Use when designing, mapping, or troubleshooting the end-to-end quote-to-cash process in orgs running Salesforce CPQ (managed package) or Revenue Cloud — covering the full object chain from SBQQ__Quote__c through Contract to blng__Invoice__c, approval routing via Advanced Approvals (sbaa__), billing schedule generation, and order activation. Trigger keywords: CPQ quote, SBQQ, revenue cloud billing, Advanced Approvals, subscription, blng invoice, contract pivot. NOT for standard Sales Cloud quote-to-cash or implementation of individual CPQ pricing rules, discount schedules, or guided selling configuration — use the quote-to-cash-requirements skill for standard objects.

Use when designing, auditing, or simplifying Record Types and Page Layouts. Triggers: 'record type', 'page layout', 'different picklist values', 'different fields per team', 'dynamic forms'. NOT for sharing rules or FLS — record types don't control data access.

Configure and manage NPSP Enhanced Recurring Donations (ERD): enable ERD mode, define schedule objects, configure installment behavior, set status automation thresholds, and interpret the Upcoming Installments UI. NOT for legacy recurring donations (pre-March 2021 model), one-time Opportunity creation, or custom payment gateway integrations beyond native NPSP.

Guide practitioners through opening, classifying, and escalating support cases with Salesforce Technical Support via the Help portal, including choosing the correct severity level, engaging Premier Success resources, using the Escalate to Technical Support Management path, and tracking incidents on the Trust site. NOT for configuring Salesforce Case Escalation Rules (declarative platform automation), Entitlement Management or SLA milestones, or building customer-facing support processes inside an org.

Use when designing, configuring, distributing, or troubleshooting Salesforce Surveys and Feedback Management. Triggers: 'create a survey', 'NPS score', 'survey invitation', 'survey response report', 'customer feedback form', 'guest user survey access'. NOT for custom-built LWC form components or third-party survey tools like SurveyMonkey or Qualtrics.

Use this skill when designing the UX and content strategy for a Salesforce-powered self-service portal or help center — covering pre-deflection article surfacing, Help Center search UX, friction-calibrated case submission forms, community peer support layers, and deflection measurement. Trigger keywords: design self-service portal, case deflection strategy, help center UX design, reduce support volume with self-service, knowledge base search experience. NOT for Experience Cloud technical setup or component configuration. NOT for knowledge article authoring or article lifecycle management.

Use this skill when setting up Service Cloud Voice with Amazon Connect — provisioning the contact center, configuring phone numbers, enabling real-time transcription, and configuring After Conversation Work Time. NOT for CTI adapter development, Open CTI customization, or custom Amazon Connect Lambda development outside the guided wizard.

Use this skill to configure a Lightning Service Console app in Salesforce — setting Console Navigation (split view), defining workspace tabs and subtabs, configuring the utility bar with Omni-Channel, Macros, and History, creating Quick Text entries, setting up keyboard shortcuts, and defining navigation rules per object. Trigger keywords: Service Console, console app, workspace tabs, subtabs, utility bar macros, Omni-Channel utility, split view, Quick Text, console navigation rules, keyboard shortcuts service console. NOT for generic Lightning app creation (use app-and-tab-configuration), NOT for Omni-Channel routing configuration (use omni-channel-routing), NOT for CTI adapter installation (use open-cti-setup), NOT for Einstein Bot or Messaging setup.

Use when designing, auditing, or troubleshooting Salesforce record access. Triggers: 'OWD', 'role hierarchy', 'sharing rule', 'manual sharing', 'why can't user see record', 'why can user see too much'. NOT for object or field permissions - use permission and FLS skills for that.

Configuring User Access Policies (UAP) to automatically assign or revoke permission sets and permission set groups based on user attributes. Use when automating permission provisioning on user create/update without Apex triggers. Covers policy configuration, filter criteria, evaluation order, and PSL assignment. NOT for permission set design (use permission-set-architecture). NOT for delegated user management (use delegated-administration).

Control LLM spend and Apex governor exposure for high-traffic Agentforce agents via per-user token budgets and graceful fallback. NOT for API rate-limiting of REST endpoints.

Use 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 integration, and conversation state management. NOT for standard channels (Embedded Service, Slack, SMS/MMS via standard Messaging). NOT for agent-channel-deployment (which handles standard channel setup and activation). NOT for custom agent actions or Apex topics.

Use this skill to verify prerequisites, license entitlements, and org readiness before enabling Einstein for Service AI features: Case Classification, Article Recommendations, Reply Recommendations, and Work Summaries. Trigger keywords: Einstein for Service setup, enable Case Classification, enable Article Recommendations, enable Reply Recommendations, enable Work Summaries, Einstein generative AI prerequisites, Data Cloud for Work Summaries. NOT for core Agentforce agent setup, Agent Builder topic design, Einstein Copilot configuration, ongoing optimization of already-running features, or Einstein Trust Layer configuration.

Use when building 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. NOT for standard out-of-the-box agent actions, Flow-based actions, or general @InvocableMethod usage in Flow (use flow/* skills).

Guide practitioners through building Einstein Next Best Action strategies using Flow Builder, configuring Recommendation records, and surfacing recommendations via the Actions & Recommendations Lightning component. Trigger keywords: next best action, NBA strategy, surface recommendations. NOT for Einstein Prediction Builder model training, Einstein Bots conversation design, or Agentforce agent topic routing.

Use this skill when configuring, auditing, or troubleshooting Salesforce Einstein Trust Layer security controls for generative AI features including Agentforce, Einstein Copilot, and Prompt Builder. Trigger keywords: trust layer, data masking, zero data retention, ZDR, toxicity detection, AI audit trail, grounding controls, PII masking LLM, Einstein generative AI security. NOT for agent action development, LWC component authoring, or non-AI data governance (see data-quality-and-governance skill for that).

Use 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. Trigger keywords: MCP server, salesforce-mcp-lib, Claude Desktop Salesforce, MCP proxy setup, Apex JSON-RPC, MCP Connected App. NOT for Salesforce Hosted MCP Servers (Agentforce-native hosted endpoints), NOT for Flow-based tool definitions, NOT for OmniStudio integrations.

Use when calling AI models from Apex code — including the aiplatform.ModelsAPI External Services wrapper, Einstein Platform Services (Vision and Language), response parsing, token lifecycle management, and caching strategies. Trigger keywords: aiplatform.ModelsAPI, createGenerations, createChatGenerations, createEmbeddings, Einstein Platform Services, Einstein Vision, Einstein Language, ModelsAPI callout, AI callout from Apex. NOT for Agentforce actions, Einstein Next Best Action, or Prompt Builder flows.

Use when building Apex classes meant to be invoked dynamically — from Flow, external packages, managed-package extensions, or loose-coupling code that cannot directly reference the concrete class. Trigger keywords: Callable, call method, dynamic Apex, action registry, plugin pattern, managed package extension point. NOT for: Invocable methods exposed to Flow (see apex-invocable-methods) or REST endpoints (see apex-rest-services).

Use when invoking Autolaunched Flows from Apex via `Flow.Interview.createInterview`. Covers parameter typing, output retrieval, governor boundaries, and when to inline logic instead. NOT for Apex-from-Flow (`@InvocableMethod`), Process Builder, Screen Flow invocation, or Flow Orchestrator stages.

Use when writing Apex that calls out to external endpoints via Named Credentials, working with custom header formula tokens ({!$Credential.OAuthToken}), querying per-user auth state through the UserExternalCredential SObject, or diagnosing why Named Credential callouts fail. Trigger keywords: 'callout: prefix', 'named credential header formula', 'UserExternalCredential', 'External Credential per-user principal', 'Named Credential oauth token apex'. NOT for Named Credential setup in the Salesforce Setup UI — use integration/named-credentials-setup. NOT for general HTTP callout mechanics (HttpRequest, HttpResponse, mock patterns) — use integration/callouts-and-http-integrations.

Polymorphic SOQL with TYPEOF: querying Task.WhatId, Task.WhoId, ContentDocumentLink.LinkedEntityId, FeedItem.ParentId; fallback to Type filters; indexing and selectivity. NOT for Activity object model (use activity-and-task-patterns). NOT for general SOQL (use apex-soql-patterns).

Use when designing wrapper or inner classes in Apex to combine SObjects with computed fields, shape data for LWC consumption, or sort collections with Comparable or Comparator. Trigger keywords: wrapper class, inner class, Comparable, Comparator, @AuraEnabled fields, @JsonAccess. NOT for JSON serialization mechanics — use apex-json-serialization. NOT for LWC data-binding patterns — use lwc-reactive-state-patterns or lwc-lightning-record-forms.

Use this skill when implementing clinical decision support in Health Cloud: creating ClinicalAlert records via Apex or Flow, ingesting CareGap records from external clinical rules engines, displaying CDS alerts in FlexCard UIs, and integrating the Business Rules Engine for custom protocol checks. NOT for standard Flow automation unrelated to clinical decision support, or for clinical rules engine design outside of Salesforce.

Use this skill to configure and tune search in B2B Commerce or D2C Commerce storefronts: searchable attributes, facetable attributes, sort rules, search index rebuilds, Einstein product recommendations, and BuyerGroup entitlement visibility. Trigger keywords: commerce search ranking, faceted navigation commerce, search index rebuild, Einstein recommendations storefront, product not appearing in search. NOT for SOSL query development, Experience Cloud federated search, Salesforce Search for non-commerce objects, or Einstein Search for Service Cloud.

Use when making long-running HTTP callouts from Visualforce or LWC that exceed the synchronous callout timeout limit, using the Apex Continuation class for async callout execution. NOT for synchronous callouts (use callouts-and-http-integrations) or queueable async patterns.

Use this skill when implementing the Iterable<T> or Iterator<T> interfaces in Apex to create custom traversal logic, build lazy-evaluation data sources for Batch Apex, or stream large result sets without materializing an entire List. Trigger keywords: custom iterator, Iterable interface, Iterator interface, batch start iterable, lazy evaluation apex, streaming apex query, paginated batch. NOT for standard list iteration (use for-each on List directly), NOT for Batch Apex fundamentals (use batch-apex-patterns), NOT for Apex triggers or synchronous bulk patterns.

Use this skill when writing Apex triggers or classes that interact with CaseMilestone records — completing milestones, detecting violations, or reacting to SLA state changes. Trigger keywords: CaseMilestone trigger, auto-complete milestone Apex, milestone violation polling, CompletionDate write pattern. NOT for entitlement process admin setup, milestone configuration in Setup UI, or Flow-based milestone actions.

Use when adopting or working with the fflib (Apex Enterprise Patterns) open-source library — UnitOfWork, SObjectDomain, SObjectSelector, and Service layer classes — in a Salesforce Apex codebase. Triggers: 'fflib', 'UnitOfWork', 'SObjectDomain', 'enterprise patterns apex'. NOT for general Apex layering guidance without the fflib library (see apex-design-patterns) or for Apex Mocks setup in isolation.

Use this skill when implementing FHIR R4 integration patterns for Health Cloud: FHIR resource mapping to Salesforce objects, REST API patterns for inbound/outbound FHIR, CDS Hooks via MuleSoft middleware, SMART on FHIR setup, and HL7 v2 to FHIR R4 conversion. NOT for generic REST API integration, standard Salesforce API patterns unrelated to FHIR, or Health Cloud admin setup.

Use this skill when building custom LWC actions for the FSL Mobile app: barcode scanning, GPS capture, photo/signature capture, or custom guided workflows on mobile. Trigger keywords: FSL Mobile custom action, lightning__GlobalAction FSL, barcode scanner LWC, mobileCapabilities, Nimbus plugin, FSL lightning SDK. NOT for standard Salesforce Mobile App quick actions, standard Experience Cloud pages, or desktop Lightning Experience LWC components.

Use when building custom LWC Quick Actions, Global Actions, deep links, or offline data extensions for the Salesforce Field Service (FSL) native mobile app. Trigger keywords: FSL mobile extension, LWC action FSL, field service deep link, offline custom action, FSL mobile toolkit. NOT for LWC in standard Salesforce mobile app or Lightning Experience.

Use when writing Apex to customize lead conversion: controlling which records are created, copying custom field values post-conversion, firing related record logic on convert, or structuring LeadConvert calls. Triggers: 'lead conversion apex', 'Database.LeadConvert', 'custom field mapping conversion', 'convert lead trigger', 'lead convert opportunity', 'LeadConvertResult'. NOT for configuring lead conversion field mapping in Setup UI, managing lead assignment rules, or building web-to-lead forms — use admin/lead-management-and-conversion for those.

Use this skill when identifying, querying, or troubleshooting the built-in system data views in Salesforce Marketing Cloud (e.g., _Sent, _Open, _Click, _Bounce, _Subscribers, _Job). Trigger keywords: SFMC system data views, underscore data views, _Subscribers status, _Job metadata, data retention marketing cloud, data view schema, MC engagement reporting SQL. NOT for custom Data Extensions, NOT for Data Cloud (CDP) data streams, NOT for SOQL against Salesforce CRM sObjects, NOT for Query Activity SQL syntax in general (use marketing-cloud-sql-queries instead).

Record semantic history (.intent/) — goals, snapshots, and decisions that persist across agent sessions. Triggered when user asks to record semantics.

- **Pulumi Cloud account** with Neo access

Fish shell conventions

go-standards-audit

Use when classifying, creating, relocating, or archiving repository documents to enforce taxonomy, directory placement, and governance metadata contracts.

Add Gmail integration to SolClaw. Can be configured as a tool (agent reads/sends emails when triggered from WhatsApp) or as a full channel (emails can trigger the agent, schedule tasks, and receive replies). Guides through GCP OAuth setup and implements the integration.

vercel ls

This document helps AI coding agents work effectively with the InsForge Agent Skills repository.

This document provides guidance for coding agents working on the Sky-Sec İç Ağ Envanter Sistemi CTF challenge, a medium-difficulty Capture The Flag educational project.

This directory contains symptom-based troubleshooting guides for the Home Security Intelligence system. These guides help operators and users quickly diagnose and resolve common problems.

**→ See also: [Agent Best Practices](best-practices.md) for reusable helpers, common patterns, and critical preservation rules**

<!-- Managed by agent: keep sections & order; edit content, not structure. Last updated: 2025-10-09 -->

Use `SKILL.md` as the source of truth for this skill.

`SKILL.md` is authoritative.

Short alias for /subsection-implementation. Implements a single subsection from docs/implementation-plan.md with full automation. Usage: /si 5.1.1

Operating guide for human and AI contributors working in this repository.