lsc-implementation-review
Skill10 starsChanged 29 days agoApache-2.0View on GitHub
Reviews an Life Sciences Cloud (LSC) / Life Sciences Cloud implementation against field-observed anti-patterns that cause production incidents and blocked go-lives — sharing model, sample/inventory, mobile sync, over-customization, territory realignment, data/MDM, Agentforce scoping, and UAT/go-live discipline. Use when the user asks to review, assess, health-check, or de-risk an implementation or design; is planning a go-live; is deciding whether to add a custom object or change an OWD/permission; or is diagnosing a post-go-live incident (Sev-1, API limits, duplicate records, inventory-count failures). Also use proactively when a proposed configuration matches a known anti-pattern.
In this repository39 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- roz-uiSkill
- lsc-account-managementSkill
- lsc-activity-planSkill
- lsc-agentforceSkill
- lsc-app-alertsSkill
- lsc-briefingsSkill
- lsc-calendar-tot-routineSkill
- lsc-config-migrationSkill
- lsc-consent-managementSkill
- lsc-custom-scriptsSkill
- lsc-data-migrationSkill
- lsc-data-modelSkill
- lsc-db-schemaSkill
- lsc-demo-data-loadingSkill
- lsc-events-managementSkill
- lsc-field-emailSkill
- lsc-health-checkSkill
- lsc-home-page-configurationSkill
- lsc-implementationSkill
- lsc-integration-patternsSkill
- lsc-intelligent-contentSkill
- lsc-key-account-managementSkill
- lsc-lists-filtersSkill
- lsc-mobile-app-settingsSkill
- lsc-mobile-validationSkill
- lsc-next-bestSkill
- lsc-performance-validationSkill
- lsc-product-managementSkill
- lsc-provider-engagement-complianceSkill
- lsc-quick-actions-configurationSkill
- lsc-reporting-analyticsSkill
- lsc-sample-managementSkill
- lsc-surveysSkill
- lsc-territory-alignmentSkill
- lsc-troubleshootSkill
- lsc-user-managementSkill
- lsc-visit-managementSkill
- salesforce-querySkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 47
Recommend remediation before go-live, not after: If several checklist items fail, say plainly that the program matches the recurring …
- Distinctive: line 51
Never widen access as a first resort: Before any OWD change or "View All" grant on a core LSC object, establish what platform logic depends …
≈ “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.
Files
What this skill covers
Catching implementation design decisions that repeatedly cause LSC production incidents, blocked go-lives, and eroded trust — before they ship. The recurring root cause is trial-and-error configuration against LSC's opinionated, pre-built data model without validating consequences in a production-like sandbox.
The authoritative content is the anti-pattern catalog. Load it first:
get_lsc_troubleshooting({ topic: "implementation-anti-patterns" })For background on any specific area, also use
search_lsc_knowledge({ query: "..." }).
When to activate
- The user asks to review / assess / health-check / de-risk an implementation or a proposed design.
- The user is planning a go-live or asking "are we ready?".
- The user proposes a change that matches a known anti-pattern — flag it proactively:
- Changing an OWD (especially Visit) to Public/Controlled-by-Parent.
- Granting "View All" / "Modify All" on Visit, ProductDisbursement, or inventory objects.
- Adding a custom object or a non-standard screen that shadows standard LSC objects.
- Proposing OmniStudio for anything in the mobile scope (it is web-only).
- Setting a very short mobile sync interval or enabling attachments on every DB Schema record.
- Rolling out Agentforce before the data foundation / MDM is ready.
- The user is diagnosing a post-go-live incident (Sev-1, API-limit "death loop", duplicate visits, reps unable to submit inventory counts). Treat these as config/design issues first, product bugs last — historically ~90% are config/knowledge gaps.
How to run a review
- Load the catalog (
get_lsc_troubleshooting({ topic: "implementation-anti-patterns" })) and work its Pre-Go-Live Review Checklist. - Inspect the live org where possible rather than asking. Useful tools:
- Sharing/visibility & permissions →
describe_sobject,list_permission_sets,check_user_config. - Mobile sync & cache →
list_db_schema/get_db_schema(attachment flags, SOQL filters),check_mobile_cache_status. - Data model bloat → look for custom objects shadowing standard ones (
Visit,ProductDisbursement,ProviderVisit, etc.). - Territory →
check_territory_config. - Overall →
health_check,get_org_status.
- Sharing/visibility & permissions →
- Map findings to anti-patterns. For each finding, state: the pattern, why it fails on the LSC data model, and the correct approach — straight from the catalog.
- Prioritize by go-live risk. Sharing-model and mobile-sync issues that can cause Sev-1 or block regulated reporting rank first.
- Recommend remediation before go-live, not after. If several checklist items fail, say plainly that the program matches the recurring failure profile and remediation should precede go-live.
Guardrails
- Never widen access as a first resort. Before any OWD change or "View All" grant on a core LSC object, establish what platform logic depends on that object's ownership/sharing (inventory counting keys off ProductDisbursement ownership; Visit is designed to be Private).
- Default to standard config. Require a written justification for each custom object; prefer standard layouts/actions.
- OmniStudio is web-only — never propose it for mobile/iPad.
- UAT on a full-copy sandbox on production's release, with production-scale data. Off-release or partial sandboxes hide exactly these defects.
- These lessons are de-identified and generalized — describe the pattern and the fix, not any customer or partner.
Related
lsc-troubleshoot— symptom-driven module troubleshooting.lsc-health-check//lsc:health-check— config-completeness verification.lsc-config-migration— safe promotion of config between orgs (revert experiments; don't migrate everything).- Catalog:
knowledge/troubleshooting/implementation-anti-patterns.md.
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
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.

