Manage Hierarchy Lookups Setup Task Guidance logo

Manage Hierarchy Lookups Setup Task Guidance

Organization
oracle
Manage Hierarchy Lookups Setup Task Guidance

Provides task-specific setup guidance for Manage Hierarchy Lookups under the Enterprise Profile functional area.

Overview

Publisheroracle
RepositoryFusion-Setup-Configuration-Registry
Skill nameManage Hierarchy Lookups Setup Task Guidance
Stars
112
Forks
26
Bundled files
7
LicenseUPL-1.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 7 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by oracle on GitHub. Read the source before you install it.

Installation

Install the Manage Hierarchy Lookups Setup Task Guidance AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/oracle/Fusion-Setup-Configuration-Registry/tree/main/pillars/cx/customer-data-management/enterprise-profile/manage-hierarchy-lookups
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/oracle/Fusion-Setup-Configuration-Registry.git /tmp/Fusion-Setup-Configuration-Registry
mkdir -p .claude/skills
cp -r /tmp/Fusion-Setup-Configuration-Registry/pillars/cx/customer-data-management/enterprise-profile/manage-hierarchy-lookups .claude/skills/oracle-manage-hierarchy-lookups-setup-task-guidance
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Manage Hierarchy Lookups Setup Task Guidance in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Manage Hierarchy Lookups Setup Task Guidance on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Manage Hierarchy Lookups Setup Task Guidance is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Manage Hierarchy Lookups

Purpose and routing

Manage the lookup values used by Customer Data Management hierarchy setup. Resolve an unambiguous natural request directly. Reuse core.fusion-api.apps-common for lookup operations, shared.setup-export.task-level-export for export, the shared validators for validation, and core.data-loader for every import. Do not implement task-local OAuth, HTTP transport, CSV processing, polling, or generic lookup CRUD.

Setup Task Skill Contract

  • task_code: HZ_MANAGE_HIERARCHY_LOOKUPS
  • task_name: Manage Hierarchy Lookups
  • parent_skill_id: cx.customer-data-management.enterprise-profile
  • pillar: CX
  • offering: Customer Data Management
  • functional_area: Enterprise Profile
  • functional_area_code: ORA_ASK_ENTERPRISE_PROFILE
  • available_flag: Y
  • export_import_supported_flag: Y
  • csv_export_import_supported_flag: Y
  • source_catalog: knowledge/setup-task-catalog/effective/setupTasksAll.json

Ownership and review

  • Owner: CX Customer Data Management pillar team.
  • Required functional reviewer: CX Customer Data Management Pillar Lead or hierarchy SME.
  • Required framework reviewer: FSCR A-Team/core reviewer.
  • Required functional-behavior reviewer: FSCR QA when read, mutation, validation, export, or import behavior changes.

Reviewer metadata is kept in the body because the current manifest schema permits owner_team but has no reviewer field.

Task-specific lookup baseline

Lookup typeMeaningConfiguration levelEvidence and restrictions
PARTY_HIERARCHY_TYPEParty Hierarchy TypeExtensible in the tested baseline; verify with the target GETOracle documents this type as the list updated after creating a hierarchy type. Protect seeded codes and require evidence from Manage Tree Structures before adding a custom code.
HZ_TREE_STATUSHierarchy StatusSystem in the tested baseline; verify with the target GETOracle documents this lookup as the Active/Inactive hierarchy-status LOV. Its association with this task comes from the developer-provided tested task scope, not from its HZ_ prefix.

Use the tested task-scope baseline for direct retrieval and require a current GET before claiming that either lookup or configuration level remains available in the target environment. Report a missing type as a baseline discrepancy and never infer additional task members from prefixes or modules. Adding a lookup value does not create a hierarchy definition, version, node, or hierarchy data. Read ora_reference_lookups.md for the official Oracle sources and evidence boundaries.

Supported operations

Natural requestSupport
Show hierarchy lookup types or valuesRead-only through the exact category resolved by core.fusion-api.apps-common; no approval required.
Retrieve one exact type or codeRead-only; require an exact match.
Add a hierarchy type codeConditional for a permitted custom PARTY_HIERARCHY_TYPE code after dependency, configuration-level, seed, and describe checks.
Change meaning, dates, or enabled stateConditional only for fields and custom codes permitted by current metadata.
Delete a custom hierarchy type codeConditional after destructive preview and approval.
Export setup dataSupported; route to shared.setup-export.task-level-export.
Validate setup dataRoute to both shared validators and apply task-local rules.
Import validated setup dataSupported through core.data-loader only after Task Hook validation of the exact immutable archive and separate explicit approval.

Never silently upsert. Reject custom codes beginning with ORA_. Never alter lookup identity, module, category, or seeded-code identity.

Manual field and operation restrictions

TargetCreateUpdateEnable or disableDelete
PARTY_HIERARCHY_TYPE Extensible custom codePermit only after exact hierarchy-type evidence, duplicate check, GET, and current describe validationPermit Meaning, Description, StartDateActive, EndDateActive, EnabledFlag, or DisplaySequence only when both Oracle configuration rules and current describe metadata allow the named fieldPermit only for a non-seeded custom code and a current writable EnabledFlagPermit only for a non-seeded custom code after destructive preview and approval
PARTY_HIERARCHY_TYPE seeded codeNoPermit only a wording change that current Oracle rules and describe metadata explicitly allow; otherwise refuseNoNo
HZ_TREE_STATUS System codeNoAt most a Meaning wording change, and only when current describe metadata confirms the field is writableNoNo

The REST schema lists more writable-looking attributes than a particular lookup's configuration level permits. Apply the stricter intersection of task scope, configuration-level rules, seeded-data protection, current describe metadata, and the user's named change. Do not update Tag or Module for Extensible or System lookups. Treat LookupType and LookupCode as immutable identity.

Treat a code as predefined seed data when current evidence reports LastUpdatedBy as SEED_DATA_FROM_APPLICATION; do not substitute naming conventions or CreatedBy guesses for that check.

CSV Export, Import, and Validation Workflow

CSVExportImportSupportedFlag is Y for this task.

  1. Export setup task data with shared.setup-export.task-level-export.
  2. Validate setup task data with shared.validation.setup-data-validator.
  3. Validate reference data with shared.validation.reference-data-validator.
  4. Route every import exclusively through core.data-loader.
  5. For an FSM ZIP, preserve the archive unchanged, require the exact case-sensitive member basename ASM_SETUP_CSV_METADATA.xml, and require exactly one metadata task identity equal to HZ_MANAGE_HIERARCHY_LOOKUPS.
  6. Let Core Data Loader prepare the final immutable upload artifact, then invoke its data-load Task Hook immediately before approval and upload. Require the Task Hook validation envelope to remain bound to that archive's SHA-256.
  7. Require the user's separate explicit approval of the exact immutable preview. Any source, archive, environment, task identity, validation result, or approval change restarts the Core Data Loader and Task Hook lifecycle.
  8. Core Data Loader owns UCM upload, initiation payload construction, endpoint and FSM routing selection, accepted-request reporting, and later status diagnostics. This pillar skill must not select an adapter, endpoint, loader routing field, or retry policy.

Use this task metadata:

  • Offering: Customer Data Management
  • Functional area / Setup Object: Enterprise Profile
  • Setup task name: Manage Hierarchy Lookups
  • Setup task code: HZ_MANAGE_HIERARCHY_LOOKUPS

Manual lookup workflow

  1. Resolve exactly one configured Fusion environment.
  2. GET the exact lookup type and exact code when applicable.
  3. Resolve the resource category and retrieve current describe metadata.
  4. Validate configuration level, seeded-code protection, hierarchy-type dependency, dates, reserved prefixes, and supported fields.
  5. Show one exact redacted method, endpoint, and payload preview.
  6. Require explicit approval for the named mutation.
  7. Send exactly one POST, PATCH, or DELETE through the shared REST transport. Never automatically retry a mutation.
  8. Verify with a separate GET and distinguish verified success, unverified success, refusal, and classified failure.

For create, explicitly send Upsert-Mode: false or omit the header so its documented default remains false. Never set it to true.

Privilege preflight

Before a live operation, verify all applicable access instead of relying on a role name alone:

  1. Require ORA_ASM_FUNCTIONAL_SETUPS_USER_ABSTRACT and access to the exact setup task for UI-backed setup work.
  2. Require the target role's task-specific Manage Hierarchy Lookups privilege. Current public Oracle documentation does not publish its code; use core.diagnostics.role-access-check or target-environment security evidence and fail closed when it cannot be confirmed.
  3. Require ORA_ASM_EXPORT_IMPORT_FUNCTIONAL_SETUPS_USER for task CSV export or import.
  4. Require authorization for the Standard Lookups REST resource and the exact lookup type. Treat a secured or unauthorized lookup as an authorization failure, not as an absent lookup.

Natural prompts

  • Show the Hierarchy Lookups in the configured environment.
  • Show the values for Party Hierarchy Type.
  • Show the hierarchy status values.
  • Add hierarchy type lookup code MY_CUSTOM_HIERARCHY with meaning My Custom Hierarchy.
  • Change the meaning of MY_CUSTOM_HIERARCHY to My Customer Hierarchy.
  • Disable MY_CUSTOM_HIERARCHY in Party Hierarchy Type.
  • Delete custom lookup code MY_CUSTOM_HIERARCHY from Party Hierarchy Type.
  • Export Manage Hierarchy Lookups setup data.
  • Validate and import this Manage Hierarchy Lookups export.

Error handling contract

Failure modes

Failure classExampleRecoverable behavior
input_validationMissing environment, invalid code, invalid date order, or changed artifactCorrect locally and restart from preflight; no side effect occurred.
catalog_or_metadata_mismatchTask flags, task scope, configuration level, or describe metadata differsStop and reconcile authoritative metadata; do not broaden scope.
approval_blockerCore Data Loader Task Hook did not issue a current validation envelope bound to the exact immutable archive SHA-256Stop before upload or initiation; rebuild and approve the immutable Data Loader preview.
auth_expired_or_invalidCached-token 401 or 403Refresh a repository-managed cached token once; never replace an explicitly supplied token.
authorization_or_privilege403 persists or task-specific privilege is absentStop and report the missing access; do not retry the operation.
transport_or_environmentDNS, VPN, connection, or environment-resolution failureRetry only a read with bounded shared-client policy; never retry a mutation automatically.
fusion_api_errorFusion rejects an approved requestReport redacted status, endpoint path, response summary, and ECID when available; stop.
process_timeoutExport or import exceeds the owning executor's wait windowStop polling and report TaskCode, ProcessId, last status, elapsed time, and the safe next-check path.
process_failedExport or import completes with errorsRetrieve and preserve ProcessLog or status evidence when available; return failure or partial failure.
artifact_persistenceZIP, validation result, run record, or token log cannot be savedPreserve safe diagnostics in a temporary location and report the intended project path.
approval_blockerPreview is missing, stale, declined, or changedDo not submit; regenerate the exact preview when inputs change.

Preflight, retry, timeout, and recovery

  • Preflight the exact environment, task code, catalog CSV flags, task membership, lookup type and code when applicable, configuration level, seeded evidence, supported fields, date order, privileges, immutable artifact hash, ZIP member safety, exact ASM_SETUP_CSV_METADATA.xml member, metadata task identity, current Task Hook validation envelope, destination path, and approval requirement.
  • Permit at most one cached-token refresh for a read. Use bounded retries only for read-only transient transport failures. Never automatically retry POST, PATCH, DELETE, CSV import, loader, or ESS submission.
  • Core Data Loader owns endpoint selection and any documented recoverable initiation behavior; this task skill must not override or duplicate that policy.
  • Delegate polling windows to the owning export or Data Loader service. On timeout, preserve the external identifier and safe resume stage rather than submitting a replacement process.
  • A manual lookup mutation has no automatic rollback. Reconcile uncertain completion with a separate GET. Request a new preview and approval for any compensating mutation.
  • For failed CSV work, preserve the immutable source ZIP, validation result, ProcessId, ProcessLog/status payload, successful business-object results, and an errors array when safe and when project_id is supplied.

Diagnostics, redaction, and approvals

Return status, stage, failure_class, message, recommended_action, environment identity, skill and task identity, redacted endpoint path, artifact references, ProcessId or ECID when available, completed checks, and verified side effects. Never print or persist credentials, tokens, authorization headers, token caches, full sensitive payloads, opaque signed URLs, or customer data. Require explicit approval bound to the displayed environment, operation, exact lookup identity or immutable ZIP, before/after values, expected impact, and preview fingerprint. Deletion, overwrite, force, mutation retry, import, and replacement submission always require fresh approval.

Synthetic golden scenarios

ScenarioSynthetic requestExpected result
Read baselineShow the Hierarchy Lookups in the configured environmentResolve one environment, GET the documented/tested types, report configuration levels and any task-scope discrepancy; no approval.
Protect System statusDisable ACTIVE in HZ_TREE_STATUSRefuse before preview because System codes can't have enabled state changed.
Missing hierarchy dependencyAdd MY_CUSTOM_HIERARCHY without Manage Tree Structures evidenceReturn an approval blocker before preview; do not invent or call an undocumented hierarchy-type endpoint.
Update custom meaningChange MY_CUSTOM_HIERARCHY meaning to My Customer HierarchyGET exact code, prove it is non-seeded, validate writable Meaning, preview one PATCH, require approval, submit once, and verify separately.
CSV validation failureImport a ZIP whose task identity isn't HZ_MANAGE_HIERARCHY_LOOKUPSRefuse before core.data-loader and report the task-identity mismatch.
Task-local import route selectionImport an exact-task FSM ZIP through a route selected by this pillar skillRefuse before POST; Core Data Loader owns endpoint, adapter, routing-field, and retry selection.
Missing Task Hook validation envelopeImport an exact-task FSM ZIP without an envelope bound to its current SHA-256Stop with approval_blocker; do not upload, initiate, or reconstruct an envelope.
Valid CSV routeValidate and import an immutable export for the exact taskValidate the exact archive and task identity, complete Core Data Loader Task Hook validation and separate approval, then let Core Data Loader execute once.

Persistence

Fail closed on ambiguity or missing task, category, dependency, describe, configuration-level, source-guidance, privilege, or import-readiness evidence. When project_id is supplied, register durable artifacts, record the skill run, update applicable project state, and append token usage using the manifest policy. Repository-only authoring does not create a project workspace.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Manage Hierarchy Lookups Setup Task Guidance AI skill do?

Provides task-specific setup guidance for Manage Hierarchy Lookups under the Enterprise Profile functional area.

Why use Manage Hierarchy Lookups Setup Task Guidance on TypingMind?

Because you install it once and use it with any model. Manage Hierarchy Lookups Setup Task Guidance is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Manage Hierarchy Lookups Setup Task Guidance in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/oracle/Fusion-Setup-Configuration-Registry/tree/main/pillars/cx/customer-data-management/enterprise-profile/manage-hierarchy-lookups. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Manage Hierarchy Lookups Setup Task Guidance?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Manage Hierarchy Lookups Setup Task Guidance?

As many as you like. As long as a model supports skills, you can use Manage Hierarchy Lookups Setup Task Guidance with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Manage Hierarchy Lookups Setup Task Guidance AI skill free?

Yes. It is published on GitHub by oracle under the UPL-1.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇