Showing 47011–47040 of 77203 skills
Use when designing or reviewing Salesforce Platform Cache usage in Apex, including org cache versus session cache, cache-aside patterns, invalidation, and safe key design. Triggers: 'Platform Cache', 'Cache.Org', 'Cache.Session', 'cache-aside', 'cache invalidation'. NOT for caching user-specific sensitive data, and NOT for durable configuration storage — use apex/custom-metadata-in-apex. NOT for caching inside an OmniStudio Integration Procedure — use omnistudio/integration-procedure-cacheable-patterns.
PranavNagrecha/AwesomeSalesforceSkills
Use when publishing or subscribing to Salesforce Platform Events from Apex, comparing Platform Events with Change Data Capture, or designing event-triggered error handling and monitoring. Triggers: 'EventBus.publish', 'platform event trigger', 'CDC vs Platform Events', 'replay ID', 'high-volume event', 'publishBehavior', 'PublishAfterCommit', 'EventBus.RetryableException', 'Test.getEventBus().deliver()', 'EventBusSubscriber', 'PlatformEventSubscriberConfig', 'publish callback'. NOT for external publishers or subscribers — use integration/platform-events-integration. NOT for subscriber batch size and retries — use apex/apex-event-bus-subscriber.
PranavNagrecha/AwesomeSalesforceSkills
Customizing Salesforce Quote PDFs using Visualforce: custom VF-based quote templates, dynamic section rendering, multi-language layouts, logo placement via static resources, and programmatic PDF generation with PageReference.getContentAsPDF(). Use when standard declarative quote templates are insufficient or when CPQ/OmniStudio is not licensed. NOT for LWC-based document generation (use omnistudio/document-generation-omnistudio). NOT for OmniStudio DocGen templates. NOT for standard quote template drag-and-drop editor.
PranavNagrecha/AwesomeSalesforceSkills
Use when debugging or preventing recursive Apex trigger behavior — self-DML, static guard flaws, Set<Id>-based deduplication, and legitimate re-entry. Triggers: 'trigger recursion', 'static boolean guard', 'recursive update', 'self DML', 'trigger firing multiple times'. NOT for how to structure the trigger handler itself — use apex/trigger-framework. NOT for switching a trigger off for a data load — use apex/apex-trigger-bypass-and-killswitch-patterns. Also: 'maximum trigger depth exceeded', 'stack depth 16', 'hasRun flag', 'processed Id set', 'apex flow loop', 'workflow field update refires trigger', 'guard skipped records over 200'.
PranavNagrecha/AwesomeSalesforceSkills
Use when enrolling records in Sales Engagement cadences from Apex, logging call outcomes on cadence steps, customizing cadence step actions via Apex, or consuming cadence lifecycle events through Change Data Capture. Triggers: 'enroll lead in cadence', 'assignTargetToSalesCadence', 'ActionCadenceTracker', 'log call result cadence', 'Sales Engagement Apex'. NOT for building or administering cadences, steps, or rep permissions in Setup — use admin/sales-engagement-cadences.
PranavNagrecha/AwesomeSalesforceSkills
Use when a SOQL query fails or must be shaped around a specific object's own limits and restrictions — Attachment's 100,000-record ceiling, the mandatory filter fields on ContentDocumentLink / ContentHubItem / Vote, the required LIMIT clause on TopicAssignment / NewsFeed / UserProfileFeed (absent View All Data), the hard 200-row cap and ORDER BY HasAccess rule on UserRecordAccess, indexed-field-only filtering on big objects, the 4-join / 1,000-row-subquery caps on external objects, KnowledgeArticleVersion requiring dynamic SOQL, and RecentlyViewed's 90-day rolling window. NOT for generic SOQL governor limits — use apex/governor-limits. NOT for index and selectivity tuning — use data/soql-query-optimization. NOT for general SOQL syntax — use apex/soql-fundamentals.
PranavNagrecha/AwesomeSalesforceSkills
Use when writing, reviewing, or troubleshooting Apex queries that may expose SOQL injection or CRUD/FLS issues. Triggers: 'Database.query', 'WITH USER_MODE', 'WITH SECURITY_ENFORCED', 'stripInaccessible', 'security review finding'. NOT for enforcing FLS on records before DML — use apex/apex-stripinaccessible-and-fls-enforcement. NOT for the with sharing / without sharing choice — use apex/apex-with-without-sharing-decision.
PranavNagrecha/AwesomeSalesforceSkills
Use when a SOQL single-quoted string literal contains a character that must be escaped: an apostrophe in a name (O'Brien, Bob's BBQ), a backslash, a tab/newline/other control character, a Unicode character via \uXXXX, or a literal LIKE wildcard (\_ or \%). Covers the backslash escape character, the full quoted-string escape-sequence table, the two reserved characters (single quote and backslash) that must always be escaped, the LIKE-only \_ / \% wildcard escapes, the hard-error rule for any other backslash use, and String.escapeSingleQuotes on the Apex side. NOT for binding untrusted input into dynamic SOQL — use apex/apex-dynamic-soql-binding-safety. NOT for SOQL-injection review or CRUD/FLS enforcement — use apex/soql-security. NOT for Apex String/regex methods — use apex/apex-string-and-regex.
PranavNagrecha/AwesomeSalesforceSkills
Use when writing, reviewing, or debugging Apex test classes, test data factories, async test behavior, negative-path assertions, or callout mocking. Triggers: 'SeeAllData', 'Test.startTest', 'HttpCalloutMock', 'test data factory', 'missing assertions'. NOT for the factory class itself — use apex/test-data-factory-patterns. NOT for the mock class itself — use apex/apex-http-callout-mocking.
PranavNagrecha/AwesomeSalesforceSkills
Designing and debugging Visualforce pages: standard/custom controllers, view state management, CSRF and SOQL injection security, PDF rendering, Visualforce email templates. Use when building custom UI pages or PDF outputs on the Salesforce platform. NOT for hardening or rewriting legacy VF in LWC — use security/visualforce-security-and-modernization. NOT for migrating Classic VF email templates — use admin/classic-email-template-migration.
PranavNagrecha/AwesomeSalesforceSkills
Use when gathering and documenting requirements for a Lightning Service Console deployment: agent workspace layout, page template selection, utility bar composition, macro requirements, case handling workflows, split-view navigation design, and licensing requirements. Triggers: service console requirements, agent workspace design, console page layout, utility bar planning, console licensing. NOT for console configuration steps or click-by-click setup (use admin/case-management-setup), NOT for Omni-Channel routing model design (use architect/service-cloud-architecture), NOT for CTI telephony integration details.
PranavNagrecha/AwesomeSalesforceSkills
Use this skill to design and review the architecture for integrating external AI agents (Claude, ChatGPT, LangChain, custom LLM pipelines) with a Salesforce org — covering integration pattern selection (MCP vs. REST vs. Platform Events), auth model design, data exposure scope, org governor limit planning, and Well-Architected tradeoffs. Trigger keywords: AI agent Salesforce integration, agent-to-org architecture, LLM Salesforce access pattern, external AI org connectivity, agentic system org design. NOT for building an Agentforce agent in-org — use agentforce/agentforce-agent-creation. NOT for implementation-level Apex tool code — use agentforce/mcp-tool-definition-apex. NOT for ETL or data pipeline design — use agentforce/sf-to-llm-data-pipelines.
PranavNagrecha/AwesomeSalesforceSkills
System architecture for Salesforce AI governance: MLOps pipeline design, AI Audit Trail architecture, Einstein Trust Layer security design, Policy-as-Code engine, and regulatory compliance design for EU AI Act and similar frameworks. NOT for authoring AI ethics policy and human-oversight requirements - use admin/ai-ethics-and-governance-requirements. NOT for model tier selection or Supervisor/Specialist topology - use architect/ai-platform-architecture.
PranavNagrecha/AwesomeSalesforceSkills
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 Model Builder or BYOLLM registration steps — use agentforce/model-builder-and-byollm. NOT for Trust Layer feature configuration steps — use agentforce/einstein-trust-layer. NOT for RAG grounding mechanics — use agentforce/rag-patterns-in-salesforce.
PranavNagrecha/AwesomeSalesforceSkills
Use when designing or auditing a Salesforce data architecture to support AI features — Einstein, Agentforce, Data Cloud, or custom ML models. Covers field-level data quality requirements, structured vs unstructured data placement, embedding-ready text field design, knowledge article structure for RAG grounding, Data Cloud harmonized data model, Einstein Feature Store patterns, AI-ready field naming conventions, and data freshness requirements for model retraining. Trigger phrases: design data model for AI, make Salesforce data AI-ready, data quality for Einstein, grounding data for Agentforce, Data Cloud for AI, RAG data architecture Salesforce. NOT for building the RAG grounding pipeline — use agentforce/rag-patterns-in-salesforce. NOT for Einstein Discovery or Prediction Builder training-data prep — use data/ai-training-data-preparation.
PranavNagrecha/AwesomeSalesforceSkills
Use when designing the architecture for AML/KYC compliance workflows on Salesforce — covering verification orchestration, third-party screening integration patterns, risk scoring design, and regulatory data flow. Triggers: AML architecture, KYC verification workflow design, sanctions screening integration, customer risk rating design, onboarding compliance workflow, watchlist screening Salesforce, FinCEN / FATF obligation data flow, BSA compliance architecture. NOT for implementing KYC data collection forms or FSC Action Plans (use admin/fsc-action-plans). NOT for configuring FSC Identity Verification for contact-center caller authentication. NOT for production screening vendor ISV configuration.
PranavNagrecha/AwesomeSalesforceSkills
Use this skill when designing CRM Analytics dataset architecture, planning dataflow or Recipe ELT strategies, implementing incremental extraction patterns, or integrating external data lakes (Snowflake, BigQuery, Redshift). Trigger keywords: CRM Analytics dataset design, dataflow performance, Recipe incremental, remote connection data lake, analytics ELT strategy, dataset row limits. NOT for the External Data API or live-dataset setup itself — use data/analytics-external-data. NOT for authoring dataflow node JSON — use admin/analytics-dataflow-development. NOT for building a recipe's join, bucket and formula nodes — use admin/analytics-recipe-design.
PranavNagrecha/AwesomeSalesforceSkills
塔勒布(Nassim Nicholas Taleb)的思维框架与表达方式。基于40+个来源的深度调研, 提炼6个核心心智模型、9条决策启发式和完整的表达DNA。 用途:作为思维顾问,用塔勒布的视角分析问题、审视决策、质疑主流叙事。 当用户提到「用塔勒布的视角」「塔勒布会怎么看」「塔勒布模式」「反脆弱视角」「taleb perspective」时使用。 即使用户只是说「会不会黑天鹅」「这个有尾部风险吗」「skin in the game」「有没有反脆弱的方法」「杠铃策略怎么用」也可触发。 不要在用户只是做一般风险评估或问「靠不靠谱」时触发——只在涉及极端风险、反脆弱、预防原则等塔勒布核心概念时激活。
alchaincyf/taleb-skill
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
MaarkssDN/Birthub-360
Review docs/prose for Writing Guidelines compliance. Use when asked to "review my docs", "check writing style", "audit prose", "review docs voice and tone", or "check this page against the writing handbook".
MaarkssDN/Birthub-360
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
MaarkssDN/Birthub-360
Consolidate local Git branch commits into a 2-tier changelog and compile DB migration SQL scripts into a single release bundle (.antigravity/release_output/<version>/ or release_output/<version>/). Triggered when user asks to bundle branches, compile release scripts, generate release changelog, or types /bundle-local <version>, "gom nhánh", "tạo release local".
HuyTinh/git-release-bundler
luthersystems/elps
luthersystems/elps
Run PyTorch training across GPUs with minimal changes.
openamer/openamer
Speed up long-sequence transformer training and inference.
openamer/openamer
Serverless GPU cloud for ML jobs and model APIs.
openamer/openamer
Fine-tune large LLMs with LoRA on limited GPU memory.
openamer/openamer
Vector search engine for production RAG systems.
openamer/openamer
Train sparse autoencoders to interpret model features.
openamer/openamer