consumer-goods-tpe-datakit-deploy

consumer-goods-tpe-datakit-deploy is a skill for Claude Code, Codex from forcedotcom/sf-skills. It costs 96 tokens per session (3,694 once invoked), scanned A, original, Apache-2.0.

A deployment tool for the TPM Accruals Data Kit, a package of data components used by Trade Promotion Effectiveness dashboards in Salesforce.

In plain words
What is it for?
Use it to install the TPM Accruals Data Kit and its data mappings in a Salesforce Data Cloud organisation.
Why use it?
It avoids manually installing the required data components and their links to Salesforce data objects. It can check the organisation and show what would change before deployment.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to install the TPM Accruals Data Kit and its data mappings in a Salesforce Data Cloud organisation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/forcedotcom/sf-skills/consumer-goods-tpe-datakit-deploy
About the project

forcedotcom/sf-skills is a collection of reusable instructions that help AI coding agents build and work with Salesforce applications and platform features. Developers use it for Agentforce agents, Lightning apps, Flow, Apex, SOQL, Lightning Web Components, and related Salesforce configuration. The catalogue entries are the repository’s skills, plugins, commands, MCP servers, and agents for AI tools that support skills.

forcedotcom/sf-skills · 1,097 stars · on GitHub

Install

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.

Any agent
npx skills add forcedotcom/sf-skills --skill consumer-goods-tpe-datakit-deploy
Clone the repo
git clone --depth 1 https://github.com/forcedotcom/sf-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for consumer-goods-tpe-datakit-deploy

README.md
[![agentmods](https://agentmods.dev/badge/skills/forcedotcom/sf-skills/consumer-goods-tpe-datakit-deploy/github.svg)](https://agentmods.dev/skills/forcedotcom/sf-skills/consumer-goods-tpe-datakit-deploy)
Your own site
<a href="https://agentmods.dev/skills/forcedotcom/sf-skills/consumer-goods-tpe-datakit-deploy"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/consumer-goods-tpe-datakit-deploy/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.

agentmods 80×15 button for consumer-goods-tpe-datakit-deploy

Your own site · 80×15
<a href="https://agentmods.dev/skills/forcedotcom/sf-skills/consumer-goods-tpe-datakit-deploy"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/consumer-goods-tpe-datakit-deploy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,694 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 145
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium Excessive Agency · line 92
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 149
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00096 $0.03694
Opus 5.5 $0.00038 $0.01478
Sonnet 5.5 $0.00019 $0.00739
Haiku 4.5 $0.00010 $0.00369

Measured 9d ago against content hash 8bda4d6d97cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

consumer-goods-tpe-datakit-deploy 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.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/detect-namespace.js, scripts/download-static-resource.js, scripts/extract-crm-field-permissions.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/consumer-goods-tpe-datakit-deploy/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TPE Data Kit Deploy

Deploys the TPM Accruals Data Kit and its DMO mappings into a Salesforce org. Standalone and self-contained — runs on its own, or as a delegated step invoked by consumer-goods-tpe-dashboard-configure (Step 7), which passes through its own already-collected username and dry-run flag rather than this skill re-deriving them.

Inputs to collect first

Ask before starting, unless already supplied by a calling skill. Do not guess.

  1. TPM System Admin username — already authenticated via sf CLI. Verify via the sibling script, never sf org display --json directly — that command's raw output includes accessToken (a live credential), which this script strips before printing:
    node ./scripts/sf-rest.js org-status --target-org <username>
    
    Prints {"username","alias","connectedStatus","orgId"}. Non-zero exit or connectedStatus != "Connected" ⇒ stop, ask the user to log in themselves.
  2. Dry-run? — offer by default. In dry-run, Phase 1 (preflight) and Phase 2's read/diff steps still run; Phase 2's FieldPermissions writes and Phases 3-5 (deploy) are skipped and recorded as pending — not run (dry-run).
  3. TPM Data Connector installed and active — cannot be verified programmatically. Ask the user, spelling out the exact navigation steps rather than just naming the setting: "Can you confirm the TPM Data Connector is Active? 1) Go to Setup → Data Cloud Setup. 2) In the left nav, under EXTERNAL INTEGRATIONS, click Other Connectors. 3) Find 'TPM Data Connector' in the list and check its status." Wait for an explicit yes. If missing or inactive, stop — tell the user we cannot proceed without the TPM Data Connector being active, and explain the two different paths depending on org type:
    • Production orgs — it's typically auto-installed within ~24h of Processing Service pairing, provided the org has a Data Cloud license. If both prerequisites are met, ask the user to wait and retry; if either isn't met (no pairing yet, or no Data Cloud license), that's the real blocker to resolve first.
    • Sandbox orgs — auto-install commonly does not happen; it typically needs to be activated manually under EXTERNAL INTEGRATIONS → Other Connectors. Tell the user this is expected in sandboxes and ask them to activate it there, then confirm before continuing. Re-run this check once the user confirms it's Active.
  4. Salesforce CRM Home org connection — cannot be verified programmatically. Ask the user, spelling out the exact navigation steps: "Can you confirm the Salesforce CRM Home org connection is Active? 1) Go to Setup → Data Cloud Setup. 2) In the left nav, under SALESFORCE INTEGRATIONS, click Salesforce CRM. 3) Check that the Home org connection status is Active." Wait for an explicit yes. If missing/inactive, stop — tell the user we cannot proceed without this connection being active (Phase 2's field-permission grants require the Data Cloud Salesforce Connector permission set, which won't exist until this connection is configured) — ask them to activate/configure it first, then re-run this check.
  5. Permission set(s) for the TPM Admin persona + GenieAdmin permission set confirmed assigned — when invoked as a delegated step from consumer-goods-tpe-dashboard-configure, it passes through both results already confirmed in its own earlier phases; reuse them, don't re-ask or re-query. When invoked standalone, confirm each directly:
    • Permission set(s) for the TPM Admin persona — "TPM Admin persona" is a role, not an actual permission set name; the org-specific permission set backing that persona (name/assignment) cannot be verified programmatically. Ask the user to confirm: "Is the permission set(s) required for the TPM Admin persona assigned to <username>?" Wait for an explicit yes.
    • GenieAdmin — resolve its Label first (never show the API Name to the user), then check the assignment:
      sf data query --target-org <username> --query "SELECT Label FROM PermissionSet WHERE Name = 'GenieAdmin'"
      sf data query --target-org <username> \
        --query "SELECT PermissionSet.Name FROM PermissionSetAssignment WHERE Assignee.Username = '<username>' AND PermissionSet.Name = 'GenieAdmin'"
      
      Missing ⇒ tell the user the Label from the first query (e.g. "User <username> is missing the <Label> permission set. Assign it now?") and ask permission to assign before continuing:
      sf data create record --sobject PermissionSetAssignment \
        --values "AssigneeId=<userId> PermissionSetId=<psId>" --target-org <username>
      
      If declined, skip and note it in the report.
  6. Namespace (NS) — when invoked as a delegated step, consumer-goods-tpe-dashboard-configure passes through its already-detected NS (raw namespace string); reuse it, don't re-detect. When invoked standalone, detect it once yourself, before Phase 1, with the sibling script:
    node ./scripts/detect-namespace.js --target-org <username>
    
    Prints {"NS","NS_SEGMENT","NS_APEX","NS_FIELD"} as one line of JSON. Store all four and reuse everywhere below.

Read the full file on GitHub · 159 lines

Files

What ships with it

5 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.

Changes

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.

  1. 9d ago Changed · +1 lines 8bda4d6d97cf
  2. 1mo ago First seen · 158 lines · 96 tokens per session scan A db8858ba3d74

Subscribe to this mod's changes

consumer-goods-tpe-datakit-deploy is a skill published in the GitHub repository forcedotcom/sf-skills (1,097 stars, last pushed today), licensed Apache-2.0. It adds 96 tokens to every session and 3,694 once invoked, about $0.0004 per session on Opus 5.5. 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.

Related

Other skills, from other repositories

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…

google/skills · 132 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens

finetuning

Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file…

microsoft/skills · 132 tokens