# Manage Duties

> Prepare custom duty creation, updates, deletion and redesign requests from user requirements or FSM templates; validate and execute supported Manage Duties changes through approval-gated Data Loader imports.

- Skill: `oracle/manage-duties` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx get-skill add oracle/manage-duties`
- Raw SKILL.md: https://api.skillmd.com/api/skills/oracle/manage-duties/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Security
- Author: Oracle (https://skillmd.com/u/oracle)
- Updated: 2026-11-18
- Page: https://skillmd.com/skills/oracle/manage-duties

---


# Manage Duties

## Purpose

Provide a controlled, cross-pillar method to export, validate, and
approval-gate the import of the **Manage Duties** FSM setup task. Delegate
transport and live import execution to the declared shared and core
dependencies. Prepare user-requested custom-duty changes using supported FSM fields.

Export and move FSM task **Manage Duties** only through declared dependencies.
Its catalog identity is `ASXS_MANAGE_DUTIES`; before execution, confirm a
current catalog or live-task lookup reports `CSVExportImportSupportedFlag=Y`.

## Boundaries

- Support a task-level CSV export and import of the exact export, a verified-template
  candidate or a user-supplied modified derivative. A modified archive is a new artifact:
  validate, hash, preview, and approve it separately.
- Cover duty-role groupings and their provisioning to abstract, job, or other
  duty roles. Accept creation, updates, deletion and hierarchy redesign for
  this task's supported duty objects; route changes to other setup objects
  through their dedicated skills.
- Do not call Fusion, OAuth, UCM, REST, FSM, or loader commands directly.
  Task Level Export owns export; Data Loader owns import preflight, upload,
  initiation, monitoring, and diagnostics.

## Preflight

1. Resolve project, operation, source and target environments, and duty scope.
   Require separate environments for migration or explicit confirmation for a
   same-environment restore.
2. Confirm `Manage Duties` / `ASXS_MANAGE_DUTIES` and current CSV support with
   `shared.setup-export.task-level-export`. On ambiguity or unsupported status,
   record a catalog-mismatch diagnostic and stop.
3. Confirm source export and target import privileges. Never request or expose
   credentials, tokens, or tenant secrets.
4. Persist source/target identity, task code, scope, and a redacted plan before
   any side effect.

## Export

1. Route to `shared.setup-export.task-level-export` with task name `Manage
   Duties`, code `ASXS_MANAGE_DUTIES`, source environment, and project ID.
2. Let that skill discover the task, validate support, create/poll/download the
   export, and persist it. Do not substitute a template export for setup data.
3. Preserve the returned ZIP unchanged and register its path, SHA-256, process
   ID, task identity, source environment, and timestamp.
4. On timeout/failure preserve task code, process ID, last status, process-log
   reference, elapsed wait, and next-check path; do not automatically re-export.

## Create, update, delete and redesign

Accept these operation requests for this task's own setup objects, including
user-specified individual changes. Prepare supported changes using the target's
FSM template and execute them through `core.data-loader`; do not reject a
request merely because the user does not already have an input archive.

Read [FSM input preparation](../references/fsm-input-preparation.md) when preparing a change or helping a user
understand the input. Obtain and safely extract the template, explain its files
and required columns, map supplied business values, and prepare a separate
candidate. Automatically authorize only the necessary template/spec export;
retain Data Loader's validation and actual import approval workflow.

For deletion, verify the explicit supported action for the exact object or
relationship. An omitted CSV row, blank value or unrelated REMOVE action is
not whole-object deletion. If the task has no supported deletion contract,
record that specific operation gap; do not impose a blanket prohibition on all
individual changes or invent a browser/API execution route.

For update or redesign, establish existing keys, preserve unrelated values and
show the intended changes. Intentional changes in the selected target are not
same-environment restores. Apply restore confirmation only to an actual restore.

## Template-first import preparation

1. Unless the user explicitly overrides this sequence, export the task first
   and provide that export as the import template before asking for import
   content. Explain that the template establishes the supported archive and
   file structure; it is not approval to import.
2. When the user provides an input file, compare it with the export template
   for file names, headers, column order, encoding, required values, and
   task-specific references. Help correct structural defects in a separate
   candidate file; preserve the supplied original and do not silently alter
   business values.
3. Give the user a concise change summary and identify any unresolved values
   or references. Use the corrected file only after it conforms to the export
   structure and has been assembled into a new candidate archive using the
   supported archive shape. That candidate is a new artifact and must pass the
   validation and approval gates below.
4. The user may override the export-first sequence, template choice, or
   proposed file corrections at any time. Honor that direction, while retaining
   the required task-identity, validation, and immediate import-approval gates.

## Validate and import

1. Accept a non-empty export ZIP or a user-modified derivative. Bind its
   SHA-256 to `ASXS_MANAGE_DUTIES`, source, and target. Never call it a Manage
   Job Roles archive.
2. Route validation to `shared.validation.setup-data-validator`; fail closed on
   archive shape, task identity, scope, catalog, environment, or privilege
   mismatch. Preserve validation evidence.
3. Do not alter, unpack/repack, merge, or transform the archive after
   validation. Any modification starts a new validation cycle.
4. Route the immutable validated archive to `core.data-loader` as an FSM,
   task-routed import with target identity, SHA-256, and validation evidence.
5. Let Data Loader build its immutable approval preview. Do not substitute a
   direct FSM API, UCM upload, REST call, CSV utility, or browser action.
6. Present target, task code, archive name/SHA-256, validation result, and
   expected impact; stop before the first POST. Proceed only after separate,
   immediate approval. Data Loader revalidates and owns execution thereafter.
7. Do not retry upload, import, overwrite, or replacement without fresh
   approval. Persist returned IDs, process-log references, and redacted
   diagnostics in the project workspace.

## Failures

Classify failures as input validation, catalog mismatch, authorization,
transport/environment, Fusion API, process timeout, process failed, artifact
persistence, or approval blocker. Redact credentials, tokens, customer data,
and sensitive duty or role configuration; record the blocker and safe next step.

