97,9 +97,8 @@ start_agent conversation:
     reasoning:
         instructions: ->
             | Current user context:
-            | {!@variables.current_context}
-            |
-            | Respond helpfully using the refreshed context above.
+              {!@variables.current_context}
+              Respond helpfully using the refreshed context above.
         actions:
             end_conversation: @utils.transition to @subagent.farewell
 

package/skills/agentforce-generate/assets/patterns/llm-controlled-actions.agent

@@ -97,13 +97,12 @@ start_agent catalog_assistance:
     reasoning:
         instructions: ->
             | Help with the user's current public-catalog request.
-            | The service notice refreshed for this turn is:
-            | {!@variables.service_notice}
-            |
-            | Mention that notice only when it is relevant.
-            | Use catalog_search for product discovery.
-            | Use availability_lookup only for current availability.
-            | If a required lookup value is absent, ask for that value instead
+              The service notice refreshed for this turn is:
+              {!@variables.service_notice}
+              Mention that notice only when it is relevant.
+              Use catalog_search for product discovery.
+              Use availability_lookup only for current availability.
+              If a required lookup value is absent, ask for that value instead
               of invoking an action with a guess.
 
         # Model-chosen: these read-only actions are available to reasoning, but

package/skills/agentforce-generate/assets/patterns/open-gate-routing.agent

@@ -61,9 +61,9 @@ start_agent agent_router:
     reasoning:
         instructions: ->
             | Route only the user's latest request:
-            | - order status, returns, or shipping: protected order help;
-            | - account settings or profile changes: protected account help;
-            | - verification details for a pending protected request:
+              - order status, returns, or shipping: protected order help;
+              - account settings or profile changes: protected account help;
+              - verification details for a pending protected request:
               authentication;
             | - cancellation, a changed subject, or a general question:
               general inquiry.

package/skills/agentforce-generate/assets/patterns/prompt-template-action.agent

@@ -55,10 +55,9 @@ start_agent agent_router:
     reasoning:
         instructions: ->
             | Ask the user what type of content they'd like to generate:
-            | 1. Personalized daily schedule
-            | 2. Professional email
-            |
-            | Route to the appropriate request handler.
+              1. Personalized daily schedule
+              2. Professional email
+              Route to the appropriate request handler.
         actions:
             go_schedule: @utils.transition to @subagent.schedule_generation
             go_email: @utils.transition to @subagent.email_generation
@@ -95,14 +94,12 @@ subagent schedule_generation:
     reasoning:
         instructions: ->
             | Help the user create a personalized daily schedule.
-            |
-            | 1. Ask for their email (required)
-            | 2. Ask for their timezone (optional, defaults to Pacific)
-            | 3. Generate the schedule using the AI template
-            | 4. Present the generated schedule
-            |
-            | The schedule will include morning routine, work blocks,
-            | breaks, and evening wind-down based on preferences.
+              1. Ask for their email (required)
+              2. Ask for their timezone (optional, defaults to Pacific)
+              3. Generate the schedule using the AI template
+              4. Present the generated schedule
+              The schedule will include morning routine, work blocks,
+              breaks, and evening wind-down based on preferences.
 
         actions:
             create_schedule: @actions.Generate_Personalized_Schedule
@@ -140,13 +137,11 @@ subagent email_generation:
     reasoning:
         instructions: ->
             | Help the user draft a professional email.
-            |
-            | Collect:
-            | 1. Recipient's name (required)
-            | 2. Email topic/purpose (required)
-            | 3. Desired tone: formal, friendly, or urgent (optional)
-            |
-            | Generate the email and present it for review.
+              Collect:
+              1. Recipient's name (required)
+              2. Email topic/purpose (required)
+              3. Desired tone: formal, friendly, or urgent (optional)
+              Generate the email and present it for review.
 
         actions:
             create_email: @actions.Generate_Professional_Email

package/skills/agentforce-generate/assets/patterns/system-instruction-overrides.agent

@@ -115,10 +115,10 @@ subagent orders:
             # ★ Tier-specific instructions carry through to subagents
             if @variables.customer_tier == "vip":
                 | This is a VIP customer. Expedite all order requests.
-                | Offer free shipping upgrades proactively.
+                  Offer free shipping upgrades proactively.
 
             | Help the customer with their order inquiry.
-            | Look up order status, process changes, or handle returns.
+              Look up order status, process changes, or handle returns.
 
         actions:
             back: @utils.transition to @subagent.agent_router
@@ -132,7 +132,7 @@ subagent billing:
             # ★ Different authority based on tier
             if @variables.customer_tier == "vip":
                 | You can waive fees up to $100 for VIP customers.
-                | Proactively offer payment plan options.
+                  Proactively offer payment plan options.
             else if @variables.customer_tier == "premium":
                 | You can waive fees up to $25 for premium customers.
             else if @variables.customer_tier == "standard":
@@ -154,7 +154,7 @@ subagent support:
         instructions: ->
             if @variables.business_hours == False:
                 | Technical support is limited outside business hours.
-                | Log the issue for follow-up and provide self-service resources.
+                  Log the issue for follow-up and provide self-service resources.
 
             if @variables.business_hours == True:
                 | Full technical support available. Troubleshoot thoroughly.
@@ -184,10 +184,8 @@ subagent formal_mode:
 
     reasoning:
         instructions: ->
-            | [Formal Mode Engaged]
-            |
-            | Good day. How may I be of assistance?
-            | I am prepared to address your inquiry with the utmost professionalism.
+            | Greet the user in the formal style defined by the system
+              instructions and ask what business matter they need help with.
 
         actions:
             back: @utils.transition to @subagent.agent_router
@@ -206,12 +204,8 @@ subagent creative_mode:
 
     reasoning:
         instructions: ->
-            | 🎨 [Creative Mode Activated!]
-            |
-            | Hey there, creative spirit! Ready to explore some ideas together?
-            | Think of me as your brainstorming buddy - no idea is too wild!
-            |
-            | What shall we dream up today?
+            | Greet the user in the playful, imaginative style defined by the
+              system instructions and ask what they want to create or explore.
 
         actions:
             back: @utils.transition to @subagent.agent_router
@@ -230,12 +224,9 @@ subagent technical_expert:
 
     reasoning:
         instructions: ->
-            | [Technical Expert Mode]
-            |
-            | I'm ready to dive deep into technical details.
-            | Feel free to use technical terminology - I'll match your level.
-            |
-            | What technical challenge are we solving?
+            | Greet the user as a technical expert, match their apparent level
+              of technical detail, and ask what technical problem they need to
+              solve.
 
         actions:
             back: @utils.transition to @subagent.agent_router

package/skills/agentforce-generate/references/actions-reference.md

@@ -155,7 +155,7 @@ subagent order_management:
    reasoning:
       instructions: ->
          | Help the customer with their order.
-         | When they ask about an order, look it up.
+           When they ask about an order, look it up.
       actions:
          # LLM automatically selects this when appropriate
          lookup: @actions.get_order
@@ -180,7 +180,7 @@ You can also reference action definitions inside `instructions:` using `{!@actio
 reasoning:
    instructions: ->
       | To look up an order, use {!@actions.get_order}.
-      | To check shipping status, use {!@actions.track_shipment}.
+        To check shipping status, use {!@actions.track_shipment}.
 ```
 
 > See [patterns-by-requirement.md](patterns-by-requirement.md) and