agentleFS
SalesforceLabsSalesforceLabs/afls-for-claude/skills/lsc-next-best/SKILL.md

lsc-next-best

Skill10 starsChanged 29 days agoApache-2.0View on GitHub

Guides Life Sciences Cloud (LSC) Next Best configuration — NBC (Next Best Customer), NBA (Next Best Action), and NBM (Next Best Message). Use when user asks about Next Best Customer, Next Best Action, Next Best Message, TerritoryAccountScore, TerritoryAcctRcmdAction, TerritoryAcctProdMsgScore, NBC widget, NBA widget, NBM recommendations, or Einstein Studio predictive models for LSC.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Always call MCP tools to get sourced documentation: Do not answer from general knowledge alone.

    line 8
  2. Distinctive:

    Always include the citation line from the tool response in your answer.

    line 23
  3. Distinctive:

    When the user asks about configuring or enabling a Next Best feature, ask them which mode they prefer:

    line 29
  4. Distinctive:

    Default to guided setup when connected to an org, or documentation mode if no org is connected.

    line 34
  5. Very specific:

    DO NOT: use run_soql for Admin Console settings — use list_admin_settings

    line 75
  6. Very specific:

    DO NOT: use run_soql for mobile cache — use check_mobile_cache_status()

    line 76

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

How to Answer Next Best Questions

Always call MCP tools to get sourced documentation. Do not answer from general knowledge alone.

User asks about...Call this tool
NBC/NBA/NBM concepts, setup, best practicesget_lsc_module_docs({ module: "next-best-nbc-nba-nbm" })
Specific next best topic (widgets, Einstein Studio, etc.)search_lsc_knowledge({ query: "<topic>" })
Admin Console next best settingslist_admin_settings({ category: "NextBest" })
Trigger handler statuslist_trigger_handlers()
Object fields and relationshipsdescribe_sobject({ sobject: "TerritoryAccountScore" })
NBC data in the orgrun_soql({ query: "SELECT ... FROM TerritoryAccountScore ..." })
NBA data in the orgrun_soql({ query: "SELECT ... FROM TerritoryAcctRcmdAction ..." })
NBM data in the orgrun_soql({ query: "SELECT ... FROM TerritoryAcctProdMsgScore ..." })
Mobile cache statuscheck_mobile_cache_status()
Validation / auditaudit_mobile_config({ group: "next-best-config-check" })

Always include the citation line from the tool response in your answer.


Configuration Mode

When the user asks about configuring or enabling a Next Best feature, ask them which mode they prefer:

  1. Show me the documentation — call get_lsc_module_docs({ module: "next-best-nbc-nba-nbm" }) and present the relevant sections
  2. Walk me through it — configure it directly in their org step-by-step (guided setup below)

Default to guided setup when connected to an org, or documentation mode if no org is connected.

Guided Setup Workflow

Step 1: Check Current State

list_trigger_handlers()
list_admin_settings({ category: "NextBest" })

Step 2: Report Findings

Present a summary table of what's configured vs what's missing/disabled.

Step 3: Propose Changes

For each issue found, propose the fix and wait for user confirmation.

Step 4: Apply Changes (with user confirmation)

toggle_trigger_handler({ handlerName: "NextBestTriggerHandler", active: true })
update_admin_setting({ recordId: "...", fields: { ... } })

Step 5: Verify

Re-run checks from Step 1 to confirm everything is configured correctly.


Tool Usage Rules

Correct Object Names

CorrectWrong (NEVER use)
TerritoryAccountScoreNextBestCustomer__c, NBCScore__c, TerritoryAccountScore__c
TerritoryAcctRcmdActionNextBestAction__c, ActionRecommendation__c, TerritoryAcctRcmdAction__c
TerritoryAcctProdMsgScoreNextBestMessage__c, ProductMessage__mdt, TerritoryAcctProdMsgScore__c
ProductGuidance—
Territory2—
Product2—
LifeSciMarketableProduct—

Tool Restrictions

  • DO NOT use run_soql for Admin Console settings — use list_admin_settings
  • DO NOT use run_soql for mobile cache — use check_mobile_cache_status()
  • DO NOT suggest OmniStudio/FlexCard/OmniScript for mobile — NOT available on LSC Mobile iPad app
  • ProductGuidance type MUST be 'message' for NBM — NOT 'objective'
  • ActionType for NBA — only Visit or Email (Managed Event NOT supported in GA)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.