TypingMindTypingMindThe best frontend for AI
Manage Duties logo

Manage Duties

Organization
oracle
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.

Overview

Publisheroracle
RepositoryFusion-Setup-Configuration-Registry
Skill nameManage Duties
Stars
112
Forks
26
Bundled files
1
LicenseUPL-1.0
Links
Skill sourceRepository
  • 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.

  • 1 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 Duties 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/common/security-console/manage-duties
  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/common/security-console/manage-duties .claude/skills/oracle-manage-duties
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Manage Duties 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 Duties 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 Duties 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 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 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.

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 Duties AI skill do?

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.

Why use Manage Duties on TypingMind?

Because you install it once and use it with any model. Manage Duties 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 Duties in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/oracle/Fusion-Setup-Configuration-Registry/tree/main/pillars/common/security-console/manage-duties. 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 Duties?

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 Duties?

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

Is the Manage Duties 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.

Related AI Skills

View all
NousResearch logo

Modal

NousResearch
OrganizationPopular

Serverless GPU cloud for ML jobs and model APIs.

53.5K
250.4K
2 files
View
NousResearch logo

Huggingface Hub

NousResearch
OrganizationPopular

HuggingFace hf CLI: search/download/upload models, datasets.

53.5K
250.4K
Instructions
View
NousResearch logo

Pinecone

NousResearch
OrganizationPopular

Managed vector DB for production RAG and search.

53.5K
250.4K
1 files
View
NousResearch logo

Qdrant

NousResearch
OrganizationPopular

Vector search engine for production RAG systems.

53.5K
250.4K
2 files
View

Set up your own AI workspace now

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