Manage Contact Lookups Setup Task Guidance logo

Manage Contact Lookups Setup Task Guidance

Organization
oracle
Manage Contact Lookups Setup Task Guidance

Provides task-specific setup guidance for Manage Contact Lookups under the Trading Community Foundation functional area.

Overview

Publisheroracle
RepositoryFusion-Setup-Configuration-Registry
Skill nameManage Contact 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 Contact 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/trading-community-foundation/manage-contact-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/trading-community-foundation/manage-contact-lookups .claude/skills/oracle-manage-contact-lookups-setup-task-guidance
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Manage Contact 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 Contact 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 Contact 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 Contact Lookups

Purpose

Provides task-specific setup planning, routing, export, import, and validation guidance for Manage Contact Lookups under Trading Community Foundation.

Setup Task Skill Contract

  • task_code: HZ_MANAGE_CONTACT_LOOKUPS
  • task_name: Manage Contact Lookups
  • parent_skill_id: cx.customer-data-management.trading-community-foundation
  • pillar: CX
  • offering: Customer Data Management
  • functional_area: Trading Community Foundation
  • functional_area_code: ORA_HZ_CDM_FOUNDATION
  • available_flag: Y
  • export_import_supported_flag: Y
  • csv_export_import_supported_flag: Y
  • source_catalog: knowledge/setup-task-catalog/effective/setupTasksAll.json

Usage

Use this skill when planning, sequencing, exporting, importing, or validating setup data for Manage Contact Lookups under Trading Community Foundation.

Setup Task Metadata

  • Task name: Manage Contact Lookups
  • Task code: HZ_MANAGE_CONTACT_LOOKUPS
  • Available: Y
  • Export/import supported: Y
  • CSV export/import supported: Y
  • CSV export/import routing: supported

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_CONTACT_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: Trading Community Foundation
  • Setup task name: Manage Contact Lookups
  • Setup task code: HZ_MANAGE_CONTACT_LOOKUPS

Inputs

  • natural_language_request
  • fusion_environment_context
  • lookup_type_or_meaning
  • lookup_code_and_named_changes
  • setup_data_artifact
  • project_id

Outputs

  • lookup_result
  • setup_data_result
  • diagnostics
  • skill_run_record
  • token_usage_record

Implementation Notes

Use the parent functional-area skill cx.customer-data-management.trading-community-foundation for functional-area sequencing and scope decisions. Track token usage for any generated project artifact or skill-run record using the manifest policy.

Ownership and review

  • Owner: CX Customer Data Management pillar team.
  • Functional reviewer: CX Customer Data Management Pillar Lead or a Trading Community Foundation SME.
  • Framework reviewer: FSCR A-Team/core reviewer.
  • QA reviewer: required when lookup read, mutation, validation, export, or import behavior changes.

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

Task-specific lookup baseline

Lookup typeMeaning or scopeConfiguration levelEvidence and restriction
RESPONSIBILITYResponsibilityUserConfirmed task member; Standard REST returned U.
HZ_SLS_CNTCT_AFFINITY_CODEAffinity of Sales ContactUserConfirmed task member; Standard REST returned U.
HZ_SLS_CNTCT_BUY_ROLE_CODEBuying Role of Sales ContactUserConfirmed task member; Standard REST returned U.
HZ_SLS_CNTCT_INFLUENCE_LVL_CDInfluence Level of Sales ContactUserConfirmed task member; Standard REST returned U.
CONTACT_ROLE_TYPEContact Role TypeUserConfirmed task member; Standard REST returned U.
DEPARTMENT_TYPEDepartment TypeUserConfirmed task member; Standard REST returned U.

Task membership was read from the configured Fusion task page, and every exact member was independently retrieved from standardLookups on 2026-08-07. Reconfirm category and configuration level with a current GET. Do not extend this inventory by inference. See ora_reference_lookups.md.

Supported and unsupported operations

RequestSupport
List lookup types belonging to this taskSupported for the six exact baseline members above.
Show codes and values or retrieve one exact codeRead-only, no approval, after exact task membership and lookup-category resolution.
Create a custom codeConditional for a confirmed User type or an allowed Extensible custom code after duplicate, seed, configuration, and describe checks.
Update meaning, description, dates, display sequence, or enabled stateConditional only for the named field at the strict intersection of Oracle configuration rules and current describe metadata.
Delete a codeConditional only for a proven custom code in a confirmed User or permitted Extensible type.
Export task setup dataSupported through shared.setup-export.task-level-export because the exact catalog CSV flag is Y.
Validate and import task setup dataSupported through core.data-loader only after shared validation, Task Hook validation of the exact immutable archive, and separate explicit approval.
Change lookup type/code identity, configuration level, category, module, tag, or seeded identityUnsupported unless an exact current Oracle contract explicitly permits the named field; otherwise refuse.

Never silently upsert. Reject a custom code beginning with ORA_. Treat CreatedBy == SEED_DATA_FROM_APPLICATION as seeded-origin evidence; use LastUpdatedBy only for audit and never guess seed status from a code name.

Configuration-level and manual mutation contract

  • All six confirmed members are Standard/User in the configured environment. Permit only REST-described Meaning, Description, DisplaySequence, EnabledFlag, StartDateActive, EndDateActive, and Tag updates; permit custom-code create/delete only when current metadata supports them and seed checks pass.
  • Protect LookupType, LookupCode, ModuleId, RestAccessSecured, CustomizationLevel, category, and seeded identity. Current GET and describe metadata remain binding.

Every manual mutation must:

  1. Resolve exactly one configured Fusion environment.
  2. GET the exact lookup type and exact code when applicable.
  3. Retrieve or use current cached describe metadata for the resolved resource family.
  4. Validate task membership, configuration level, CreatedBy seeded-origin evidence, dates, reserved prefix, and named writable fields.
  5. Show one exact redacted preview containing environment, method, endpoint, before/after values, payload, impact, and preview fingerprint.
  6. Require explicit approval bound to that environment, target, method, payload, and fingerprint.
  7. Send exactly one POST, PATCH, or DELETE through core.fusion-api.apps-common and core.fusion-api.rest-api-client.
  8. Never automatically retry a mutation and never enable upsert.
  9. Verify with a separate GET.
  10. Report verified success, unverified success, refusal, or classified failure distinctly.

Read-only listing and retrieval require no approval.

Task CSV export contract

Route export to shared.setup-export.task-level-export with exact TaskCode: HZ_MANAGE_CONTACT_LOOKUPS. The owning exporter must create one task CSV export, capture and monitor its ProcessId, download immutable FileContent only after success, retrieve ProcessLog after failure, and save the ZIP or diagnostic under the supplied project workspace. Do not implement export HTTP, polling, or ZIP processing here.

FSM ZIP validation and import contract

  1. Run shared.validation.setup-data-validator and shared.validation.reference-data-validator for task-local setup and reference checks.
  2. Route the import only to core.data-loader; this pillar skill supplies the exact task context and rules but never selects or invokes an import adapter or endpoint.
  3. Detect an FSM ZIP only when a member has the exact case-sensitive basename ASM_SETUP_CSV_METADATA.xml.
  4. Reject missing, duplicate, unreadable, encrypted, unsafe-path, or ambiguous metadata.
  5. Parse metadata without rewriting the archive and require exactly one task identity equal to HZ_MANAGE_CONTACT_LOOKUPS.
  6. Preserve the archive bytes and SHA-256 through validation, Task Hook preview, approval, and execution.
  7. After Core Data Loader prepares the final immutable upload artifact, require its data-load Task Hook to evaluate this task's compiled ora-resource rules and issue the validation envelope bound to the exact archive SHA-256.
  8. Require a later standalone explicit approval of that exact immutable preview. A changed source, archive, environment, task identity, rule result, or approval invalidates the envelope and restarts validation.
  9. Let Core Data Loader own UCM upload, FSM initiation routing and payload construction, accepted-request reporting, and any later status or ProcessLog retrieval. Do not reconstruct its envelope or locally choose an endpoint, adapter, routing field, or retry behavior.
  10. Submit only once under the current Core Data Loader contract. If Task Hook validation or approval is missing, stale, or mismatched, stop with approval_blocker before any POST.
  11. Treat a later Run Book or Journey updateProgress failure as a separate synchronization result. Do not change an accepted FSM import to failed, and never retry or resubmit the import because progress synchronization failed.

Natural prompts

  • Show the Contact Lookups in the configured environment.
  • Show the values for <lookup meaning or exact lookup type>.
  • Add lookup code <code> with meaning <meaning> to <lookup type>.
  • Change the meaning of <code> in <lookup type>.
  • Disable <code> in <lookup type>.
  • Delete custom lookup code <code> from <lookup type>.
  • Export Manage Contact Lookups setup data.
  • Validate and import this Manage Contact Lookups export.

Resolve an unambiguous request directly; do not ask the user to choose an internal operation name.

Error and diagnostic contract

Failure classUse
input_validationMissing environment, invalid code/date/flag, changed artifact, or unsafe ZIP.
catalog_or_metadata_mismatchTask membership, category, level, describe, exact TaskCode, CSV flag, or adapter contract cannot be proven.
auth_expired_or_invalidCached authentication rejected; refresh once only under repository cache policy.
authorization_or_privilegeAccess remains denied or the task/resource privilege is missing.
transport_or_environmentEnvironment, VPN, DNS, or connection failure. Retry only bounded reads.
fusion_api_errorFusion rejects the one approved request; report status and ECID when available.
process_timeoutExport/import polling window expires; preserve TaskCode, ProcessId, last status, and next-check path.
process_failedExport/import completes with errors; preserve ProcessLog/status and partial results.
artifact_persistenceA required ZIP, diagnostic, result, run record, or token log cannot be saved.
approval_blockerPreview is missing, stale, changed, or declined.

Durable diagnostics include status, stage, failure class, message, recommended action, environment, redacted endpoint, artifact references, ProcessId/ECID, completed checks, and verified side effects. Never persist credentials, tokens, authorization headers, customer data, signed URLs, or sensitive payloads.

Synthetic behavior checks

ScenarioExpected result
General read with incomplete membership evidenceReturn only confirmed types, label the inventory incomplete, and do not infer additions.
System-code state changeRefuse before preview unless the exact field is explicitly permitted by current rules and describe.
Custom-code updateExact GET, category/level/seed/describe validation, one preview, approval, one mutation, separate GET verification.
Wrong-task FSM ZIPRefuse before import because metadata does not equal HZ_MANAGE_CONTACT_LOOKUPS.
Task-local import route selectionRefuse before POST; Core Data Loader owns endpoint, adapter, routing-field, and retry selection.
Missing or stale Task Hook validation envelopeFail closed with approval_blocker; do not upload, initiate, or reconstruct an envelope.
Valid exact-task FSM archivePreserve bytes and hash, pass exact task context to Core Data Loader, complete Task Hook validation and separate approval, then let Core Data Loader execute once.

Persistence

When project_id is supplied, persist artifacts under the manifest paths, append a run record under project/{project_id}/state/runs, and append token usage under the shared token log. Repository-only authoring does not create a project workspace. Fail closed when required authority, membership, category, metadata, privilege, adapter, approval, or safe destination evidence is absent.

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 Contact Lookups Setup Task Guidance AI skill do?

Provides task-specific setup guidance for Manage Contact Lookups under the Trading Community Foundation functional area.

Why use Manage Contact Lookups Setup Task Guidance on TypingMind?

Because you install it once and use it with any model. Manage Contact 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 Contact 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/trading-community-foundation/manage-contact-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 Contact 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 Contact Lookups Setup Task Guidance?

As many as you like. As long as a model supports skills, you can use Manage Contact 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 Contact 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 👇