# Design Data Asset Training Programs

Generic data asset training often misses the needs of different business roles. This skill creates structured courses, exercises, assessments, and delivery plans.

## Install

```bash
npx skillstore add 图灵数盟/dhturing-data-asset-training-lecturer
```

## Metadata

- Status: approved
- Slug: dhturing-data-asset-training-lecturer
- Skillstore revision: r1
- Version status: missing
- Tree hash: 4ec01eff4603760e0e42b0478a01e4036e03fed76536b2b02cb0849859f1a0ea
- Author: 图灵数盟
- GitHub username: dhturing
- License: MIT
- Repository: https://github.com/dhturing/turing-data-experts/tree/9c58ffa97ec5b760befef6f910eb23107cdcdbf4/skills/data-asset-training-lecturer
- Ref: 50b73f83991cf073cbdf3f5afad2bbac71dd3bae
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: allowed
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: filesystem, external\_commands, network
- Quality score: 77
- Quality tier: bronze
- Public page: https://skillstore.pages.dev/skills/dhturing-data-asset-training-lecturer
- Manifest: https://skillstore.pages.dev/api/skills/dhturing-data-asset-training-lecturer/manifest

## Capabilities

- Diagnoses learner roles, training goals, maturity, budget, schedule, and delivery constraints.
- Maps management, finance, data, and business audiences to suitable course modules.
- Creates course outlines, lesson schedules, presentation plans, and role-specific learning objectives.
- Designs anonymized cases, simulation exercises, question banks, scoring rules, and completion criteria.
- Compares internal training, public courses, and public lectures with clear delivery and pricing assumptions.
- Drafts completion reports covering attendance, satisfaction, mastery, and recommended next steps.

## Use Cases

- Plan Executive Awareness Training: Create a concise program covering policy direction, strategic value, investment decisions, and governance responsibilities.
- Build Finance Team Practice: Develop an accounting-focused course with anonymized cases, simulations, assessments, and clear professional-service boundaries.
- Prepare a Public Data Lecture: Structure a short public session with audience goals, content modules, interaction, compliance limits, and follow-up options.

## Prompt Templates

### Create a Basic Course Outline

```
Create a 90-minute introduction to data assets for [audience]. Include objectives, modules, timing, one case, and a short knowledge check.
```

### Design Role-Based Learning Paths

```
Design separate learning paths for management, finance, data, and business teams. Show objectives, modules, duration, activities, and expected outputs.
```

### Develop an Applied Workshop

```
Create a [duration] workshop for [role] on [topic]. Include anonymized cases, simulation tasks, scoring criteria, assessment questions, and facilitator notes.
```

### Produce a Complete Training Proposal

```
Using these requirements: [details], produce a diagnostic summary, curriculum, schedule, materials list, assessment plan, delivery risks, pricing assumptions, and evaluation framework.
```

## Limitations

- It cannot access referenced internal presentations, videos, spreadsheets, or PDFs unless the user provides them.
- Its training guidance does not replace accounting, legal, valuation, audit, or financing advice.
- Policy citations and pricing references require verification before external or commercial use.
- It prepares training materials but cannot deliver live instruction, issue certificates, or measure real learner performance.

## Best Practices

- Define learner roles and measurable outcomes before selecting modules or materials.
- Use anonymized or fictional cases and confirm permissions for every external training asset.
- Verify current policies, pricing assumptions, and professional boundaries before delivery.

## Anti Patterns

- Do not teach every role with one undifferentiated agenda.
- Do not promise accounting recognition, financing, certification, or other regulated outcomes.
- Do not use confidential business data, copyrighted materials, or unverified policy claims.

## Security Audit

- Audited at: 2026-09-27T03:04:18.68\+00:00
- Summary: All 12 static findings are false positives caused by installation examples, Markdown backticks, public website links, or entropy heuristics on multilingual text. The reviewed files contain no executable behavior, encoded payloads, prompt injection, or data exfiltration intent.

## Stats

- Views: 0
- Downloads: 1
- Favorites: 0
- Popularity score: 0