AI & ML

thejordanleopold Skill

Use when building MCP (Model Context Protocol) servers to expose tools, resources, or prompts to LLMs. Use when designing tool schemas, implementing TypeScript or Python MCP servers, writing tool descriptions for discoverability, creating evaluations for MCP effectiveness, or debugging MCP integrations. Triggers: "MCP server", "model context protocol", "build MCP", "MCP tool", "MCP development", "Claude tool", "tool server", "MCP SDK", "function calling server", "create MCP", "MCP integration".

thejordanleopold Skill

Use when performing threat modeling, identifying attack surfaces, mapping trust boundaries, applying STRIDE analysis, scoring threats with DREAD, classifying data sensitivity, or designing security controls for a new system. Use before writing security code, when onboarding to a new codebase's security posture, or when preparing for a security review. Triggers: "threat model", "attack surface", "STRIDE", "trust boundary", "security design", "what could go wrong", "security risks", "data classification".

banibratachatterjee Bundle

Use when enabling, configuring, or troubleshooting Person Accounts in a Salesforce org — includes B2C data model design, IsPersonAccount flag handling, Account-Contact behavior differences, reporting impact, migration planning, and integration requirements. NOT for standard B2B Account/Contact modeling. NOT for managing business accounts that share an org with Person Accounts.

banibratachatterjee Bundle

Use this skill to create, deactivate, freeze, or manage Salesforce users, assign user licenses and feature licenses, configure profiles and roles, set login hours and IP restrictions, and set up delegated administration. Triggers: adding a new user, deactivating a departing employee, license assignment, freezing a user account, delegated admin setup. NOT for permission sets (use permission-set-architecture) or sharing model design (use sharing-and-visibility).

thejordanleopold Skill

Use when needing to reduce LLM API spend, audit token usage, route tasks to cheaper models, implement prompt caching, batch LLM requests, track cost per feature or user, or design cost governance for AI products. Triggers: "LLM costs", "token usage", "reduce AI spend", "model routing", "prompt caching", "cost per request", "LLM bill", "cheaper model", "batch API calls", "cost optimization", "AI budget".

thejordanleopold Skill

Use when building retrieval-augmented generation (RAG) pipelines, implementing vector search, choosing embedding models or vector databases, optimizing retrieval strategies, evaluating RAG quality (faithfulness, relevance, groundedness), or debugging RAG failures like hallucination, retrieval miss, or context overflow. Use for document chunking, hybrid search, reranking, context window optimization, and RAG evaluation with RAGAS or similar frameworks.

thejordanleopold Bundle

Use when an AI agent has been compromised, behaved unexpectedly, executed unauthorized actions, or may have had credentials exposed. Use when CLAUDE.md was modified without authorization, a skill executed a malicious payload, an agent accessed files outside its scope, or suspicious tool calls were detected. Triggers: "agent compromised", "agent behaved unexpectedly", "suspicious agent behavior", "CLAUDE.md modified", "skill executed payload", "agent accessed credentials", "unauthorized tool calls", "agent incident", "agent compromise response", "agent forensics", "credential exposed by agent", "agent wrote unexpected files", "memory poisoned", "hook fired", "agent anomaly".

thejordanleopold Bundle

Use when testing a system prompt against adversarial attack probes, measuring prompt robustness with a 0-100 trust score, or identifying which prompt injection or extraction techniques succeed against a given AI configuration. Use when red-teaming an AI assistant's system prompt, validating injection defenses before production deployment, or reproducing a reported prompt injection. Triggers: "test system prompt", "prompt robustness", "jailbreak test", "trust score", "prompt red team", "extraction probe", "injection probe", "DAN test", "EchoLeak", "skeleton key", "system prompt leakage", "prompt injection test", "adversarial probe", "BiDi injection", "many-shot priming", "canary test", "AgentSeal scan", "instruction override test", "delimiter attack", "prompt security test".

banibratachatterjee Bundle

Use when designing or reviewing Agentforce actions, including Flow actions, Apex invocable actions, prompt-template actions, action naming, input and output contracts, confirmation requirements, and safe error behavior. Triggers: 'agent actions', 'flow action for agent', 'agent invocable action', 'action schema design', 'agent action error handling'. NOT for topic boundary design or general Apex invocable guidance when the main concern is not an agent-facing action contract.

thejordanleopold Skill

Use when facing 2+ tasks that can be decomposed and delegated to subagents, when coordinating parallel workstreams across a codebase, when executing implementation plans with independent tasks, or when multiple agents need to work in the same repository without conflicts. Triggers: "run in parallel", "dispatch agents", "subagent", "parallel tasks", "agent coordination", "orchestrate", "multiple agents", "swarm", "worker agents", "concurrent work".

williamwjhuang Skill

Agent skill for portfolio construction, risk management, backtesting, and quantitative finance analysis with proper methodology.

banibratachatterjee Bundle

Use this skill when designing, selecting, or troubleshooting external ID fields on Salesforce objects for upsert operations, cross-system record correlation, or idempotent data loads. Trigger keywords: external ID field design, upsert key strategy, cross-system record matching, source system ID mapping, composite key for uniqueness, duplicate insert on upsert, relationship resolution by external ID. NOT for data migration steps (use data-migration-planning), NOT for REST API upsert endpoint wiring (use rest-api-patterns), NOT for general data model field decisions (use data-model-design-patterns).

banibratachatterjee Bundle

Use this skill when selecting or designing the correct Salesforce CPQ pricing model for a product or product line — choosing among the four native Pricing Methods (List, Cost Plus Markup, Block, Percent of Total), deciding between Range and Slab Discount Schedule types, and mapping business pricing requirements to the correct CPQ mechanism before any configuration begins. Trigger keywords: CPQ pricing method, SBQQ__PricingMethod__c, Cost Plus Markup, Block Pricing design, Percent of Total design, discount schedule type, Range vs Slab discount, pricing model strategy, which CPQ pricing mechanism to use. NOT for CPQ implementation of Price Rule objects (use cpq-pricing-rules), NOT for standard Salesforce pricing without CPQ (use products-and-pricebooks), NOT for CPQ product catalog or bundle setup.

banibratachatterjee Bundle

Use when designing or reviewing Agentforce topic structure, including topic boundaries, instruction quality, handoff rules, out-of-scope behavior, and topic-selector strategy. Triggers: 'agent topics', 'topic design', 'topic selector', 'agent scope boundary', 'handoff conditions'. NOT for action contract design or prompt-template wording when the main problem is not topic scoping.

banibratachatterjee Bundle

Enforce change quality via PR templates, required reviews, metadata ownership, and automated checks. NOT for branching model selection.

banibratachatterjee Bundle

Use this skill when querying, migrating, auditing, or maintaining account-to-territory and user-to-territory data in a Salesforce Enterprise Territory Management (ETM) org. Covers ObjectTerritory2Association DML via API, UserTerritory2Association data, Territory2ModelHistory audit queries, the Track Territory Assignment History feature (GA Spring '25), coverage analysis SOQL with AssociationCause filter, and data migration of territory associations between models. Trigger keywords: ObjectTerritory2Association, UserTerritory2Association, territory assignment data, territory coverage analysis, territory association bulk load, ETM data migration, track territory assignment history. NOT for ETM configuration or territory model setup — use territory-design-requirements for that. NOT for territory rule creation or activation — those are admin concerns.

banibratachatterjee Bundle

Use when a BA or admin needs to document the Salesforce data model: creating field inventories, object relationship maps, ER diagrams, or analyzing field usage across objects. Triggers: 'data dictionary', 'document our data model', 'object relationship map', 'field inventory', 'ER diagram for Salesforce'. NOT for designing the data model (use object-creation-and-design or architect skills) or for optimizing queries against the model (use soql-query-optimization).

banibratachatterjee Bundle

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.

banibratachatterjee Bundle

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.

banibratachatterjee Bundle

Use when designing, reviewing, or troubleshooting Salesforce object relationships and field type choices — lookup vs master-detail, junction object modeling, indexing strategy, and data model anti-patterns. NOT for object creation steps (use object-creation-and-design). NOT for bulk data loading operations.

banibratachatterjee Bundle

Use when modeling, loading, or troubleshooting Salesforce product and pricebook data — covering the Product2 → Pricebook2 → PricebookEntry three-object chain, standard pricebook constraints, bulk load sequencing (Product2 → Standard PBE → custom Pricebook2 → custom PBE), UseStandardPrice inheritance, and product hierarchy strategies. NOT for Salesforce CPQ product and pricing model (use cpq-vs-standard-products-decision). NOT for Industries CPQ catalog-item model (use industries-cpq-vs-salesforce-cpq). NOT for Opportunity Line Item mechanics.

banibratachatterjee Bundle

Use when creating a new Salesforce custom object: naming the object and setting its API name, selecting optional features (Activities, Chatter, History Tracking), choosing an org-wide default sharing model, and creating a tab. Triggers: 'create a custom object', 'new custom object setup', 'what sharing model should I choose', 'how do I create a tab for my object', 'object features like activities and history tracking'. NOT for custom field design on the object (use custom-field-creation), sharing rule or role hierarchy configuration (use sharing-and-visibility), or object relationship design decisions (use data-model-design-patterns).

banibratachatterjee Bundle

Configuring Salesforce Omni-Channel routing from scratch or updating existing routing: enabling Omni-Channel, creating Service Channels, configuring Routing Configurations (queue-based and skills-based), setting up Presence Statuses and Presence Configurations, assigning skills to Service Resources, and defining Skills-Based Routing Rules. Trigger keywords: Omni-Channel setup, routing configuration, queue-based routing, skills-based routing, presence status, service channel, routing rules. NOT for capacity model design (use omni-channel-capacity-model). NOT for OmniStudio FlexCards or DataRaptors. NOT for Omni-Channel Supervisor dashboard analysis.

banibratachatterjee Bundle

Use when designing a multi-system integration architecture using the three-layer API-led connectivity pattern (System, Process, Experience APIs), deciding how many layers to apply, mapping Salesforce as a system-layer endpoint or experience-layer consumer, or evaluating how Agentforce and MuleSoft Agent Fabric leverage API-led patterns. Triggers: 'API-led connectivity', 'system API process API experience API', 'MuleSoft integration layers', 'application network'. NOT for configuring MuleSoft Anypoint Salesforce Connector flows (use mulesoft-salesforce-connector). NOT for Salesforce REST API CRUD patterns (use rest-api-patterns). NOT for event-driven architecture without an API layer (use event-driven-architecture-patterns).

banibratachatterjee Bundle

Use this skill when designing, auditing, or troubleshooting behavioral boundaries for Agentforce agents — including topic Scope fields, agent-level system instructions, topic/action filters, the Escalation topic, restricted topics, and Instruction Adherence monitoring. Trigger keywords: agent guardrails, agent out of scope, restrict agent behavior, topic scope, agent instructions, agent fallback, Escalation topic, abuse prevention, action filters. NOT for Trust Layer content filtering (Einstein Trust Layer is a separate product concern), NOT for general topic routing design (use agentforce/agent-topic-design), NOT for prompt template construction (use agentforce/prompt-template-design).

banibratachatterjee Bundle

CPQ solution architecture covering bundle design, pricing engine performance, multi-currency strategy, and integration patterns. Trigger keywords: CPQ architecture, quote scalability, bundle design, QCP performance, CPQ integration, large quote, pricing waterfall, ServiceRouter. NOT for individual feature design such as configuring specific Price Rules or Discount Schedules — see cpq-pricing-rules or pricing-model-design instead.

banibratachatterjee Bundle

Use when designing or reviewing Salesforce record-triggered Flows, especially before-save vs after-save behavior, entry criteria, recursion avoidance, and when to escalate to Apex. Triggers: 'before save vs after save', '$Record__Prior', 'record-triggered flow', 'order of execution', 'flow recursion'. NOT for screen-flow UX or pure bulkification work when the trigger model is already correct.

banibratachatterjee Bundle

Configuring Salesforce Email-to-Case: Standard vs On-Demand mode selection, routing address setup, email threading via Lightning tokens, auto-response rules, attachment limits, and per-address case field defaults. Use when setting up a new Email-to-Case channel, troubleshooting duplicate cases from customer replies, or choosing between On-Demand and Standard mode. Trigger keywords: email-to-case, routing address, on-demand email-to-case, email threading, case from email, email agent, routing address setup. NOT for email templates or letterheads (use email-templates-and-alerts). NOT for Omni-Channel routing of case work items after creation (use omni-channel-routing-setup). NOT for Web-to-Case or inbound-only chat channels.

banibratachatterjee Bundle

Apex test patterns for @InvocableMethod agent actions: per-branch coverage, bulk safety, deterministic assertions. NOT for UI/LWC testing or agent conversational quality scoring.

banibratachatterjee Bundle

Observability for Agentforce: adoption, deflection, latency, cost, quality. NOT for agent evaluation/testing (see agentforce-eval-harness) or raw platform-event monitoring.

banibratachatterjee Bundle

Use this skill when designing or evaluating the holistic Salesforce AI platform strategy: model tier selection (Salesforce Default vs BYOLLM vs zero-data-retention partner models), Trust Layer design decisions at the architecture level, and multi-agent Supervisor/Specialist orchestration topology. Trigger keywords: AI platform strategy, model selection strategy, Supervisor agent topology, multi-agent orchestration, Einstein LLM gateway, BYOLLM architecture, trust layer design, agentic platform design, model tier decision. NOT for individual agent action development, Trust Layer feature configuration steps, RAG grounding mechanics, or BYOLLM registration procedures (see agentforce/einstein-trust-layer, agentforce/rag-patterns-in-salesforce, agentforce/model-builder-and-byollm for those).

banibratachatterjee Bundle

Use when designing or refactoring Salesforce access architecture around minimal profiles, permission sets, permission set groups, muting, and assignment governance. Triggers: 'profile sprawl', 'permission set strategy', 'PSG architecture', 'access bundle design', 'least privilege'. NOT for record-sharing model design or CRUD/FLS enforcement inside Apex.

banibratachatterjee Bundle

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.

banibratachatterjee Bundle

Use when bulk-loading or migrating Salesforce CPQ product catalog configuration data — SBQQ-namespaced objects including Product2, ProductOption, PriceRule, PriceAction, DiscountSchedule, DiscountCategory, ConfigurationAttribute, and OptionConstraint — across orgs or from an external source system. Trigger keywords: CPQ bulk load, SBQQ product migration, ProductOption insert order, CPQ trigger disable, price rule migration, CPQ sandbox refresh catalog, bundle migration. NOT for standard product import or CRM product migration (use product-catalog-data-model). NOT for CPQ quote or subscription data migration. NOT for Industries CPQ (Vlocity) catalog migration.

banibratachatterjee Bundle

Use 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. NOT for agent topic design (use agent-topic-design) or testing methodology (use agent-testing-and-evaluation).

banibratachatterjee Bundle

Use this skill when designing the checkout experience for a Salesforce B2B or D2C Commerce storefront — covering runtime model selection (LWR Managed Checkout vs Aura Flow Builder), cart and line-item requirements, payment option scoping, shipping rule definition, and guest vs. registered buyer experience design. Trigger keywords: checkout flow design, checkout UX requirements, LWR vs Aura checkout, guest checkout design, payment options design, shipping rules, checkout experience planning. NOT for implementation: does not cover Apex adapter code, CartCheckoutSession debugging, Extension Point registration, or Flow Builder configuration steps.