sshvarzman-salesforce/claude-skills

sf-agent-api-variables

Agent API context and custom variables — passing session context to an agent and configuring variable accessibility.

View source

How to use

  1. Copy the installation command and review the source package before installing it in your own agent environment.
  2. Check the source document for required tools, credentials and supported hosts.
  3. Describe your input and desired deliverable; review the output against the source material.
npx skills add https://github.com/sshvarzman-salesforce/claude-skills --skill sf-agent-api-variables

Before you start

  • Installation does not include a model subscription, API allowance or permission to access your files.
  • Repository stars and installation counts describe activity, not an independent quality or security test.
Original skill document

Rendered from the source repository. Headings, examples, code, tables, links, and referenced images are preserved.

Agent API Variables

Use This Skill When

  • Passing context variables ($Context.*) or custom variables in a start-session or send-message call.
  • Deciding which variables can be set at start vs edited mid-conversation.
  • Configuring variable API accessibility in Agentforce Builder or via Metadata API (ConversationVariable, ConversationContextVariable).

Concept

You can pass two kinds of variables so the agent can use them on subsequent turns:

  • Context variables — prefixed $Context. (for example $Context.EndUserLanguage). Predefined session context.
  • Custom variables — your own named values (for example team_descriptor, troubleshootingSteps).

Quick Start

Add a variables array to the start-session body (or a send-message body for editable variables):

json
{
  "externalSessionKey": "{RANDOM_UUID}",
  "instanceConfig": { "endpoint": "https://{MY_DOMAIN_URL}" },
  "streamingCapabilities": { "chunkTypes": ["Text"] },
  "bypassUser": true,
  "variables": [
    { "name": "$Context.EndUserLanguage", "type": "Text", "value": "en_US" },
    { "name": "team_descriptor", "type": "Text", "value": "The Greatest Team" },
    { "name": "troubleshootingSteps", "type": "Text", "value": "Complete this list of troubleshooting steps: 1. Confirm username/password. 2. ..." }
  ]
}

Each variable has name, type, and value.

Editability Rules

  • Many variables are read-only and can only be set during the start session call.
  • Context variables ($Context prefix) are not editable after the session starts — except $Context.EndUserLanguage.
  • Only editable variables can be modified during a send-message call.
  • When referencing variables derived from custom fields, omit the `__c` suffix. Example: Conversation_Key__c → $Context.Conversation_Key.

Variable Types

Text, Number, Boolean, Object, Date, DateTime, Currency, Id.

Configuring Accessibility

Agentforce Builder

When creating an agent variable, check Allow value to be set by API so the API can populate it.

Metadata API

Configure via ConversationVariable (in BotVersion/BotTemplate) and ConversationContextVariable (in Bot/BotTemplate).

Key fields:

FieldPurpose
dataTypeText, Number, Boolean, Object, Date, DateTime, Currency, Id
developerNameUnique name; starts with a letter, no spaces, no trailing underscore, no double underscores
labelHuman-readable label in the UI
descriptionUsed by the Agentforce planner service
includeInPromptWhether the variable is included in the prompt sent to the model
visibilityinternal = set only by action output; external = also settable by API (ConversationVariable only)

Do not change includeInPrompt for the default Id, EndUserId, and EndUserLanguage variables — doing so can block the agent from key session data.

Guardrails

  • To set a variable via API it must be external visibility (ConversationVariable) and "Allow value to be set by API" enabled.
  • Strip __c from custom-field-derived names, and use the $Context. prefix for context variables.
  • Don't try to mutate read-only/context variables after start (except $Context.EndUserLanguage) — the change is ignored.
  • Treat variable values as untrusted input downstream; validate before using in SOQL, HTML, or callouts.
  • Keep prompt-injected variables (includeInPrompt: true) minimal and non-sensitive.

Deliverables

  • A variable contract: name, type, context-vs-custom, set-at-start-vs-editable, and API accessibility.
  • Metadata definitions (ConversationVariable / ConversationContextVariable) for any API-settable variables.
  • A validation plan for how variable values are consumed downstream.

Additional Resources

Related by task

from this repository

More skills

All skills
sshvarzman-salesforce
Community

activating-datacloud

Salesforce Data Cloud Act phase. Use this skill when the user manages activations, activation targets, data actions, or downstream delivery of Data Cloud audiences and data. TRIGGER when: user manages activations, activation targets, data actions, or downstream delivery of Data Cloud audiences and data. DO NOT TRIGGER when: the task is segment creation (use segmenting-datacloud), data retrieval/search work (use retrieving-datacloud), or STDM/session tracing (use observing-agentforce).

installs
1
GitHub stars
0
Updated
Oct 15
sshvarzman-salesforce
Community

agentforce-skills-research

Research Agentforce configuration patterns — topics, actions, instructions, CLTs, knowledge, planner behavior. Searches Salesforce docs, Trailhead, internal repos (git.soma), Slack channels, and Google Docs to find working examples, known issues, and best practices.

installs
1
GitHub stars
0
Updated
Oct 15
sshvarzman-salesforce
Community

harmonizing-datacloud

Salesforce Data Cloud Harmonize phase. Use this skill when the user works with DMOs, mappings, relationships, identity resolution, unified profiles, data graphs, or universal IDs. TRIGGER when: user works with DMOs, mappings, relationships, identity resolution, unified profiles, data graphs, or universal IDs. DO NOT TRIGGER when: the task is only about streams/DLOs (use preparing-datacloud), segments/insights (use segmenting-datacloud), retrieval/search (use retrieving-datacloud), or STDM/sessio

installs
1
GitHub stars
0
Updated
Oct 15
sshvarzman-salesforce
Community

preparing-datacloud

Salesforce Data Cloud Prepare phase. Use this skill when the user creates or manages Data Cloud data streams, DLOs, transforms, or Document AI configurations. TRIGGER when: user creates or manages Data Cloud data streams, DLOs, transforms, or Document AI configurations, or asks about ingestion into Data Cloud. DO NOT TRIGGER when: the task is connection setup only (use connecting-datacloud), DMOs and identity resolution (use harmonizing-datacloud), or query/search work (use retrieving-datacloud)

installs
1
GitHub stars
0
Updated
Oct 15