Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add BanibrataChatterjee/AwesomeSalesforceSkills --skill einstein-discovery-deploymentgit clone --depth 1 https://github.com/BanibrataChatterjee/AwesomeSalesforceSkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/banibratachatterjee/awesomesalesforceskills/einstein-discovery-deployment)<a href="https://agentmods.dev/skills/banibratachatterjee/awesomesalesforceskills/einstein-discovery-deployment"><img src="https://agentmods.dev/badge/skills/banibratachatterjee/awesomesalesforceskills/einstein-discovery-deployment/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/banibratachatterjee/awesomesalesforceskills/einstein-discovery-deployment"><img src="https://agentmods.dev/badge/skills/banibratachatterjee/awesomesalesforceskills/einstein-discovery-deployment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00120 | $0.03313 |
| Opus 5 | $0.00060 | $0.01656 |
| Sonnet 5 | $0.00024 | $0.00663 |
| Haiku 4.5 | $0.00012 | $0.00331 |
Grade A, and why
einstein-discovery-deployment scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Einstein Discovery Deployment
Use this skill when an admin needs to deploy a trained Einstein Discovery model declaratively — activating the prediction definition, mapping prediction output fields to record pages, configuring the Einstein Discovery Action in Flow, and monitoring model health in Model Manager. This skill covers the declarative admin path only. For developer API integration (Connect REST API, bulk scoring via code, programmatic model refresh), use agentforce/einstein-discovery-development.
Before Starting
Gather this context before working on anything in this domain:
- License confirmation: Einstein Discovery requires a CRM Analytics (formerly Tableau CRM) license. Confirm the license is provisioned before attempting any deployment step.
- Story readiness: The Einstein Discovery story must be complete and have at least one model in Enabled status. You cannot create a prediction definition from a story that has no trained model.
- Prediction definition ID: Every deployment step centers on the prediction definition (prefix
1OR). Locate it in Setup > Prediction Definitions or in the Model Manager. Do not confuse this with the story ID or the model ID. - Scoring is NOT automatic: Changing field values on a record does NOT automatically update its prediction score. Bulk predict jobs must be run explicitly to refresh scores. Plan scheduled jobs accordingly.
- Model refresh does NOT auto-activate: After a model refresh job completes, the new model version is NOT automatically used for scoring. An admin must explicitly set the new version as active on the prediction definition before scoring picks it up.
Core Concepts
Prediction Definitions and Activation
A prediction definition (prefix 1OR) is the deployable artifact that links a trained Einstein Discovery model to a Salesforce object and exposes output fields (predicted value, top factors, improvement actions) that can be written to records. A prediction definition can have multiple model versions; exactly one version is designated active at any time. The active model is the one used for all scoring — bulk jobs and Flow actions.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 213 lines · 120 tokens per session scan A bf6527875010
einstein-discovery-deployment is a skill published in the GitHub repository BanibrataChatterjee/AwesomeSalesforceSkills (3 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 120 tokens to every session and 3,313 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
analytics-adoption-strategy
Use this skill when driving adoption of CRM Analytics (Einstein Analytics) across an org — the Analytics Adoption App for measuring who uses which dashboards, embedding analytics into Lightning pages, pinning dashboards to the Analytics home page, self-service personas, and analytics success metrics. Triggers…
analytics-data-manager
Use this skill when configuring Data Manager in CRM Analytics: enabling objects for sync, scheduling data sync runs, setting up remote connections to external databases, monitoring sync status and error logs, or troubleshooting connected object issues. Trigger keywords: data sync, connected objects, Data Manager, sync…
analytics-permission-and-sharing
Configure CRM Analytics (formerly Einstein Analytics) app sharing, dataset-level permissions, row-level security predicates, sharing inheritance, and license assignment. Trigger keywords: CRM Analytics security, row-level security predicate, dataset permissions, analytics sharing inheritance, Analytics Plus license.…
analytics-dashboard-design
Use when designing or troubleshooting CRM Analytics dashboards — chart types, bindings, faceting, dashboard interactions, mobile layout, and filters. NOT for standard Salesforce reports and dashboards — use admin/reports-and-dashboards-fundamentals. NOT for hand-editing dashboard JSON or a SAQL step — use…
analytics-dashboard-json
Use this skill when editing CRM Analytics dashboard JSON directly to implement advanced bindings, custom SAQL/SOQL step queries, layout changes, step parameters, or cross-widget interactions. Trigger keywords: dashboard JSON, SAQL step, binding syntax, mustache binding, dashboard REST API, widget layout, step limit…
analytics-dataflow-development
Use this skill when building, debugging, or optimizing CRM Analytics dataflows — defining node types (sfdcDigest, Append, Augment, computeExpression, computeRelative, Flatten, dim2mea, sfdcRegister), scheduling runs, handling run failures, and tuning performance. NOT for doing the same transformation in a Data Prep…