forcedotcom/sf-skills
86 skills182k installs65.6k starsGitHub
Install
npx skills add https://github.com/forcedotcom/sf-skillsSkills in this repo
1Generating Apexgenerating-apex is the primary Salesforce Apex authoring skill for new classes, selectors, services, batch and queueable jobs, invocable methods, triggers, and REST resources plus evidence-based review of existing .cls or .trigger files. Phase 1 discovers project conventions, chooses the smallest correct pattern, reads matching assets/ templates and references/ examples, authors ApexDoc-commented classes with required .cls-meta.xml files, and delegates test generation exclusively to the generating-apex-test skill. Phase 2 mandates run_code_analyzer on all generated classes with remediation through sev2, then executes org tests via sf apex run test capturing pass counts and coverage. Hard-stop rules forbid SOQL or DML inside loops, missing sharing keywords, hardcoded IDs, unhandled exceptions, SOQL injection via unbound dynamic queries, System.debug on hot paths, and @future methods in favor of Queueable with Finalizer. Defaults use with sharing, public access, API version 66.0 minimum, and generated tests deployed with runSpecifiedTests. The workflow is sequential across discover, author, analyze, test, and report phases with incomplete reports rejected when analyzer or test outpu.2.7kinstalls2Generating Apex Testgenerating-apex-test is a Salesforce agent skill that produces production-ready Apex test classes with disciplined test-fix loops and coverage analysis. Core principles require one behavior per method, bulk tests with 251 or more records, TestDataFactory delegation in every @TestSetup, meaningful Assert class assertions, HttpCalloutMock boundaries, negative path coverage, and Test.startTest plus Test.stopTest wrappers. The workflow gathers target classes, existing factories, coverage thresholds, and org aliases, then emits both the test class and matching .cls-meta.xml metadata files. It forbids legacy System.assert calls, SOQL inside loops, magic-number assertions, and god test classes over 500 lines while pointing to reference docs for async testing, mocking, and assertion patterns. Anti-pattern tables document fixes for generic exception catches and long Given-When-Then methods. Developers reach for generating-apex-test when creating new Apex tests, improving coverage, debugging failing tests, or implementing patterns for triggers, services, controllers, batch jobs, and integrations on Salesforce platforms.2.6kinstalls3Generating Lwc Componentsgenerating-lwc-components is a Salesforce agent skill for creating and editing Lightning Web Components across lwc JavaScript, HTML, CSS, and js-meta.xml bundles. It applies the PICKLES methodology covering prototype, integrate, compose, layout, libraries, execution, and security, plus a 165-point scoring rubric across eight quality categories. The skill chooses data access patterns such as LDS getRecord, base record forms, cacheable Apex, GraphQL wire adapters, or Lightning Message Service based on the UI need. It ships asset templates for datatables, modals, Flow screen components, GraphQL pagination, LMS publishers, and Jest test scaffolds, with reference guides for SLDS 2, dark mode, accessibility, performance, and template anti-patterns. Triggers include LWC file paths, wire service questions, and Jest LWC tests, while Apex-only or Aura work delegates to sibling sf-skills. Local dev preview via scripts supports hot reload without deployment. Output reports components changed, pattern chosen, quality notes, and next deploy or controller steps.2.6kinstalls4Generating FlowThe generating-flow listing packages the Salesforce data360-query skill for Data Cloud retrieve work: SQL, metadata introspection, async exports, and semantic search. It owns sf data360 query, search-index, metadata, profile, and insight commands while delegating standard CRM SOQL to platform-soql-query and segment design to data360-segment. Operators first gather org alias and whether they need counts, medium sets, large exports, schema inspection, or vector search, then run diagnose-org.mjs with --phase retrieve for readiness. Data Cloud SQL is not SOQL; table names are double-quoted, sqlv2 suits medium paginated results, and async-create fits large exports. Vector and hybrid search require healthy search indexes listed via search-index list, with hybrid prefilters only on configured fields. Curated examples in examples/search-indexes guide index creation instead of inventing JSON. Output reports retrieve task type, commands run, verification rows, and next steps toward segment or harmonize phases.2.6kinstalls5Generating Custom ObjectGenerating Custom Object is a Salesforce metadata skill that outputs deployment-safe CustomObject XML for .object-meta.xml files. It enforces required elements including label, pluralLabel, sharingModel, deploymentStatus Deployed, nameField, and visibility Public. Sharing model logic defaults to ReadWrite unless a Master-Detail relationship exists, which forces ControlledByParent and prevents common Metadata API errors such as cannot set sharingModel to ReadWrite on a CustomObject with a MasterDetail relationship field. Name field guidance chooses Text for human-named entities or AutoNumber with displayFormat and startingNumber for transactional records like invoices or tickets. The skill triggers on custom object creation, object metadata, sharing models, validation rules on objects, and deployment troubleshooting around Master-Detail constraints. Agents verify Tier 1 syntactic essentials and Tier 2 smart defaults before emitting XML. Use it whenever users create new objects, generate object metadata, or fix object deployment failures tied to sharing or name field configuration.2.5kinstalls6Generating Custom FieldGenerating Custom Field is a Salesforce metadata skill focused on deployment-safe CustomField XML with emphasis on high-failure field types. Every field requires fullName derived from label, label, description stating business purpose, and inlineHelpText with actionable guidance beyond the label. Precision and scale rules cap totals at eighteen digits with scale less than or equal to precision, and TextArea types need length two fifty five per API quirks. Roll-up Summary and Master-Detail sections document format errors, attribute restrictions, and lookup filter constraints called out as critical focus areas. External ID configuration triggers on integration or import keywords for Text, Number, and Email types. Agents verify universal mandatory attributes and type-specific requirements before output. Use it when creating fields, relationship lookups, formula or picklist metadata, or troubleshooting field deployment errors especially for roll-ups and Master-Detail relationships.2.5kinstalls7Querying SoqlQuerying SOQL is a Salesforce skill for SOQL and SOSL authoring, optimization, and analysis with a hundred-point scoring rubric. It owns .soql files, natural-language query generation, relationship and aggregate patterns, query-plan analysis, and governor-aware design. Workflow starts from target objects, required fields, filters, and sort limits, then picks shapes such as child-to-parent traversal, subqueries, aggregates, semi-joins, anti-joins, or SOSL text search. Optimization checks indexed selective filters, avoids scan-heavy wildcards, and notes security enforcement for Apex contexts. High-signal rules reject SELECT star thinking, loop queries, and post-filtering in Apex when SOQL can filter. Reference assets include starter .soql examples, selector templates, anti-pattern guides, and a post-tool validation script for live query plans. Cross-skill delegation covers execution via handling-sf-data, Apex embedding via generating-apex, and log-based debugging via debugging-apex-logs. Use it when writing, optimizing, or debugging SOQL, touching .soql files, or improving relationship query performance.2.5kinstalls8Debugging Apex Logsdebugging-apex-logs is a Salesforce skill for root-cause analysis from debug logs covering governor-limit diagnosis, stack-trace interpretation, slow-query investigation, and heap or CPU pressure. It owns tasks involving .log files, exceptions, SOQL or DML troubleshooting, and query-plan evidence extracted from logs. The workflow retrieves logs via SF CLI, then analyzes entry point, exceptions, governor limits, repeated SOQL or DML patterns, CPU or heap hotspots, and callout timing. Each finding is classified Critical, Warning, or Info and reported in six fields: what failed, where, why, severity, recommended fix, and verification step. High-signal patterns include SOQL in loop, DML in loop, non-selective queries, CPU pressure, heap pressure, and null pointer errors with default fix directions. The skill delegates Apex code generation to generating-apex and test execution to running-apex-tests. A 100-point scoring rubric grades analysis quality. Gotchas cover truncated 2 MB logs, async versus sync CPU limits, and framework lines masking user code in stack traces.2.5kinstalls9Deploying MetadataDeploying Metadata is a Salesforce DevOps skill for orchestrating metadata releases with sf CLI v2 only. It owns sf project deploy start, quick, report, retrieval workflows, release sequencing, CI CD guidance, and failure triage while delegating Apex authoring, LWC creation, Flow authoring, and data seeding to sibling sf-skills. Critical rules require explicit deploy scope on non-source-tracking orgs, dry-run validation before real deploys, and safe Flow rollout as Draft before activation. Default ordering deploys custom objects and fields first, then permission sets, Apex, Flows as Draft, and post-verify activation to avoid FLS and dependency errors. Workflows gather target org alias, scope via source-dir metadata or manifest, test level, and rollback expectations, then run preflight sf org display and validate with JSON output. CI pipelines cover authenticate, static analysis with sf code-analyzer v5, dry-run, tests including RunRelevantTests, deploy, and verify. Use it when shipping Salesforce metadata, scratch org management, pipeline design, or troubleshooting INVALID_CROSS_REFERENCE_KEY and test failures during deploy.2.5kinstalls10Platform Docs GetAn official Salesforce skill that fetches the platform's official documentation on demand so an agent can ground its answers in accurate reference material for Apex, metadata, and platform APIs. A solo builder reaches for it while building on Salesforce and wants the agent to consult authoritative docs rather than guess at APIs and syntax from memory.2.5kinstalls11Fetching Salesforce DocsThe fetching-salesforce-docs skill retrieves official Salesforce documentation from developer.salesforce.com, help.salesforce.com, architect.salesforce.com, admin.salesforce.com, and lightningdesignsystem.com using a targeted retrieval playbook. It classifies requests into developer, help, architect or admin, design system, or legacy atlas families before fetching, and rejects broad landing pages, shell-rendered help shells, third-party blogs, and PDF fallbacks. For JS-heavy pages it prefers browser-rendered extraction, verifies the exact concept or identifier appears on the page, and follows only the best one to three official child links when needed. Help articles require real article bodies, not Loading or CSS Error chrome, and soft 404 shells must be rejected. Grounded answers must cite title, exact URL, source type, and extraction caveats. Optional Playwright scripts in scripts/ support extraction but the playbook works without them. Out of scope items include code changes, deployments, and generating metadata.2.5kinstalls12Running Apex TestsRunning Apex Tests guides Salesforce test execution, coverage analysis, and structured test-fix loops using sf apex run test workflows and a 120-point scoring rubric. It owns tasks involving Apex unit test failures, code coverage gaps, uncovered lines, and disciplined reruns while delegating production Apex authoring to generating-apex and LWC Jest work elsewhere. The workflow discovers test scope and factories, runs the smallest useful test set first, analyzes failures and stack traces, fixes code or tests, and widens regression only after stability. High-signal rules require SeeAllData=false, meaningful assertions, bulk tests with 251+ records, Test.startTest and stopTest for async, and factories or TestSetup for clarity. Gotchas cover SeeAllData org dependencies, uncommitted work pending on callout tests, mock setup order, and TestSetup re-query requirements. Reference files span CLI commands, test patterns, mocking, performance optimization, and agentic test-fix loops with parse-test-results hooks. Output reports test scope, pass or fail summary, coverage, root causes, and next steps.2.5kinstalls13Generating Permission SetGenerating Permission Set guides creation of deployable Salesforce PermissionSet metadata for object CRUD, field-level security, user permissions, and app or tab visibility. Step one defines fullName, label, and description with descriptive API names such as Sales_Manager_Access. Object permissions set allowCreate, allowRead, allowEdit, allowDelete, modifyAllRecords, and viewAllRecords per object. Field permissions require readable and editable flags using ObjectName.FieldName format, with explicit warnings that required fields must never appear in field permissions and formula fields cannot be editable. User permissions grant system capabilities like ApiEnabled and RunReports, with security review flagged for ViewAllData, ModifyAllData, and ManageUsers. Application and tab visibility blocks configure Sales Console visibility and tab settings of Visible, Available, or None, including the rule that custom object tabs must keep the __c suffix. The skill targets Metadata API v60.0 plus deployments and emphasizes verifying field metadata before granting FLS to avoid deployment failures.2.5kinstalls14Platform Apex Generateplatform-apex-generate is a Salesforce Apex code generator that authors production-grade classes, triggers, and async jobs following enterprise Service-Selector-Domain architecture. It runs the Apex code analyzer, remediates governor-limit and security issues, and enforces org conventions like sharing keywords and bulkification. A solo developer on the Salesforce platform reaches for it when scaffolding new Apex or refactoring existing .cls/.trigger files without hand-writing boilerplate.2.5kinstalls15Generating Flexipagedata360-query covers the Salesforce Data Cloud retrieve phase for query, search, and metadata introspection tasks. Use it when work involves sf data360 query commands, search-index lifecycle operations, metadata inspection, or profile and insight reads. Treat Data Cloud SQL as its own language, not standard CRM SOQL, and run the diagnose-org readiness classifier before relying on query surfaces. Start with describe before guessing columns, prefer sqlv2 or async flows for larger result sets, and reserve vector or hybrid search for healthy search indexes. Core commands include sql counts, sqlv2 pagination, async-create exports, table describe, search-index list, and vector or hybrid queries with optional prefilter fields. Curated search-index JSON examples ship for vector knowledge and hybrid structured indexes. High-signal gotchas cover double-quoted table names, HNSW parameter defaults, and keeping STDM parquet tracing in agentforce-observe instead of this skill.2.5kinstalls16Generating Custom TabThis listing serves Data Cloud retrieve workflows through the data360-query skill bundled under the sf-skills repo. It owns sf data360 query, search-index, metadata, profile, and insight inspection when users need Data Cloud SQL counts, paginated sqlv2 reads, async exports, table describe, or semantic search. The skill delegates standard CRM SOQL to platform-soql-query, segment design to data360-segment, and STDM parquet tracing to agentforce-observe. Operating rules require the community sf data360 CLI plugin, a Data Cloud-enabled org alias, and the diagnose-org retrieve classifier before trusting query planes. Recommended flow classifies readiness, picks the smallest correct query shape, describes known DMO tables, then runs vector or hybrid search only when indexes list healthy. Output format documents retrieve task type, target org, commands run, verification rows, and next steps toward segment or harmonize work. Gotchas include double-quoted SQL table names and prefilter fields limited to index configuration.2.5kinstalls17Generating Custom ApplicationGenerating Custom Application defines tab-based Salesforce CustomApplication metadata for Lightning apps that group navigation, branding, and action overrides before deployment. Core properties include fullName, label, uiType Lightning, navType Standard or Console, and formFactors for LARGE and SMALL targets. Standard navType suits general business apps while Console is reserved for multi-record service workflows needing split-view workspaces. Optional brand configuration with headerColor and footerColor is highly recommended for professional identity even though it is technically optional. actionOverrides and profileActionOverrides wire custom Lightning record pages when those pages already exist in the org. The tabs array lists included navigation tabs and utilityBar references the utility bar configuration component. Settings such as isNavAutoTempTabsDisabled control navigation personalization behavior for end users. The skill explicitly excludes React UI bundle launcher apps, directing those cases to generating-ui-bundle-custom-app instead of CustomApplication XML. Deployment troubleshooting guidance helps resolve tab references, override targets, and navigation personalizatio.2.5kinstalls18Platform Apex Test GenerateAn official Salesforce skill that generates Apex unit test classes for your Apex code, helping meet the platform's mandatory code-coverage thresholds. A solo builder reaches for it when they need tests for Apex triggers and classes and would rather have the agent scaffold thorough test methods than hand-write assertions and test data setup.2.4kinstalls19Generating Lightning AppGenerating Lightning App builds deployable Salesforce Lightning Experience applications from natural language descriptions by orchestrating dependent metadata types in correct order. It defines a Lightning Custom Application and invokes specialized skills for custom objects, fields, tabs, FlexiPages, list views, validation rules, flows, and permission sets. The metadata type registry requires loading each specialized skill and calling salesforce-api-context before generation except for Flow which uses the metadata-experts pipeline. Use cases include project management apps, vehicle tracking solutions, and employee onboarding with custom Lightning record pages spanning multiple interconnected components. The skill excludes single-component work, Classic apps, troubleshooting-only tasks, or bare application containers without supporting metadata. Related skills cover generating-custom-object, generating-flexipage, generating-flow, generating-validation-rule, generating-list-view, and generating-permission-set as composable blocks orchestrated in dependency order to produce a deployable LEX solution from scenario descriptions.2.4kinstalls20Generating Custom Lightning TypeGenerating Custom Lightning Type guides creation of JSON Schema-based Custom Lightning Types for Einstein Agent structured inputs and outputs with optional editor and renderer configurations. Critical rules forbid the $schema field, require root object type lightning__objectType with unevaluatedProperties false, and restrict list arrays with lightning__listType at root without items keywords. Nested objects reference other CLTs via c__TypeName or Apex @apexClassType classes rather than nested lightning__objectType. Optional editor.json uses componentOverrides and layout with lightning/propertyLayout accepting only the property attribute. Widget rendition requires fetching widget-rendition.md before mosaic UEM tree generation. Custom LWC components need lightning__AgentforceInput or lightning__AgentforceOutput targets in meta.xml. A deployment error table maps common validator failures to fixes including misspelled lightning types, deprecated propertyRenderers keys, and attribute mapping mistakes. Verification checklist covers bundle paths under lightningTypes and Gen AI subfolder conventions.2.4kinstalls21Platform Apex Logs DebugAn official Salesforce skill that retrieves and helps analyze Apex debug logs from an org so a developer can trace what happened during a transaction and pinpoint errors. A solo builder reaches for it when Apex code misbehaves in a Salesforce org and they need to read the debug logs to diagnose the failure instead of manually pulling logs from setup.2.4kinstalls22Generating List Viewdata360-query owns the Salesforce Data Cloud retrieve phase for query, search, and metadata introspection using the external sf data360 CLI plugin on Data Cloud enabled orgs. It covers sync SQL, paginated sqlv2, async query workflows, table describe, vector search, hybrid search, and search index operations. Core rules treat Data Cloud SQL as distinct from CRM SOQL, run diagnose-org readiness with --phase retrieve, describe tables before guessing columns, and prefer sqlv2 or async flows for larger result sets. Vector and hybrid search require healthy search index lifecycle with list and prefilter constraints documented in curated examples. Delegation routes standard SOQL to platform-soql-query, segments to data360-segment, and STDM tracing to agentforce-observe. Recommended workflow classifies org readiness, chooses the smallest correct query shape, describes fields, then runs vector or hybrid queries only when indexes exist. High-signal gotchas include double-quoted table names, async preference for large exports, and HNSW index parameter defaults. Output format reports retrieve task type, org alias, commands, verification, and next steps.2.4kinstalls23Platform Apex Test RunAn official Salesforce skill that runs Apex tests in a target org via the Salesforce CLI and reports pass/fail results and code coverage. A solo builder reaches for it before deploying to confirm their Apex classes and triggers still pass and meet the required coverage, turning a manual test run into a single agent-driven step.2.4kinstalls24Generating Validation Ruledata360-query handles Salesforce Data Cloud retrieve work including sync SQL, paginated sqlv2, async query jobs, table describe, vector search, hybrid search, and search index lifecycle via the sf data360 CLI plugin. It applies when users run sf data360 query, search-index, metadata, profile, or insight commands on Data Cloud enabled orgs. Operating rules require diagnose-org --phase retrieve readiness, describe before column guesses, sqlv2 over OFFSET paging for medium sets, and async-create for large exports. Data Cloud SQL uses double-quoted table names and differs from CRM SOQL delegated to platform-soql-query. Vector and hybrid queries need healthy indexes listed before use with prefilter limited to configured fields. Curated examples in examples search-indexes supply vector-knowledge and hybrid-structured templates instead of inventing JSON. STDM parquet tracing belongs to agentforce-observe while segment design routes to data360-segment. Output format documents retrieve task type, org alias, target object, commands run, verification rows or schema, and suggested next harmonize or segment steps.2.4kinstalls25Handling Sf DataThe handling-sf-data skill covers Salesforce data operations with sf data CLI commands, bulk import and export, test data generation, cleanup scripts, and Apex anonymous seeding for validating Flow, Apex, and integration behavior. It owns record CRUD, tree import, factory patterns, and org cleanup while delegating pure SOQL writing, Apex test execution, and metadata deployment to sibling skills. A required mode decision distinguishes script generation from remote execution in a real org. Operating rules demand describe-first preflight when schema is uncertain, synthetic non-PII test data, cleanup planning before large seeds, and preferring 251 plus records when bulk behavior matters. The workflow verifies prerequisites, chooses the smallest correct mechanism from single-record sf data through Bulk API 2.0 and tree import, executes or generates assets from built-in templates, verifies counts and relationships, applies bounded retries, and leaves cleanup guidance after creation.2.4kinstalls26Building Sf IntegrationsThe building-sf-integrations skill covers Salesforce integration architecture and runtime plumbing including Named Credentials, External Credentials, External Services from OpenAPI specs, REST and SOAP callout patterns, Platform Events, and Change Data Capture. It owns metadata for namedCredential-meta.xml, outbound callouts, event-driven design, and sync versus async pattern selection while delegating Connected App OAuth, pure Apex logic, metadata deploy, and data import to sibling skills. The workflow chooses integration pattern by need, selects secure auth models without hardcoded secrets, generates from template assets under named-credentials, callouts, platform-events, and cdc folders, validates timeout retry and logging safety, and hands off deployment to deploying-metadata. High-signal rules forbid synchronous trigger callouts, require explicit timeouts, plan retries and dead-letter strategies, and prefer External Credentials for new development. Anti-patterns include missing request logging and mixing auth setup with runtime design.2.4kinstalls27Platform Soql QueryAn official Salesforce skill that executes SOQL queries against a target org, returning records so a developer can read and inspect platform data programmatically. A solo builder reaches for it when they need to pull or verify Salesforce data - checking records, debugging state, or exporting results - without navigating the org's UI record by record.2.4kinstalls28Platform Custom Field GenerateAn official Salesforce skill that generates custom field metadata for objects - the XML defining a field's type, label, and properties. A solo builder reaches for it while shaping a Salesforce data model when they need to add fields to standard or custom objects and would rather have the agent produce correct field metadata than write it by hand.2.3kinstalls29Generating Mermaid DiagramsThe generating-mermaid-diagrams skill produces text-based Salesforce diagrams as Mermaid with optional ASCII fallback for architecture, OAuth, ERD, integration sequence, and Agentforce behavior maps. In scope are sequenceDiagram auth flows, flowchart LR ERDs, system landscapes, role hierarchies, and markdown-embeddable outputs. Out of scope are rendered PNG or SVG mockups and non-Salesforce-only systems, which delegate to sibling skills. Workflow gathers diagram type, entities, output preference, styling level, and org metadata for grounded ERDs before generating Mermaid and optional ASCII. High-signal rules cover autonumber for sequences, simple ERD cards, restrained styling, and readable ASCII width. Cross-skill integration points to custom object discovery, visual diagrams, connected apps, Agentforce, and Flow skills. Reference files include conventions, syntax, styling palettes, OAuth templates, and datamodel ERD assets. Agents trigger on diagram, visualize, ERD, or architecture requests for Salesforce contexts.2.3kinstalls30Platform Metadata DeployAn official Salesforce (forcedotcom) skill that deploys platform metadata - custom objects, fields, permission sets, Apex classes - from a local project into a target Salesforce org. A solo builder reaches for it when they need to ship configuration and code changes to a live org through the Salesforce CLI instead of clicking through the setup UI.2.3kinstalls31Platform Custom Object GenerateAn official Salesforce skill that generates custom object metadata - the definition of a new object including its name, label, and settings on the platform. A solo builder reaches for it when modeling a Salesforce app's data and needs to create custom objects, letting the agent produce valid object metadata instead of crafting the XML by hand.2.3kinstalls32Configuring Connected AppsThe configuring-connected-apps skill guides OAuth app setup in Salesforce via Connected App or External Client App metadata including auth code, PKCE, JWT bearer, device, and client credentials flows. First decision table prefers ECA for new regulated or packageable solutions and Connected Apps for simple single-org legacy compatibility, noting Spring 26 disables new Connected App creation by default. Workflow chooses app model, OAuth flow by client type, loads XML templates from assets rather than scratch builds, applies a 120-point security checklist, and validates deployment readiness. Rules forbid committing consumer secrets, default Full scope, wildcard callbacks, or creating ECA OAuth security settings without org retrieve first. Metadata paths span connectedApps, externalClientApps, and multiple extlClntApp directories with abbreviated suffixes like ecaGlblOauth. Error handling covers DUPLICATE_VALUE, INVALID_CROSS_REFERENCE_KEY, and INSUFFICIENT_ACCESS_OR_READONLY with stop-on-failure guidance. Delegates Named Credential callouts, metadata deploy-only tasks, and Apex token code to sibling skills.2.3kinstalls33Generating Visual Diagramsgenerating-visual-diagrams produces rendered Salesforce visuals rather than text Mermaid diagrams. It covers visual ERDs, LWC and Experience Cloud mockups, architecture illustrations, and image edits using the Gemini Nano Banana Pro extension. A hard prerequisites gate runs check-prerequisites.sh before any generation, routing failures to gemini-cli-setup guidance. Interview-first workflow loads question banks for ERD, UI, architecture, and edit tasks unless the user requests quick mode with 1K draft defaults. The recommended loop drafts at 1K with gemini --yolo /generate, iterates with /edit, then exports final 2K or 4K images via generate_image.py. Default ERD style follows architect.salesforce.com aesthetics with dark borders and cloud accent colors. Out-of-scope tasks delegate to generating-mermaid-diagrams, generating-custom-object, generating-lwc-components, or generating-apex skills. Error recovery covers missing GEMINI_API_KEY, failed yolo runs, missing nanobanana extension installation, and fallback to generate_image.py scripts.2.3kinstalls34Developing Agentforcedeveloping-agentforce covers the full Agent Script lifecycle for Salesforce AI agents on the Atlas Reasoning Engine. Agents are AiAuthoringBundle metadata with .agent source and bundle-meta.xml describing subagents, actions, instructions, and flow control backed by Apex, Flows, and Prompt Templates. Hard rules require --json on every sf CLI command, target org verification, diagnose-before-fix with --use-live-actions preview traces, and spec approval gates before code generation. The create workflow designs an Agent Spec, scans for existing @InvocableMethod, AutoLaunchedFlow, and promptTemplates, stops for user approval, validates employee versus service agent prerequisites, generates authoring bundles, writes Agent Script, validates compilation, generates Apex stubs, previews with live actions, publishes, activates, and configures access. Agent Script is explicitly not JavaScript or Python and has zero training data in models, so reference files must be read before edits. Debugging workflows read session traces for subagent routing, action I/O, and LLM reasoning before modifying .agent files.2.3kinstalls35Platform Permission Set GenerateAn official Salesforce skill that generates permission set metadata - the XML that grants users access to objects, fields, Apex classes, and other resources on the platform. A solo builder reaches for it while building a Salesforce app when they need to define who can see and do what, without hand-crafting the verbose permission set XML.2.3kinstalls36Switching Orgdata360-query owns the Data Cloud retrieve phase for query, search, and metadata introspection using the community sf data360 CLI plugin on Data Cloud-enabled orgs. It covers sf data360 query sql, sqlv2, async-create, describe, vector, hybrid, and search-index commands plus profile and insight inspection. Core rules treat Data Cloud SQL as distinct from CRM SOQL, run diagnose-org.mjs readiness classification before queries, prefer describe before guessing columns, and use sqlv2 or async flows for larger result sets. Vector and hybrid search require healthy search index lifecycle with curated examples in vector-knowledge.json and hybrid-structured.json rather than invented JSON. Delegation routes standard SOQL to platform-soql-query, segment design to data360-segment, and STDM tracing to agentforce-observe. Gotchas include double-quoted table names, HNSW userValues typically empty on create, profileState not equaling expiration, and describe requiring known DMO table names. Output format summarizes retrieve task type, org alias, commands run, verification rows, and suggested next orchestration step.2.3kinstalls37Platform Metadata Api Context Getplatform-metadata-api-context-get is a Salesforce sf-skills reference covering all 604 Metadata API types with field docs, XML samples, and schema definitions. It supports section-specific loading to cut token use by 60-80% and includes SFDX project structure and naming guidance for authoring .meta.xml files. A Salesforce developer or DevOps engineer reaches for it to understand a metadata type's exact shape before creating or deploying it.2.3kinstalls38Platform Custom Tab Generateplatform-custom-tab-generate is a Salesforce sf-skills entry that generates valid custom tab metadata for a Salesforce DX project. It follows a CLI-template-first workflow to produce correct XML and deploy it, so custom objects and pages appear in app navigation. A Salesforce developer reaches for it to scaffold tabs quickly instead of hand-authoring and debugging .meta.xml files.2.3kinstalls39Generating Ui Bundle MetadataThe generating-ui-bundle-metadata skill governs Salesforce UI bundle scaffolding and metadata when uiBundles/*/src/ exists or when editing ui-bundle.json, uibundle-meta.xml, or CSP trusted site files. Scaffolding must use sf template generate ui-bundle with --template reactbasic and alphanumeric bundle names only. After generation, replace all boilerplate, populate real home content, and configure a hosting target via companion skills for Experience sites or CustomApplication App Launcher entries. The uibundle-meta.xml requires masterLabel, version, isActive, and a target element because bundles without targets are invisible in the org. ui-bundle.json supports outputDir, routing rewrites and redirects, trailingSlash, and headers with strict path safety rules rejecting globs and parent segments. CSP Trusted Sites metadata maps external domains to img, connect, font, style, media, and frame directives whenever CDNs, APIs, or third-party assets appear in code.2.2kinstalls40Platform Flexipage Generateplatform-flexipage-generate is a Salesforce sf-skills entry for creating, modifying, and troubleshooting Lightning pages (FlexiPages). It mandates starting from a CLI template, then validates XML structure and deploys record, app, and home pages so metadata stays valid. A Salesforce developer or admin reaches for it to build Lightning pages correctly instead of hitting common FlexiPage XML errors.2.2kinstalls41Platform Custom Lightning Type Generateplatform-custom-lightning-type-generate is a Salesforce sf-skills entry that generates valid custom Lightning Type metadata for a Salesforce DX project. It uses a CLI-template-first workflow to produce correct XML structure and deploy it, avoiding the common errors of hand-authored metadata. A Salesforce developer reaches for it to scaffold and ship custom Lightning types without wrestling with raw .meta.xml files.2.2kinstalls42Building Ui Bundle AppThe building-ui-bundle-app skill coordinates a complete Salesforce React UI bundle from natural language through seven dependency-ordered phases. Phase 1 scaffolds with sf template generate ui-bundle, npm install, metadata, and CSP trusted sites. Phase 2 optionally installs pre-built features like auth, shadcn, search, and navigation with conflict resolution. Phase 3 grounds Salesforce entities against the live org before authoring GraphQL via experience-ui-bundle-salesforce-data-access, never guessing field names. Phase 4 builds layout, pages, and components replacing all boilerplate. Phase 5 adds optional Agentforce chat or file upload integrations. Phase 6 follows the canonical seven-step deploy sequence including permissions, schema fetch, and final build. Phase 7 chooses Experience Site for external users or CustomApplication for App Launcher internal hosting. Each phase requires explicitly loading the specialized skill, executing its workflow, running lint and build verification, and checkpointing before proceeding. The build plan mandates org grounding before query authoring to prevent guessed fields.2.2kinstalls43Generating Ui Bundle FeaturesThe generating-ui-bundle-features skill installs pre-built authentication and search packages into Salesforce UI bundle apps under uiBundles/*/src instead of building those capabilities from scratch. Workflow starts by searching existing src/ implementations, then listing features with npx @salesforce/ui-bundle-features list and --search filters, describing candidates with describe for components and copy operations, and installing via install --ui-bundle-dir with --dry-run, --yes, or --on-conflict error modes. Conflict handling in non-interactive environments uses a two-pass flow: detect conflicts with --on-conflict error, author a resolution JSON mapping paths to skip or overwrite, then rerun with --conflict-resolution. Post-install integration reads __example__ files, applies patterns into target files named in describe output, and deletes examples after merge. Hint placeholders such as desired-page-with-search-input may require manual rename or relocation because the CLI does not resolve angle-bracket paths automatically.2.2kinstalls44Platform Data Manageplatform-data-manage is a Salesforce sf-skills entry for data operations: creating, updating, deleting, and bulk importing or exporting records, plus generating realistic test datasets and cleanup scripts using the sf CLI and anonymous Apex. It is meant for seeding and managing org data during development and QA, while delegating SOQL-only queries and metadata deploys to other skills. A Salesforce developer or QA engineer reaches for it to populate and clean up org data during testing.2.2kinstalls45Building Ui Bundle FrontendThe building-ui-bundle-frontend skill must activate before editing any uiBundles/*/src file for visual or UI changes in existing Salesforce UI bundle apps. It classifies work into pages, header or footer shell updates, or reusable components with implementation guides for each. appLayout.tsx is the navigation and branding source of truth shared across routes.tsx pages, requiring real nav labels instead of template placeholders and matching index.html title updates. React Router imports come from react-router with createBrowserRouter basename derived at runtime from the document base href, never hardcoded. Components use shadcn/ui imports such as Button from @/components/ui and Tailwind utility classes with responsive sm, md, and lg breakpoints and 44px touch targets. TypeScript rules forbid any, require typed useState, and prefer type guards over unsafe assertions. Module restrictions block lightning platform imports; Salesforce data access defers to using-ui-bundle-salesforce-data. Design guidance pushes distinctive typography, cohesive CSS variables, and mobile-responsive layouts before lint and build verification.2.2kinstalls46Platform List View Generateplatform-list-view-generate is a Salesforce sf-skills entry that generates valid list view metadata for a Salesforce DX project. It follows a CLI-template-first workflow to produce correct XML and deploy filtered record views, avoiding hand-authored metadata errors. A Salesforce developer reaches for it to scaffold list views quickly instead of hand-writing .meta.xml files.2.2kinstalls47Deploying Ui BundleThe fetched SKILL.md for this listing documents data360-query, the Salesforce Data Cloud retrieve phase skill. It covers sync and paginated SQL, async query workflows, table describe, vector and hybrid search, and search-index lifecycle via sf data360 commands. Data Cloud SQL is distinct from CRM SOQL and requires double-quoted table names such as ssot__Individual__dlm. Readiness classification runs diagnose-org.mjs with --phase retrieve before relying on query surfaces. Workflows choose sql for counts, sqlv2 for medium sets, and async-create for large exports, always describing tables before guessing columns. Vector and hybrid search require healthy search indexes listed via search-index list, with hybrid prefilter fields limited to index configuration. Curated examples vector-knowledge.json and hybrid-structured.json should seed index JSON instead of inventing schemas. Delegation routes standard SOQL to platform-soql-query, segment design to data360-segment, and STDM tracing to agentforce-observe. Output format summarizes retrieve task type, org alias, commands run, verification, and next harmonize or segment steps.2.2kinstalls48Platform Lightning App Coordinateplatform-lightning-app-coordinate orchestrates the creation of a complete Salesforce Lightning app from a natural-language description. Acting as a project manager, it extracts business entities, maps them to metadata types, invokes the specialized generation skills in correct dependency order (objects before fields, fields before validation rules, tabs before the app), and assembles a deployable SFDX project. A Salesforce architect reaches for it to prototype an entire business app rather than one component at a time.2.2kinstalls49Generating Ui Bundle SiteGenerating UI Bundle Site creates Digital Experience Site infrastructure hosting React UI bundles on Salesforce. Activation requires uiBundles/*/src/ in the project or tasks involving digitalExperiences, networks, customSite, or guest access configuration. Five properties must resolve before metadata generation: siteName UpperCamelCase, siteUrlPathPrefix lowercase, appNamespace from sfdx-project.json or org query defaulting to c, appDevName from UIBundle metadata or query defaulting to siteName, and enableGuestAccess boolean default false. Workflow step one resolves all properties, step two creates Network, CustomSite, DigitalExperienceConfig, DigitalExperienceBundle, and sfdc_cms__site paths, step three loads full docs templates substituting brace placeholders only, and step four forbids editing non-templated default fields. React sites use appContainer true thin containers without LWR routes or branding sets, linking appSpace to the UIBundle record. Wrong appNamespace or appDevName yields deployed blank pages. Verification checklist confirms five properties, file existence, appSpace match, and sf project deploy validation before deploy.2.2kinstalls50Testing AgentforceThe testing-agentforce skill covers automated testing for Salesforce Agentforce agents through Mode A ad-hoc preview and Mode B Testing Center batch suites plus direct Flow or Apex action execution. Mode A uses sf agent preview start, send, and end with --authoring-bundle for local traces during iterative development and fix validation from observing-agentforce. Test planning auto-derives utterances from subagents, actions, guardrails, multi-turn flows, and safety probes, but always presents the plan before running. Trace analysis jq commands inspect topic routing, action invocation, grounding, safety scores, enabled tools, and variable updates under .sfdx/agents sessions paths. Safety probes require an explicit SAFE, UNSAFE, or NEEDS_REVIEW verdict with deployment warnings when unsafe. Mode B deploys AiEvaluationDefinition YAML via sf agent test create and run with expectedOutcome assertions, Level 2 invocation names in expectedActions, and results fetched by job ID. Fix loops allow up to three iterations mapping trace failures to description, guard, instruction, or reasoning fixes. Dependencies include sf CLI 2.121.7+, jq, and python3 for control-character stripping before JSON.2.2kinstalls51Uplifting Components To Slds2The uplifting-components-to-slds2 skill from Salesforce sf-skills systematizes Lightning Web Component migration from SLDS 1 to SLDS 2. Workflow always starts with npx @salesforce-ux/slds-linter@latest lint --fix ., then fixes remaining violations across color, spacing, sizing, typography, border, radius, and shadow hook categories. Four violation types have dedicated references: no-hardcoded-values-slds2, lwc-token-to-slds-hook, no-slds-class-overrides, and no-deprecated-tokens-slds1. Class overrides require renaming CSS selectors to component-prefixed classes and adding them alongside SLDS classes in HTML markup. Color hooks demand context-based selection via the color-hooks decision guide; non-color hooks map to numbered scales. All replacements use var(--slds-g-hook, originalValue) fallbacks. Layout values like 100%, auto, and 0 stay unchanged. Validation loops the linter until zero errors and checks light, dark, and density rendering. Advanced patterns cover color-mix for transparency and calc expressions with tokens. Prerequisites include Node.js 14.x and git backup before bulk uplift work.2.2kinstalls52Observing AgentforceThe observing-agentforce skill analyzes production Agentforce agent behavior using session traces and Data Cloud. A three-phase workflow observes STDM sessions from Data Cloud or falls back to test suites plus sf agent preview local traces, reproduces problematic conversations with sf agent preview, and improves by editing .agent files, validating, publishing, and verifying. Routing gathers org alias, agent API name, optional agent file path, session IDs, and lookback days. It resolves MasterLabel and DeveloperName from GenAiPlannerDefinition, locates or retrieves aiAuthoringBundles .agent files, and discovers the active Data Cloud data space before STDM queries. Prerequisite checks probe ssot__AiAgentSession__dlm availability; failure switches to Phase 1-ALT with test suites and preview traces. Phase steps include findSessions analysis, preview send with utterances, and direct .agent instruction edits. The skill triggers for production failures, regressions, and trace analysis, not for developing or testing .agent files during local iteration.2.2kinstalls53Searching MediaThe data360-query skill covers Salesforce Data Cloud retrieve-phase work: sync SQL, paginated sqlv2, async query workflows, table describe, vector search, hybrid search, and search-index operations. Use when tasks involve sf data360 query, search-index, metadata, profile, or insight inspection. Delegate standard CRM SOQL to platform-soql-query, segment design to data360-segment, and STDM tracing to agentforce-observe. Gather org alias, result-set size needs, and table or index names first. Run diagnose-org with phase retrieve before relying on query surfaces. Prefer describe before guessing columns, sqlv2 or async for larger sets, and vector or hybrid only when index lifecycle is healthy. Examples include COUNT on ssot__Individual__dlm, describe table, vector and hybrid queries against Knowledge_Index with optional prefilter. Gotchas: Data Cloud SQL is not SOQL, double-quote table names, HNSW userValues often empty on create, and query describe needs a known DMO after readiness passes. Output reports retrieve task type, org, object, commands, verification, and next step.2.1kinstalls54Implementing Ui Bundle File UploadThe implementing-ui-bundle-file-upload skill guides React UI bundle file uploads using @salesforce/ui-bundle-template-feature-react-file-upload programmatic APIs only, not prebuilt components. Install the package when uiBundles/*/src exists and the task involves attaching or dropping files. Pattern A uploads files and returns contentBodyId without record linking for deferred attachment flows. Pattern B passes recordId to create ContentVersion records linked immediately to existing Accounts, Opportunities, or Cases. Pattern C uploads first, creates the record, then calls createContentVersion to link contentBodyId values after form submission. The upload function exposes onProgress callbacks for custom progress UI because FileUpload components and useFileUpload hooks are not exported. Reference demo components illustrate UI ideas but must be rebuilt locally. The skill pairs with Salesforce data access skills for record creation and forbids rolling custom FormData or XHR upload stacks when this API package is available.2.1kinstalls55Using Ui Bundle Salesforce DataThe using-ui-bundle-salesforce-data skill owns all Salesforce record operations in React UI bundles when uiBundles/*/src imports @salesforce/sdk-data or GraphQL codegen files exist. createDataSDK provides graphql and fetch with optional chaining because methods may be undefined per surface. Preconditions require the data SDK package, schema.graphql at project root via npm run graphql:schema, and deployed custom objects confirmed through graphql-search.sh from the sfdx-project folder. GraphQL rules mandate parsing errors despite HTTP 200, @optional on read fields for FLS safety, explicit first pagination, uiapi mutation wrappers with allOrNone, and schema lookup before any field names because Salesforce names are case-sensitive. Supported REST paths include UI API record metadata, Apex REST, Connect file upload config, and Einstein LLM generations while blocking enterprise SOQL query endpoints and Aura-enabled Apex. Workflow steps acquire schema, search entities, author one operation per .graphql file, run codegen to graphql-operations-types.ts, then lint and validate.2.1kinstalls56Implementing Ui Bundle Agentforce Conversation ClientThis skill embeds the Salesforce Agentforce Conversation Client in UI Bundle projects that contain uiBundles/*/src directories. A hard constraint forbids creating custom chatbot components; all requests must use AgentforceConversationClient from @salesforce/ui-bundle-template-feature-react-agentforce-conversation-client. Step one greps for existing usage excluding implementation files and validates agentId against ^0Xx[a-zA-Z0-9]{15}$. Step two resolves agent IDs via sf CLI SOQL for Employee Agents, handling missing CLI, unauthenticated orgs, inactive agents, and user selection without auto-pick. Step three defines canonical imports. Local development requires trusted domain localhost:5173 in Session Settings with a warning to remove before production. Prerequisites include user-configured Salesforce settings the skill calls out after embedding. Custom agent builds and projects without uiBundles are explicit do-not-trigger cases. Projects without uiBundles never trigger this skill. See SKILL.md for the authoritative workflow and constraints. Step four applies the embed or update in the target React file.2.1kinstalls57Getting Datacloud SchemaThe getting-datacloud-schema skill retrieves Data Lake Object and Data Model Object schema from Salesforce Data Cloud using SSOT REST APIs via bundled Python scripts. Parameters are required org_alias plus optional dlo_name or dmo_name. Execution discovers connected org with sf org list, validates authentication via sf org display, then runs get_dlo_schema.py or get_dmo_schema.py from the skill scripts directory using absolute skill_dir paths not relative ./scripts. List mode shows all DLOs or DMOs with labels, categories, IDs, and record counts; detail mode returns field names, data types, primary key flags, and nullable status while highlighting custom fields over system cdp_sys fields. Error handling covers disconnected orgs, not-found objects, permission 403s, and API version v64.0 notes. After results it suggests follow-ups like querying data, calculated insights, segments, data streams, or DMO mappings. Error handling covers disconnected orgs, not-found objects, and HTTP 403 permissions.2.1kinstalls58Developing Datacloud Code Extensiondeveloping datacloud code extension Skill This skill provides a complete workflow for developing testing and deploying custom Python code extensions to Salesforce Data Cloud Code extensions allow you to write Python transformations that read from and write to Data Lake Objects DLOs and Data Model Objects DMOs User wants to create a new code extension project User needs to test a code extension locally User wants to scan code for required permissions User needs to deploy a code extension to Data Cloud User is working with Data Cloud transformations User wants to read write DLO or DMO data programmatically Before executing any code extension commands verify prerequisites The developing datacloud code extension skill documents workflows prerequisites and usage patterns grounded in its repository SKILL md Agents should follow the documented steps respect safety and permission notes and cite only capabilities described in the source It triggers on phrases matching the skill description and integrates with the agent toolchain for the tasks outlined in the documentation2.1kinstalls59Connecting Datacloudconnecting datacloud Data Cloud Connect Phase Use this skill when the user needs source connection work connector discovery connection metadata connection testing source object browsing connector schema inspection or connector specific setup payloads for external sources Use connecting datacloud when the work involves sf data360 connection connector catalog inspection connection creation update test or delete browsing source objects fields databases or schemas identifying connector types already in use preparing connector definitions for Snowflake SharePoint Unstructured or Ingestion API sources Delegate elsewhere when the user is creating data streams or DLOs preparing datacloud preparing datacloud SKILL md creating DMOs mappings IR rulesets or data graphs harmonizing datacloud harmonizing datacloud SKILL md writing Data Cloud SQL or search index workflows retrieving datacloud retrieving datacloud SKILL md Ask for or infer target org alias connector type or source system whether the user wants inspection only or live mutation connection name or ID if one already exists whether credentials are already configured outside the CLI whether the user also expects stream creation right a.2kinstalls60Retrieving Datacloudretrieving datacloud Data Cloud Retrieve Phase Use this skill when the user needs query search and metadata introspection for Data Cloud sync SQL paginated SQL async query workflows table describe vector search hybrid search or search index operations Use retrieving datacloud when the work involves sf data360 query sf data360 search index sf data360 metadata sf data360 profile or sf data360 insight inspection understanding Data Cloud SQL results or query shape Delegate elsewhere when the user is writing standard CRM SOQL only querying soql querying soql SKILL md designing segment or calculated insight assets segmenting datacloud segmenting datacloud SKILL md analyzing STDM session tracing parquet telemetry observing agentforce observing agentforce SKILL md Ask for or infer target org alias whether the user needs quick count medium result set large export schema inspection or semantic search table index name if known whether the task is read only SQL or search index lifecycle management2kinstalls61Activating Datacloudactivating datacloud Data Cloud Act Phase Use this skill when the user needs downstream delivery work activations activation targets data actions or pushing Data Cloud outputs into other systems Use activating datacloud when the work involves sf data360 activation sf data360 activation target sf data360 data action sf data360 data action target verifying downstream delivery setup Delegate elsewhere when the user is still building the audience or insight segmenting datacloud segmenting datacloud SKILL md exploring query search or search indexes retrieving datacloud retrieving datacloud SKILL md setting up base connections or ingestion connecting datacloud connecting datacloud SKILL md preparing datacloud preparing datacloud SKILL md Ask for or infer target org alias destination platform or downstream system whether the segment already exists and is published whether the user needs create inspect update or delete whether the task is activation focused or data action focused2kinstalls62Harmonizing Datacloudharmonizing datacloud Data Cloud Harmonize Phase Use this skill when the user needs schema harmonization and unification work DMOs field mappings relationships identity resolution unified profiles data graphs or universal ID lookup Use harmonizing datacloud when the work involves sf data360 dmo sf data360 identity resolution sf data360 data graph sf data360 profile sf data360 universal id lookup Delegate elsewhere when the user is still ingesting streams or building DLOs preparing datacloud preparing datacloud SKILL md working on segment logic or calculated insights segmenting datacloud segmenting datacloud SKILL md running SQL describe or search index workflows retrieving datacloud retrieving datacloud SKILL md Ask for or infer source DLO and target DMO names whether the task is schema creation mapping IR or graph related target org alias whether a ruleset already exists the user s desired unified entity model2kinstalls63Orchestrating Datacloudorchestrating datacloud Salesforce Data Cloud Orchestrator Use this skill when the user needs product level Data Cloud workflow guidance rather than a single isolated command family pipeline setup cross phase troubleshooting data spaces data kits or deciding whether a task belongs in Connect Prepare Harmonize Segment Act or Retrieve This skill intentionally follows sf skills house style while using the external sf data360 command surface as the runtime The plugin is not vendored into this repo Use orchestrating datacloud when the work involves multi phase Data Cloud setup or remediation data spaces sf data360 data space data kits sf data360 data kit health checks sf data360 doctor CRM to unified profile pipeline design deciding how to move from ingestion harmonization segmentation activation cross phase troubleshooting where the root cause is not yet clear Delegate to a phase specific skill when the user is focused on one area2kinstalls64Preparing Datacloudpreparing datacloud Data Cloud Prepare Phase Use this skill when the user needs ingestion and lake preparation work data streams Data Lake Objects DLOs transforms Document AI unstructured ingestion or the handoff from connector setup into a live stream Use preparing datacloud when the work involves sf data360 data stream sf data360 dlo sf data360 transform sf data360 docai choosing how data should enter Data Cloud rerunning or rescanning ingestion after a source update preparing Ingestion API backed streams after connector setup is complete Delegate elsewhere when the user is still creating testing source connections connecting datacloud connecting datacloud SKILL md mapping to DMOs or designing IR data graphs harmonizing datacloud harmonizing datacloud SKILL md querying ingested data retrieving datacloud retrieving datacloud SKILL md Ask for or infer target org alias source connection name source object dataset document source desired stream type DLO naming expectations whether the user is creating updating running or deleting a stream whether the source is CRM a database connector an unstructured file source or an2kinstalls65Running Code AnalyzerEvery interaction with Code Analyzer results MUST go through the bundled scripts in skill_dir scripts No exceptions bash WRONG inline Python to parse results python3 c import json data json load open results json WRONG inline Node js to parse results node e const data require results json WRONG jq to filter results cat results json jq violations select engine pmd WRONG reading the results file directly it can be 10MB Read tool code analyzer results json The running code analyzer agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2kinstalls66Segmenting Datacloudsegmenting datacloud Data Cloud Segment Phase Use this skill when the user needs audience and insight work segments calculated insights publish workflows member counts or troubleshooting Data Cloud segment SQL Use segmenting datacloud when the work involves sf data360 segment sf data360 calculated insight segment publish workflows member counts and segment troubleshooting calculated insight execution and verification Delegate elsewhere when the user is still building Data Model Objects DMOs mappings or identity resolution harmonizing datacloud harmonizing datacloud SKILL md activating a segment downstream activating datacloud activating datacloud SKILL md writing read only SQL or search index queries retrieving datacloud retrieving datacloud SKILL md Ask for or infer target org alias unified DMO Data Model Object or base entity name whether the user wants create publish inspect or troubleshoot whether the asset is a segment or calculated insight expected success metric member count aggregate value or publish status2kinstalls67Deploying Omnistudio Datapacksdeploying omnistudio datapacks Vlocity Build DataPack Deployment Use this skill when the user needs Vlocity DataPack deployment orchestration export deploy workflow manifest driven deploys failure triage and CI CD sequencing for OmniStudio Industries DataPacks Use deploying omnistudio datapacks when work involves vlocity packDeploy packRetry packContinue packExport packGetDiffs validateLocalData DataPack job file design projectPath expansionPath manifest queries org to org DataPack migration and retry loops troubleshooting DataPack dependency matching key and GlobalKey issues Delegate elsewhere when the user is deploying standard metadata with sf project deploy deploying metadata deploying metadata SKILL md building OmniScripts FlexCards IPs or Data Mappers building omnistudio designing Product2 EPC bundles modeling omnistudio epc catalog modeling omnistudio epc catalog SKILL md writing Apex LWC code generating apex generating apex SKILL md generating lwc components generating lwc components SKILL md Use Vlocity Build vlocity commands for DataPacks not sf project deploy Prefer Salesforce CLI auth integration sfdx username alias over username password files when available Always ru.1.9kinstalls68Creating B2b Commerce StoreInteractive workflow to create a Commerce B2B Store in Salesforce and retrieve the auto generated storefront metadata to your repository Commerce B2B Store backend data Storefront frontend metadata Store must be created first in the org to auto generate the Storefront Never create storefront metadata manually See Store vs Storefront Reference references store vs storefront md Trigger when users request Create a B2B Commerce store Build a Commerce storefront Set up Commerce B2B Create B2B Commerce Retrieve Commerce storefront metadata Deploy B2B storefront 1 Always follow the interactive flow Do NOT skip steps Each step requires user confirmation before proceeding The creating b2b commerce store agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation1.9kinstalls69Building Omnistudio Integration Procedurebuilding omnistudio integration procedure OmniStudio Integration Procedure Creation and Validation Expert OmniStudio Integration Procedure IP builder with deep knowledge of server side process orchestration Create production ready IPs that combine DataRaptor Data Mapper actions Apex Remote Actions HTTP callouts conditional logic and nested procedure calls into declarative multi step operations In scope Creating well structured Integration Procedures from requirements selecting and wiring element types DataRaptor Remote Action HTTP Conditional Block Loop Set Values nested IP dependency validation error handling patterns 110 point scoring deployment and activation Out of scope Building OmniScripts use building omnistudio omniscript creating Data Mappers directly use building omnistudio datamapper designing FlexCards use building omnistudio flexcard mapping full dependency trees use analyzing omnistudio dependencies deploying metadata to org use deploying metadata Purpose What business process is this IP orchestrating e g onboard a new account process an order Target objects data sources Which Salesforce objects external APIs or both Type SubType naming PascalCase pair that uniquely.1.9kinstalls70Building Omnistudio Omniscriptbuilding omnistudio omniscript OmniStudio OmniScript Creation and Validation Expert OmniStudio OmniScript builder for declarative step based guided digital experiences OmniScripts are the OmniStudio analog of Screen Flows multi step interactive processes that collect input orchestrate server side logic Integration Procedures DataRaptors and present results to the user all without code Scoring 120 points across 6 categories Thresholds 90 Deploy 67 89 Review 67 Block fix required In scope Creating OmniScripts from requirements element selection and PropertySetConfig design dependency analysis Integration Procedures DataRaptors data flow tracing 120 point validation scoring deployment and activation Out of scope Building FlexCards use building omnistudio flexcard creating Integration Procedures directly use building omnistudio integration procedure mapping full dependency trees use analyzing omnistudio dependencies deploying metadata to org use deploying metadata Input Description Default Type Process category e g ServiceRequest Enrollment None required SubType Specific variation e g NewCase UpdateAddress None required Language Locale for the OmniScript English Purpose Business proce.1.9kinstalls71Building Omnistudio Callable Apexbuilding omnistudio callable apex Callable Apex for Salesforce Industries Common Core Specialist for Salesforce Industries Common Core callable Apex implementations Produce secure deterministic and configurable Apex that cleanly integrates with OmniStudio and Industries extension points In scope Creating System Callable classes for Industries extension points reviewing callable implementations for correctness and risks migrating VlocityOpenInterface VlocityOpenInterface2 to System Callable 120 point scoring and validation Out of scope Generic Apex classes without callable interface use generating apex building Integration Procedures use building omnistudio integration procedure authoring OmniScripts use building omnistudio omniscript deploying Apex classes use deploying metadata 1 Callable Generation Build System Callable classes with safe action dispatch 2 Callable Review Audit existing callable implementations for correctness and risks 3 Validation Scoring Evaluate against the 120 point rubric 4 Industries Fit Ensure compatibility with OmniStudio Industries extension points Ask for Entry point OmniScript Integration Procedure DataRaptor or other Industries hook Action names stri.1.9kinstalls72Building Omnistudio Datamapperbuilding omnistudio datamapper OmniStudio Data Mapper Creation and Validation Expert OmniStudio Data Mapper developer specializing in Extract Transform Load and Turbo Extract configurations Generate production ready performant and maintainable Data Mapper definitions with proper field mappings query optimization and data integrity safeguards In scope Creating and validating OmniStudio Data Mapper configurations Extract Transform Load Turbo Extract field mapping design query optimization FLS Field Level Security validation deployment via deploying metadata skill Out of scope Building Integration Procedures use building omnistudio integration procedure authoring OmniScripts use building omnistudio omniscript designing FlexCards use building omnistudio flexcard analyzing cross component dependencies use analyzing omnistudio dependencies 1 Generation Create Data Mapper configurations Extract Transform Load Turbo Extract from requirements 2 Field Mapping Design object to output field mappings with proper type handling lookup resolution and null safety 3 Dependency Tracking Identify related OmniStudio components Integration Procedures OmniScripts FlexCards that consume or feed Data Mapp.1.9kinstalls73Analyzing Omnistudio Dependenciesanalyzing omnistudio dependencies OmniStudio Cross Component Analysis Expert OmniStudio analyst specializing in namespace detection dependency mapping and impact analysis across the full OmniStudio component suite Performs org wide inventory of OmniScripts FlexCards Integration Procedures and Data Mappers with automated dependency graph construction and Mermaid visualization In scope Namespace detection Core vlocity_cmt vlocity_ins org wide component inventory dependency graph construction impact analysis Mermaid diagram generation Out of scope Authoring or modifying OmniScripts use building omnistudio omniscript building FlexCards use building omnistudio flexcard creating Integration Procedures use building omnistudio integration procedure configuring Data Mappers use building omnistudio datamapper Input Default if not provided Target org alias Ask the user Analysis scope Full org all OmniStudio component types Specific component to impact analyze None produce full inventory first Output format preference All three Mermaid diagram JSON summary human readable report Each analysis run produces one or more of1.9kinstalls74Building Omnistudio Flexcardbuilding omnistudio flexcard OmniStudio FlexCard Creation and Validation Expert OmniStudio engineer specializing in FlexCard UI components for Salesforce Industries Generate production ready FlexCard definitions that display at a glance information with declarative data binding Integration Procedure data sources conditional rendering and proper SLDS Salesforce Lightning Design System styling All FlexCards are validated against a 130 point scoring rubric across 7 categories In scope Creating and validating OmniStudio FlexCard definitions OmniUiCard configuring Integration Procedure data sources designing card layouts states and action buttons scoring against the 130 point rubric deployment and activation Out of scope Building OmniScripts use building omnistudio omniscript creating Integration Procedures use building omnistudio integration procedure mapping full dependency trees use analyzing omnistudio dependencies deploying metadata to org use deploying metadata 1 FlexCard Authoring Design and build FlexCard definitions with proper layout states and field mappings 2 Data Source Binding Configure Integration Procedure data sources with correct field mapping and error handling 3 Tes.1.9kinstalls75Modeling Omnistudio Epc Catalogmodeling omnistudio epc catalog CME EPC Product and Offer Modeling Expert Salesforce Industries CME EPC modeler for creating Product2 based catalog entries assigning configurable attributes and building offer bundles through Product Child Item relationships This skill is optimized for DataPack style metadata authoring Use the canonical template set in assets assets product2 offer template json assets attribute assignment template json assets product child item template json assets pricebook entries template json assets price list entries template json assets object field attributes template json assets orchestration scenarios template json assets decomposition relationships template json assets compiled attribute overrides template json assets override definitions template json assets parent keys template json Additional packaged examples are available under assets examples organized by offer type The modeling omnistudio epc catalog agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with.1.9kinstalls76Applying Cms Branddata360-query enables developers to retrieve and search data from Salesforce Data Cloud using SQL, async queries, vector search, and hybrid search workflows. This skill handles Data Cloud-specific retrieve operations including table describe, search-index lifecycle, and metadata introspection. It integrates with the sf data360 CLI plugin and requires a Data Cloud-enabled org. Developers use this when querying DMO/DLO tables, performing semantic search across indexed content, or inspecting Data Cloud object schemas. It delegates standard SOQL queries, segment design, and observability tasks to sibling skills.1.6kinstalls77Integrating B2b Commerce Open Code ComponentsThe integrating-b2b-commerce-open-code-components skill from Salesforce sf-skills guides agents building B2B Commerce buyer experiences with Open Code Components. Although the cached catalog doc may point at a sibling Data Cloud query skill, the listing targets B2B Commerce OCC integration: wiring Lightning Web Components into B2B storefront pages, extending product discovery, cart, checkout, and account self-service flows, and aligning with Salesforce Commerce APIs and org configuration. Agents gather org alias, storefront context, and whether work is component authoring, API integration, or deployment packaging. Workflows cover OCC project structure, commerce cloud SDK usage, authenticated buyer sessions, and delegation to platform SOQL or Data Cloud skills when the task shifts to CRM or Data Cloud SQL only. Use when users mention B2B Commerce Open Code Components, storefront LWC customization, or headless B2B buyer UI integration.1.6kinstalls78Generating Ui Bundle Custom AppThis skill generates Salesforce CustomApplication metadata records that expose React UI bundles in the Lightning App Launcher for internal user access. Developers use it when a uiBundles/ directory exists and they need to create a launcher entry without building a Digital Experience Site. The workflow resolves appName, appLabel, and appNamespace; queries the target org's API version to determine field compatibility (uiBundle vs. webApplication); generates the .app-meta.xml file in applications/; and optionally updates .uibundle-meta.xml with the target field. Step 2 ensures the metadata matches the org's Salesforce API version, preventing blank-page errors from mismatched bundle references.1.4kinstalls79Building Mobile Appsbuilding-mobile-apps is an agent skill from forcedotcom/sf-skills that salesforce data cloud retrieve phase. use this skill when the user runs data cloud sql, async queries, vector search, search-index workflows, or metadata introspection for data cloud objects. trigger . # data360-query: Data Cloud Retrieve Phase Use this skill when the user needs **query, search, and metadata introspection** for Data Cloud: sync SQL, paginated SQL, async query workflows, table describe, vector search, hybrid search, or search index operations. ## When This Skill Owns the Task Use `data360-query` when the work involves: - `sf da Developers invoke building-mobile-apps during build/integrations work for automation & workflows tasks. The skill documents triggers, prerequisites, and step-by-step workflows grounded in SKILL.md. Compatible with Claude Code, Cursor, and Codex agent runtimes that load marketplace skills.1.4kinstalls80Reviewing Lwc Mobile Offlinereviewing-lwc-mobile-offline is an agent skill from forcedotcom/sf-skills that review a lightning web component for **mobile offline** compatibility — the komaci offline static analyzer that pre-primes the data graph for salesforce mobile app plus and field service mobile app. p. # Reviewing LWC Mobile Offline Run a structured offline-priming compliance pass over a Lightning Web Component, producing a report of issues found and code-level fixes to bring the component into compliance with Komaci's static analysis requirements for the Salesforce Mobile App Plus and Field Service Mobile App. ## When to Use - The user asks f Developers invoke reviewing-lwc-mobile-offline during build/integrations work for automation & workflows tasks. The skill documents triggers, prerequisites, and step-by-step workflows grounded in SKILL.md. Compatible with Claude Code, Cursor, and Codex agent runtimes that load marketplace skills.1.3kinstalls81Using Mobile Native Capabilitiesusing-mobile-native-capabilities is an agent skill from forcedotcom/sf-skills that build a salesforce lwc that uses native mobile device capabilities — barcode scanner, biometrics, location, nfc, calendar, contacts, document scanner, geofencing, ar space capture, app review, and pay. # Using Mobile Native Capabilities The `lightning/mobileCapabilities` module exposes a set of factory functions that return service objects for native device features (barcode scanning, biometrics, location, etc.). Each service extends a common [BaseCapability](references/base-capability.md) with an `isAvailable()` method, so an LWC can degrade gr Developers invoke using-mobile-native-capabilities during build/integrations work for automation & workflows tasks. The skill documents triggers, prerequisites, and step-by-step workflows grounded in SKILL.md. Compatible with Claude Code, Cursor, and Codex agent runtimes that load marketplace skills. Review the Security Audits panel on this listing before installing in production environments.1.3kinstalls82Applying Sldsapplying-slds is a forcedotcom/sf-skills agent skill (version 1.0) for the Salesforce Lightning Design System, a CSS framework with thousands of UI artifacts. It teaches agents to choose between Lightning Base Components and SLDS Blueprints, apply styling hooks for theming, use utility classes for layout and spacing, and pick the right icons when building modals, forms, data tables, and other SLDS-styled surfaces. Developers reach for applying-slds whenever UI work must match Salesforce platform conventions rather than generic Tailwind or Bootstrap patterns. Triggers include phrases like build a modal, create a form, data table, SLDS styling, style with hooks, or add an icon inside Salesforce projects.945installs83Validating Sldsvalidating-slds is a Salesforce-focused agent skill that audits Lightning Web Components for SLDS compliance and returns a scored quality report. The skill runs the SLDS linter, analyzes CSS for theming hook usage and pairing, checks HTML for accessibility attributes, and aggregates findings into category scores with an overall grade. Developers reach for validating-slds when asked to score a component, produce an SLDS scorecard, audit compliance, or evaluate whether an LWC is ready to ship. Trigger phrases include "rate my component", "audit SLDS compliance", and "review my component before code review". Output includes a structured quality report suitable for manual review gating before submission.931installs84Investigating Agentforce Architectureinvestigating-agentforce-architecture produces a declared architecture snapshot for one Salesforce Agentforce agent from design-time metadata—not runtime session traces. It reads planner configuration, topics, actions, flows, Apex classes, prompt templates, and NGA plugins, then renders a human-readable architecture document plus a Mermaid invocation graph. Developers reach for it when asked to describe, diagram, inventory, audit, document, or diff agent architecture—such as v3 versus v5—by agent API name in a specific org. The skill explicitly excludes runtime conversation transcripts, generation timings, and gateway audit chains, focusing solely on metadata-defined action trees and tool inventories.847installs85Investigating Agentforce D360investigating-agentforce-d360 in forcedotcom/sf-skills targets Agentforce session investigation through Salesforce Data Cloud. The companion agentforce-d360-analyze skill (metadata version 1.0) runs a three-stage pipeline—fetch_dc.py, assemble_dc.py, render_dc.py—that queries up to 24 dc.<name>.json DMO exports plus manifest, tree, and markdown summary artifacts for one session UUID or 0Mw MessagingSession id. discover_sessions.py lists sessions by time, agent, channel, outcome, or grep before fetch. Typical wall-clock is about 10–30 seconds for a 15-turn session and requires sf CLI, Python 3.10+, and materialized STDM GenAI DMOs. Use it to trace escalations, walk transcripts, and audit gateway requests; it answers what happened in DC, not full runtime planner eligibility.833installs86Managing Managed Event Subscriptionmanaging-managed-event-subscription is a Salesforce sf-skills entry for creating, reading, updating, and deleting ManagedEventSubscription metadata. The skill handles managed event subscriptions, platform event subscriptions, event channel subscribers, and `.managedEventSubscription-meta.xml` files including replay preset configuration, activation, and deactivation. Developers reach for this skill when subscribing to platform events, setting up event replay, or managing subscription lifecycle—but skip it when creating the platform event channel itself (use generating-platform-event instead). Triggers include requests to subscribe to platform events or update replay presets.830installs