agentforce-architectur…
Declared architecture snapshot for one Agentforce agent: planner, topics, actions, flows, Apex, prompt templates, and NGA…
Use this skill to configure Education Cloud domains (Student Success, Recruitment & Admissions, Academic Operations, Alumni Relations, Student Management, or Mentoring) through conversational setup. Triggers when a user wants to enable or configure Education Cloud features.
Claude Code
$ npx -y skills add forcedotcom/sf-skills --skill education-cloud-domain-configure --agent claude-code
Codex
$ npx skills add forcedotcom/sf-skills --skill education-cloud-domain-configure -a codex -y
Cursor
$ npx skills add forcedotcom/sf-skills --skill education-cloud-domain-configure -a cursor -y
Gemini CLI
$ npx skills add forcedotcom/sf-skills --skill education-cloud-domain-configure -a gemini-cli -y
GitHub Copilot
$ npx skills add forcedotcom/sf-skills --skill education-cloud-domain-configure -a github-copilot -y
OpenCode
$ npx skills add forcedotcom/sf-skills --skill education-cloud-domain-configure -a opencode -y
Windsurf
$ npx skills add forcedotcom/sf-skills --skill education-cloud-domain-configure -a windsurf -y
name: education-cloud-domain-configure
description: "Use this skill to configure Education Cloud domains (Student Success, Recruitment & Admissions, Academic Operations, Alumni Relations, Student Management, or Mentoring) through conversational setup. Triggers when a user wants to enable or configure Education Cloud features. Guides step-by-step: enables Person Accounts prerequisite, activates target domain, then configures domain sub-features. Covers support processes, case record types, success teams, care plans, applications, admissions, course catalog, alumni engagement, fundraising, enrollment, programs, and mentoring. Explains each feature, confirms before proceeding, verifies every change took effect, and warns that domain and feature toggles are IRREVERSIBLE. DO NOT TRIGGER for metadata generation, custom objects, or package deployment — this configures existing platform features via org settings, not metadata files."
metadata:
version: "1.1"
minApiVersion: "60.0"
domains:
- "Education"
cliTools:
- tool: ["python3"]
semver: ">=3.9.0"
- tool: ["sf"]
semver: ">=2.0.0"
relatedSkills:
- "platform-custom-field-generate"
- "platform-custom-object-generate"
- "platform-metadata-deploy"
- "platform-permission-set-generate"
- "platform-validation-rule-generate"
accessCheck: "OrgPermissions.EducationCloud"Guide users through conversational setup of Education Cloud domains. Enable Person Accounts prerequisite, activate target domain via Setup, and configure domain-specific sub-features with user confirmation at each step.
---
Gather before starting:
Defaults:
---
Every domain/sub-feature toggle lives on the `IndustriesSettings` settings file (NOT Core's `ORG_PREFERENCES` allowlist) and is **IRREVERSIBLE** (`false → true` only — warn before flipping, never promise a revert). Write sequence is always **READ (tooling GET by DurableId) → WRITE (`PUT /services/data/v68.0/headless/metadata` via the write-enabled `dispatch` tool) → cold-VERIFY (repeat the GET — `success:true` alone is not proof)**. Read `references/toggle-write-path.md` before any toggle write for the full endpoint table, exact `xmlRep` shape, the `DurableId` constant, and the confirmed failure classes (silent no-op, cold-verify 500s, license-gating).
---
1. **Feature-first framing.** Lead with the FEATURE NAME and a plain-language description of what it does for the customer (e.g. "Enforce Time Conflicts — prevents learners registering for course offerings with conflicting schedules") — not the toggle's API element name (`enableCosConflicts`). Keep the element name only in the technical/API-call subsection. 2. **Describe before toggling.** For every feature and sub-feature, include a one-line "What it does" so the customer understands what's being enabled before confirming. 3. **List sub-features + confirm.** When a domain has sub-features, enumerate all of them and ask the customer to confirm or exclude before proceeding. 4. **Announce every C/U/D.** Before any create/update/delete, state the operation and offer approve / reject / modify. 5. **Flag manual steps.** If a step can't be done via API, note it as manual and surface it at the end of the domain's configuration. 6. **Always cold-verify.** `success:true` on a write is not proof. Re-read state (GET on the record or settings object) and confirm the intended field/element value.
---
Before first call, probe transport health: `GET /services/data/vXX.X/limits` via headless-360 dispatch. 2xx → route all calls through it. On absent/4xx/5xx → probe other available transports (other Salesforce MCP, authenticated `sf` CLI, custom MCP) with the same read, use first healthy, announce it. None healthy → stop, ask user to connect one; never fabricate.
> **SOQL routes via headless-360 — pass the query through `queryParams`, NOT inline `?q=` in `url`** (inline 404s with `ROUTE_NOT_FOUND`). Call-shape detail: `references/gotchas-extended.md` ("Transport call shapes").
---
Five HXL widgets (`display_widget`: Intent, Review, Plan, Apply, Verify) visualize the workflow. Render each automatically at its checkpoint; never ask whether to show one. They are visual aids, never gates: if the host or org cannot paint them, continue in text. Compute every prop from live reads. A click on a row's action button (for example Enable) is the user's approval of that one item: no separate confirmation turn. Checkpoints, prop contracts, render call, and fallback: `references/setup-widgets.md`.
---
All Education Cloud domains require these foundation settings. Verify before proceeding to domain configuration.
> **Visual review.** After the Phase 0, 1, and 1.5 reads, render the 8 prerequisites once with `HxlSetupReview` (see Setup Widgets), then walk the pending items
This repository provides Salesforce agent skills, plugins, and sample apps for building applications.
Declared architecture snapshot for one Agentforce agent: planner, topics, actions, flows, Apex, prompt templates, and NGA…
Use this skill to Upgrade Einstein Bots into Agentforce agents end-to-end in a single pass, orchestrating per-bot Agent Spec…
Data Cloud 360° view of a single Agentforce session. TRIGGER when user asks to trace, inspect, summarize, or describe a specific…
Build, modify, audit, repair, optimize, debug, and deploy agents with Agentforce Agent Script. TRIGGER when: user creates,…
Analyze production Agentforce agent behavior using session traces and Data Cloud, and manage Agent Health Monitoring (AHM)…
Use to design an AI agent persona — identity, voice, tone, behavioral style, guardrails — and encode it into Agent Script (.agent…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.