Home / agentforce
Agentforce skills (53)
Agentforce and Einstein: agents, topics, actions, prompt templates, grounding, guardrails and evaluation.
- agent-action-error-handlingDesign Invocable Apex actions that return deterministic, agent-friendly errors instead of surfacing raw exceptions to the LLM.
- agent-action-input-slot-extractionUse when designing how an Agentforce agent extracts structured input parameters (slots) from a user's natural-language utterance to invoke an action.
- agent-action-unit-testsApex test patterns for @InvocableMethod agent actions: per-reason-code branch coverage, bulk safety, callout mocking, deterministic assertions.
- agent-actionsDesigning or reviewing Agentforce actions: Flow actions, Apex invocable actions, prompt-template actions, action naming, input and output contracts, confirmation requirements, and safe error behavior.
- agent-channel-deploymentUse when deploying an Agentforce agent to a channel surface: Embedded Service web chat, Slack, Experience Cloud, Agent REST API, or Salesforce Mobile.
- agent-deployment-checklistCanonical go-live checklist for Agentforce deployments with rehearsed rollback and stakeholder sign-off records.
- agent-metric-dashboardsBuild the executive KPI dashboard for Agentforce: adoption, deflection, latency, cost, quality — KPI definitions, data sources, CRM Analytics lenses, alert thresholds.
- agent-rate-limit-strategyControl LLM spend and Apex governor exposure for high-traffic Agentforce agents via per-user token budgets and graceful fallback when the budget is exhausted.
- agent-script-dslAuthoring and managing Agentforce agent definitions using the declarative Agent Script DSL (.agent files) and associated metadata types, including the Agent Script language for the new Agentforce Builder (hybrid-reasoning -> logic vs | prompt instructions...
- agent-security-reviewPre-production security checklist for Agentforce deployments: agent run-as permission scope, grounding-source data classification, action write-scope, audit trail.
- agent-testing-and-evaluationUse when testing, evaluating, or building regression suites for Agentforce agents: conversation testing in Agent Builder, topic (now subagent) coverage and utterance testing, Testing API and AiEvaluationDefinition metadata, Agentforce DX CLI test runs (sf...
- agent-topic-designUse when designing or reviewing Agentforce topic (renamed subagent in April 2026) structure, including topic boundaries, instruction quality, handoff rules, out-of-scope behavior, and topic-selector strategy.
- agentexchange-publishingUse when an ISV or consulting partner is creating, pricing, publishing, or maintaining an AgentExchange listing through the Partner Console — covers the listing plan, the 5-step Listing Builder workflow (Fill in the Basics, Set Pricing, Add Details, Link Your...
- agentforce-agent-creationUse when creating, configuring, auditing, or troubleshooting an Agentforce agent end-to-end: agent definition, agent user setup, channel assignment, system instructions, activation, and lifecycle management.
- agentforce-agent-handoff-patternsUse when designing how an Agentforce agent transfers the conversation to a human agent (Omni-Channel), to another bot/agent, or to an alternate workflow — including context package, deflection, escalation triggers, and user messaging.
- agentforce-cost-optimizationUse when Agentforce run costs are climbing, you need to forecast scale, or you want to reduce tokens per conversation without hurting quality.
- agentforce-custom-channel-devUse this skill when building custom channel integrations with the Agentforce Agent API or BYOC (Bring Your Own Channel) for CCaaS — covering session lifecycle management, webhook handling, externalSessionKey design, sequenceId sequencing, BYOC Interaction API...
- agentforce-custom-lightning-typesUse when overriding the default UI of an Agentforce agent action's Apex input or output with your own Lightning web components via a LightningTypeBundle (schema.json + editor.json/renderer.json, lightning__AgentforceInput / lightning__AgentforceOutput...
- agentforce-eval-harnessAuthor and run offline evals for Agentforce agents: fixture format, scoring rubrics, hallucination checks, regression baselines, CI integration, prompt-change safety.
- agentforce-gridUse when designing or reasoning about an Agentforce Grid worksheet — the spreadsheet-like Agentforce workspace where rows are jobs and columns are sequential Data / AI / Action steps that process left to right — to run bulk record updates, generate insights...
- agentforce-guardrailsUse this skill when designing, auditing, or troubleshooting behavioral boundaries for Agentforce agents — including topic (now subagent) Scope fields, agent-level system instructions, topic/action filters, the Escalation topic, restricted topics, and...
- agentforce-in-slackUse when configuring Slack-specific Agentforce capabilities AFTER the basic Slack deployment is complete: enabling Slack-native actions, managing public vs.
- agentforce-multi-turn-patternsDesign Agentforce conversations that span multiple turns without losing context: session variable scoping, conversation memory, clarifying-question patterns, topic-to-topic (now subagent) handoff, and the right abstractions for accumulating state across turns.
- agentforce-observabilityUse when monitoring Agentforce agent sessions, analyzing conversation logs, measuring deflection rates, or diagnosing agent performance issues.
- agentforce-persona-designUse when defining or refining the tone, voice, and behavioral personality of an Agentforce agent: system instruction encoding, brand voice alignment, adaptive response formats, multi-persona strategies.
- agentforce-pii-redactionRedact PII in your own code before it reaches Agentforce prompts, models, and logs.
- agentforce-production-readiness-checklistAn Agentforce agent is moving from build or sandbox to live end-user traffic and the team needs a comprehensive readiness gate: coverage testing, Trust Layer config, guardrails, cost telemetry, observability, rate limits, permissions, rollout strategy...
- agentforce-prompt-versioningVersion Prompt Templates and agent topic (now subagent) prompts: source-control shape, change review, model-version pinning, A/B, and rollback.
- agentforce-sales-ai-setupSetup and configuration of Einstein for Sales AI features: Opportunity Scoring, Pipeline Inspection AI insights, Einstein email insights and composition, and Forecasting AI — prerequisites, license checks, feature sequencing, data readiness validation.
- agentforce-service-ai-setupVerify prerequisites, license entitlements, and org readiness before enabling Einstein for Service AI features: Case Classification, Article Recommendations, Reply Recommendations, and Work Summaries.
- agentforce-testing-strategyDesign the Agentforce test pyramid: topic (now subagent) coverage, action unit tests, deterministic golden sets, adversarial prompts, and regression harness.
- agentforce-tool-use-patternsPick the right tool shape for each agent action: Apex invocable vs Flow action vs External Service vs Prompt Template vs Data Cloud retrieval.
- custom-agent-actions-apexBuilding custom Apex-based actions for Agentforce agents: designing @InvocableMethod classes for Atlas Reasoning Engine invocation, defining input/output schema, handling errors, and managing security context.
- data-cloud-grounding-for-agentforceGrounding an Agentforce agent with Data Cloud retrievers, DMO selection, chunking, and freshness windows.
- data-cloud-vector-search-devDeveloping Data Cloud vector search: configuring search indexes, selecting chunking strategies (Easy Setup vs Advanced Setup), generating embeddings via the Salesforce-managed model, calling the Query API with a Data Cloud access token, and wiring retrieval...
- einstein-bots-to-agentforce-migrationUse when migrating an existing Einstein Bot (legacy or Enhanced) to Agentforce: feature mapping, conversation design translation, cutover planning, hybrid bot/agent architecture, and context handoff.
- einstein-copilot-for-salesSales-specific AI features in Sales Cloud: Einstein Opportunity Scoring setup and optimization, Einstein Activity Capture configuration, AI email generation, Pipeline Inspection AI insights, and Einstein Relationship Insights.
- einstein-copilot-for-serviceService-specific AI features in Service Cloud: Case Classification setup and optimization, Article Recommendations configuration, Reply Recommendations, Work Summary (After-Visit Summary), Service Replies with Einstein, Auto-Routing, and Einstein Conversation...
- einstein-discovery-developmentIntegrating Einstein Discovery predictions into Salesforce apps, automating bulk scoring jobs, deploying stories as prediction definitions, managing models via API, or querying prediction history.
- einstein-next-best-actionGuide practitioners through building Einstein Next Best Action strategies using Flow Builder, configuring Recommendation records, and surfacing recommendations via the Actions & Recommendations Lightning component.
- einstein-prediction-builderEinstein Prediction Builder for creating custom binary classification predictions on Salesforce objects: field selection, training data requirements, model activation, score embedding, and monitoring.
- einstein-search-personalizationEinstein Search personalization: configure search result ranking, promoted results, searchable objects, and Natural Language Search (NLS) for Lightning Experience.
- einstein-trust-layerConfigure, audit, or troubleshoot Einstein Trust Layer security controls for generative AI features including Agentforce, Einstein Copilot, and Prompt Builder.
- employee-hr-service-agent-rolloutUse when an org is rolling out an Agentforce-based HR / Employee Service agent for self-service workflows like leave requests, benefits questions, onboarding tasks, and time-off balance lookups.
- mcp-tool-definition-apexUse this skill to implement custom Apex MCP tool classes by extending McpToolDefinition from the salesforce-mcp-lib package.
- model-builder-and-byollmUse when configuring Model Builder in Salesforce to register external LLMs or select standard models for Agentforce and Einstein features.
- prompt-builder-templatesUse when creating, reviewing, or troubleshooting Prompt Builder templates (Field Generation, Record Summary, Sales Email, or Flex types), including grounding with merge fields, Flow, or Apex.
- prompt-injection-defenseRed-team an Agentforce agent against prompt-injection and jailbreak attacks; codify adversarial test cases and guardrails, scoped to the agent boundary rather than general application-security review.
- prompt-template-versioningLifecycle management for Prompt Builder templates: version, test, promote, roll back via CMDT-backed bindings.
- rag-patterns-in-salesforceGrounding Agentforce agents with retrieved knowledge using Data Cloud vector search: RAG pipeline design, vector search index configuration, chunking and embedding strategy, and how retrieved context flows through the Einstein Trust Layer into prompts.
- sales-coach-agent-rolloutUse when an admin or RevOps team is rolling out the out-of-the-box Sales Coach agent (the Agentforce template that role-plays opportunity-stage conversations with reps for Discovery, Needs Analysis, Qualification, Proposal/Pricing, and Negotiation/Review).
- salesforce-mcp-server-setupUse this skill to install and configure the salesforce-mcp-lib Apex package and npm stdio proxy so that an MCP client (Claude Desktop, Cursor, ChatGPT) can call Salesforce org data and logic via the Model Context Protocol.
- sf-to-llm-data-pipelinesUse this skill when extracting Salesforce data for consumption by external LLMs or vector stores outside the Salesforce ecosystem — covering Bulk API v2 extraction patterns, PII scrubbing before transmission, chunking and embedding pipelines that run in...