Total 58,631 skills
Showing 12 of 58631 skills
Use this skill when a Salesforce Administrator needs to create OR maintain an institutional hierarchy for Education Cloud by parsing organizational structure from a PDF, URL, text, or CSV. On a first run it creates System, Campus, College, and Department Account records linked via ParentId plus 1:1 Business Profile records. On later runs it reconciles the org's existing hierarchy against the desired structure and applies only the delta — adding new units, renaming, or moving a node under a different parent — never recreating what exists. TRIGGER when the user wants to set up, configure, build, update, restructure, or reorganize a multi-campus structure, institutional hierarchy, or account hierarchy with business profiles; or add, rename, or move a campus, college, or department. DO NOT TRIGGER for single-campus flat setups without hierarchy levels, one-off manual account creation, or non-Education-Cloud account management.
Use this skill when users need to create, generate, or validate Salesforce Custom Metadata Type metadata — the __mdt object, its fields, and its deployable records. Trigger when users mention custom metadata types, CMDT, __mdt objects, custom metadata records, .md-meta.xml files, or reference/config data that must ship between orgs. Also trigger for admin-maintained mapping, lookup, or crosswalk tables and field mappings ("map fields from A to B", code lookups) — config admins change without a code deploy belongs in a CMDT, never hardcoded in Apex or Flow — and when troubleshooting CMDT record/type deploy errors. DO NOT TRIGGER for Custom Settings — route to platform-custom-setting-generate; for regular custom objects holding business records — use platform-custom-object-generate; or for secrets and API keys — recommend a Named Credential, which this skill never generates.
Use this skill when users need to create, generate, or validate Salesforce Custom Setting metadata. Trigger when users mention custom settings (hierarchy or list), customSettingsType, SetupOwnerId, per-profile/per-user config overrides, feature flags, feature toggles, kill switches, or on/off switches admins flip to enable/disable behavior, e.g. bypass triggers/automation during a data load. Also use for "create a custom setting" or errors like "Cannot specify: pluralLabel for CustomSettings" or a setting that silently deployed as a regular custom object. A trigger bypass or kill switch is just a checkbox on a hierarchy custom setting — generate ONLY the setting, never an Apex trigger/handler. DO NOT TRIGGER for Custom Metadata Types or __mdt objects — route to platform-custom-metadata-type-generate; for business-record objects — use platform-custom-object-generate; for secrets, API keys, passwords, or tokens — recommend a Named Credential, never generated here.
Use to configure Salesforce Email-to-Case in a headless flow via the Metadata API. Reads the current CaseSettings, applies the desired emailToCase configuration with the updateMetadata CRUD call, and verifies by re-reading. Also the entry point when the user wants an Agentforce service agent on Email-to-Case: this skill configures the E2C base, then delegates agent creation and channel wiring. Start here even when no agent exists yet. TRIGGER when the user says set up Email-to-Case, configure email to case, enable Email-to-Case routing addresses, add an email routing address, Email-to-Case Metadata API, or set up Email-to-Case with an Agentforce service agent (attach an agent to an email routing address). DO NOT TRIGGER when the user needs the interactive Service Easy Setup wizard for E2cEasy addresses, when configuring On-Demand Email-to-Case only, for general Case object or web-to-case setup, or when only creating an Agentforce agent with no Email-to-Case involved.
Configure routing on a newly-inserted Enhanced `MessagingChannel` so that activation will accept it. Given a `{CHANNEL_ID}`, walks the user through picking a routing type (Omni-Channel Queue, Omni-Flow, Agentforce Service Agent, Digital Worker, or direct User), locates or provisions the routing target, then PATCHes the channel's `SessionHandlerId` (plus `FallbackQueueId` where required) to it. Use between the insertion skill and the activation skill — activation fails server-side with `nullQueueId` / `LiveMessageSetupException` if no valid `SessionHandlerId` is set on the channel.
Confirm the customer's WhatsApp Business Account is shared with Salesforce on Meta's side. Pure instruction + one user-confirmation prompt — no API calls, no token handling. The actual sharing happens in Meta Business Suite (UI-only; Meta provides no Graph endpoint to automate this step). Renders step-by-step instructions with Salesforce's Business Manager ID substituted in, then asks the user to confirm whether "Salesforce" appears in the WABA's Partners list.
Set up or align a repository's GitHub collaboration and delivery surface: repo settings, branch or ruleset policy, templates, Dependabot, Actions hardening, Environments, releases, publishing, and deploy workflows. Use for GitHub setup, CI/CD policy, protected delivery, package releases, or app deployment. Do not use for product architecture, provider infrastructure internals, application security review, or repository boot/readiness work.
Builds, fixes, styles, and composes UI with the Gravity UI design system — the React ecosystem of @gravity-ui/* packages (uikit, charts, table, navigation, date-components, icons, and more). Routes to the correct package when look-alikes exist, applies theming and required setup, and prevents invented component APIs. Applies when working with @gravity-ui imports, uikit, ThemeProvider, --g- CSS tokens, or any prompt (EN or RU) mentioning gravity-ui, гравити, дизайн-система, компоненты, дашборд, таблица, график, or форма.
Build, test, publish, invoke, schedule, and update Railcode managed agents with the Railcode CLI. Use when creating an organization or personal managed agent, editing an agent manifest (JSON or YAML), running a draft or saved agent, investigating a run, managing its cron schedule, running it from Slack (@Railcode $agent), pairing it with a companion app, processing files in its sandbox, or using personal connectors (Gmail, Slack, ...) on behalf of one owner. Do not use for static Railcode apps, in-app LLM tool loops (llm.generate({ tools }) — see create-railcode-app), or general organization administration.
Adds or modifies robot hardware integrations under physicalai.robot. Use when implementing the Robot protocol, SO101 or Trossen WidowX drivers, robot connect helpers, verify.py checks, optional extras so101 or trossen, or tests in tests/unit/robot.
Export a trained getitune model (the Geti training library) to a deployable format. Use when a user wants to run `engine.export(...)` or `getitune export`, choose between OpenVINO IR and ONNX, set FP32 vs FP16 precision with `ExportFormat` / `Precision`, or understand where exported artifacts are written and how they load back for inference. Covers the export/load contract between training and OpenVINO/ONNX inference.
Optimize an exported getitune model (the Geti training library) with post-training quantization. Use when a user wants to run `OVEngine.optimize()` / `engine.optimize()` to produce an INT8 model via NNCF, understands calibration-set requirements, or needs to re-validate and run inference with a quantized model versus the original FP32/FP16 model. Covers OpenVINO NNCF post-training quantization and the accuracy/size trade-off.