TypingMindTypingMindThe best frontend for AI
Data Loader Task Hook logo

Data Loader Task Hook

Organization
oracle
Data Loader Task Hook

Dispatch task-level validation for Data Loader.

Overview

Publisheroracle
RepositoryFusion-Setup-Configuration-Registry
Skill nameData Loader Task Hook
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 Data Loader Task Hook 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/core/data-loader/task-hook
  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/core/data-loader/task-hook .claude/skills/oracle-data-loader-task-hook
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Data Loader Task Hook 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 Data Loader Task Hook 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 Data Loader Task Hook 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.

Data Loader Task Hook

Purpose

Dispatch the selected task's Data Loader validation and preview lifecycle while preserving the supplied task identity, rule order, approval envelope, and final archive digest.

Preflight

Before any command, require the supplied task context and an exact supported route. For data-load, validate the selected task name and positive sequence; before building a preview, require the expected ordered rule results and archive SHA-256. Validate the preview when recording approval, and require its matching approval envelope before verifying the final archive. Fail closed on missing, ambiguous, inconsistent, or unrecognized inputs without selecting another task, route, or execution mechanism.

  • Data Loader preflight:
    • Confirm the persisted preflight before invoking data-load.
    • Require taskRouted: true, mappingComplete: true, and a SHA-256 matching the final artifact.
    • Stop before Task Validation when the preflight is missing or invalid.
    • Keep preflight parsing and verification in Data Loader.
    • Do not import Data Loader implementation code into Task Hook.

Redaction

Never include credentials, access tokens, or archive contents in Task Hook output or diagnostics. Preserve the existing user-visible preview fields and return only the validation, approval, and digest evidence defined by the selected command.

Use this as the single task-level dispatcher after the workflow has supplied the selected task context. Do not modify or reinterpret that task context.

  • data-load: required Ora Resource Task Validation using ../task-validator/scripts/task_validator.py and ../references/task-rule-registry-execution.md. Use this Task Hook's build-data-load-preview, approve-data-load-preview, and verify-approved-data-load-archive commands for the preview lifecycle; callers must not invoke Task Validator commands directly. Continue only with an approved envelope that matches the final upload artifact SHA-256.

Never scan arbitrary Skills, reselect a task, or call Run Book REST APIs.

Data Loader Preview Lifecycle

Handle data-load's returned taskValidation.taskValidationStatus before continuing:

  • ready: the rule plan is executable. The caller must immediately read the returned executionGuide and rule files and execute applicable nodes using the registry prerequisites and transitions. Declared read-only Fusion GETs through the shared REST client are part of this selected workflow. Record evidence and ordered ruleResults. This assisted execution step does not require a separate evaluator command; its absence is not a workflow gap.
  • overridden: require the existing explicit user waiver, preserve its reason and original failure evidence, require literal allowReadinessOverride: true, and execute remaining applicable rules.
  • skipped: record unavailable task guidance or rule registry as not_applicable and continue without requesting a user override.
  • Resolver errors or missing/unrecognized statuses: stop with the actual error or status. Do not substitute a different route.

ready is registry readiness, not completed validation. Follow the returned nextAction; only evaluated results may be supplied to preview creation.

After data-load resolves the task plan and the non-write rules have been evaluated, call build-data-load-preview --input-stdin with JSON containing taskContextPath, taskName, sequence, finalData, and ordered ruleResults. finalData.archiveSha256 is required. Rule exceptions remain visible as status: overridden with their user waiver and reason.

Only after explicit user approval, call approve-data-load-preview --input-stdin with the preview. Then call verify-approved-data-load-archive --input-stdin --archive <final-zip> with the preview and approval. Its taskValidationEnvelope is the exact JSON object to persist and pass to core.data-loader as --task-validation-envelope.

Never manually create, reconstruct, or modify Task Hook preview, approval, or taskValidationEnvelope outputs, including approval flags, archive digests, or Run Book bindings. Obtain these outputs only through the prescribed Task Hook preview, approval, and archive-verification commands, and persist and pass the returned taskValidationEnvelope unchanged. If it is missing, invalid, or no longer matches the artifact, stop submission and repeat the required Task Hook validation and approval steps. Never substitute direct Task Validator calls.

Project Evidence

  • Persist only the successful verify-approved-data-load-archive output as artifacts/core/data-loader/task-hook/runs/{run_id}/validation-result.json.
  • Register the validation result using core.project-mgmt.artifact-registry-manager.
  • Record one core.data-loader.task-hook skill run for the complete Task Hook lifecycle using core.project-mgmt.project-state-manager; do not create one run record per Task Hook command.
  • Append one token-usage entry for that lifecycle using core/project-mgmt/scripts/token_usage_logger.py.
  • On failure, record the failed skill run and token usage; do not create a successful validation-result artifact.

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 Data Loader Task Hook AI skill do?

Dispatch task-level validation for Data Loader.

Why use Data Loader Task Hook on TypingMind?

Because you install it once and use it with any model. Data Loader Task Hook 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 Data Loader Task Hook in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/oracle/Fusion-Setup-Configuration-Registry/tree/main/core/data-loader/task-hook. 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 Data Loader Task Hook?

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 Data Loader Task Hook?

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

Is the Data Loader Task Hook 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
affaan-m logo

Docs Governance

affaan-m
CommunityPopular

Route broad documentation-governance requests to existing ECC skills and run an opt-in, read-only audit of mapped documentation roles, links, ADR indexes, and evidence references. Use when a user asks…

41.4K
277.3K
4 files
View
affaan-m logo

Ecc Conventions

affaan-m
CommunityPopular

Development conventions and patterns for ECC. JavaScript project with conventional commits.

41.4K
277.3K
1 files
View
affaan-m logo

Mcp Dependency Review

affaan-m
CommunityPopular

Statically review MCP configuration for mutable package references before approval or CI, without executing discovered MCP servers. Use when reviewing .mcp.json, Cursor, VS Code, Claude, Windsurf, or…

41.4K
277.3K
1 files
View
affaan-m logo

Skill Host Compat

affaan-m
CommunityPopular

Lint ECC skills for Codex/Cursor-safe frontmatter and Claude-only substitutions before a skill PR.

41.4K
277.3K
1 files
View

Set up your own AI workspace now

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