platform-tracing-agentforce-configure

Name: platform-tracing-agentforce-configure
Author: forcedotcom

github.com/forcedotcomCloud & DevOps1.1k5.2k installsUpdated 1d ago

About platform-tracing-agentforce-configure

A skill for generating Salesforce metadata to enable or disable forwarding Agentforce execution trace spans to Data Cloud. It configures the single `enableAgentforcePlatformTracing` setting.

Key features

01Set Agentforce tracing state
02Generate tracing settings metadata
03Limit configuration to one boolean field
04Check Data Cloud, permission, and API prerequisites

Use cases

01Forward Agentforce traces to Data Cloud
02Stop forwarding Agentforce traces

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/forcedotcom/sf-skills --skill platform-tracing-agentforce-configure

After installing, type/platform-tracing-agentforce-configurein Claude Code to confirm it loaded.

Bundled filesassets/AgentforcePlatformTracing-template.xml

Details

From the project README

Platform Tracing — Agentforce Configure

Generate AgentforcePlatformTracingSettings metadata to enable or disable forwarding of Agentforce agent execution trace spans to Data Cloud's ingestion pipeline. This is a singleton Settings type with one boolean field introduced in API v68.0 (Spring '25).

Scope

In scope: Generating AgentforcePlatformTracing.settings-meta.xml to enable or disable Agentforce agent tracing.
Out of scope: Platform Tracing for TraceSpanEvent (use platform-tracing-configure). Event Log Files. Change Data Capture. Org permission provisioning. Data Cloud provisioning.

Prerequisites

Before generating, inform the user of these requirements. The skill cannot check org state, but deploying without these prerequisites means the setting has no effect:

Data Cloud must be provisioned in the org — trace spans are forwarded to Data Cloud's ingestion pipeline. Without Data Cloud, there is no destination for the spans.
PlatformObservability org permission must be active — this permission gates the feature. It is provisioned (not settable via metadata).
API version 68.0+ — the AgentforcePlatformTracingSettings type was introduced in Spring '25. Orgs on older API versions will not recognize it.

If the user reports the setting isn't working after deploy, the most likely cause is a missing prerequisite above.

Clarifying Questions

Before generating, confirm with the user if not already clear:

Enable or disable? (Which state do you want for Agentforce agent tracing?)

No other clarification needed — this is a singleton type with one boolean field.

Required Inputs

Gather or infer before proceeding:

Desired state: true (enable) or false (disable)

Defaults unless specified:

If user says "enable" or "turn on": set to true
If user says "disable" or "turn off": set to false

If the user provides a clear request, generate immediately without unnecessary back-and-forth.

Workflow

Warn about prerequisites — inform the user that this feature requires Data Cloud and the PlatformObservability org permission.
Read the template — load assets/AgentforcePlatformTracing-template.xml.
Generate the settings file — replace {ENABLED} with true or false based on the user's desired state.
Place the file — output to settings/AgentforcePlatformTracing.settings-meta.xml in the project's source directory.

Rules / Constraints

Constraint	Rationale
Singleton — only one file per org, one boolean field	The metadata type has exactly one instance. Deploying the file sets the org-wide preference.
XML namespace must be `http://soap.sforce.com/2006/04/metadata`	Any other namespace causes deploy failure.
File must be named `AgentforcePlatformTracing.settings-meta.xml`	SFDX source format convention for this Settings type.
Only include `enableAgentforcePlatformTracing` field	No other fields exist on this type.
Requires API v68.0+	Older orgs reject the metadata type entirely.

Gotchas

Issue	Resolution
Deploy succeeds but tracing doesn't activate	Org lacks `PlatformObservability` permission or Data Cloud is not provisioned. These are provisioned, not settable via metadata.
`AgentforcePlatformTracingSettings` type not recognized	Org or tooling is on API version < 68.0. Update `sfdx-project.json` sourceApiVersion.
User confuses this with Platform Tracing (TraceSpanEvent)	Clarify: this sends Agentforce agent execution spans to Data Cloud. For TraceSpanEvent publishing, use the `platform-tracing-configure` skill.

Output Expectations

Deliverables:

settings/AgentforcePlatformTracing.settings-meta.xml

Before delivering, verify:

XML namespace is exactly http://soap.sforce.com/2006/04/metadata
File is named AgentforcePlatformTracing.settings-meta.xml
Only enableAgentforcePlatformTracing is present (no extra fields)

Cross-Skill Integration

Need	Delegate to
Enable TraceSpanEvent publishing (Platform Tracing)	`platform-tracing-configure` skill
Query or analyze existing Agentforce agent trace data in Data Cloud	`agentforce-observe` skill
Set up Change Data Capture	`integration-eventing-cdc-configure` skill
Configure ManagedEventSubscription	`integration-eventing-subscription-configure` skill

Reference File Index

File	When to read
`assets/AgentforcePlatformTracing-template.xml`	Step 2 — template for generating the settings file

Comments

Markdown supported

Details

Author: forcedotcom
Repository: forcedotcom/sf-skills
Category: Cloud & DevOps
Installs: 5,198
GitHub stars: 1,127

Report

More skills

All skills

lark-apps

open.feishu.cn

732.0k

Develop and host Miaoda (Spark/Miaoda) apps: app creation, local full-stack development, cloud generation and iteration, creative design (UI mockups / interactive prototypes / wireframes / landing pages / dashboards / slide decks / visual exploration), integration of AI-related capabilities, Feishu platform capabilities, or other external capabilities; log/Trace/monitoring metric/PV/UV queries; environment variable management; app collaborators and collaboration permissions; app roles and members; and automation triggers (scheduled / record changes / Webhook / Feishu approvals). Use when users want to develop or create a system, tool, platform, or app; develop locally or in the cloud, modify, deploy, publish, launch, or get a shareable link; create a page or website with HTML and deploy it to Miaoda; design, create a mockup, prototype, wireframe, PPT, deck, or visual exploration; or mention Miaoda/Spark/Miaoda apps (links like `/app/app_xxx` or `/page/<token>`, runtime domains like *.aiforce.cloud), app databases, app file storage, open API Keys, visibility, app collaborators/developer permissions, app roles/role members, production logs, API request volume, error volume, latency, traffic, environment variables, or setting up automation tasks, scheduled triggers, or approval-triggered automation for Miaoda apps. Not for regular cloud drive file uploads (lark-drive), Feishu document editing (lark-doc), or native slide creation (lark-slides).

azure-prepare

github.com/microsoft

571.7k

Prepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Terraform), and Dockerfiles for the Azure Developer CLI (azd) workflow. USE ONLY when the user explicitly wants to use azd as the deployment tool, or the project already has an azure.yaml file. DO NOT USE FOR: non-azd deployments, Python App Service code-only deploys (use python-appservice-deploy), or cross-cloud migration (use azure-cloud-migrate). WHEN: prepare app for azd, create azure.yaml, set up azd infrastructure, modernize app for Azure with azd, deploy with azd, function app, timer trigger, service bus trigger, event-driven function, managed identity, generate Bicep, generate Terraform, create and deploy to Azure.

wizard

github.com/mattpocock

571.5k

Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.

azure-ai

github.com/microsoft

571.2k

Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.