Conducts adaptive multi-round interviews to initialize learning resource projects. Collects topic, domain, motivation, background, preferences, and volume through dynamic conversation using ARCS/SDT theories. Use when starting new projects via /init-project or reinitializing project configuration.
/plugin marketplace add BitYoungjae/dokhak/plugin install dokhak@dokhak-marketplaceThis skill is limited to using the following tools:
branching-rules.mddomain-questions.mdinterview-data-template.mdinterview-flow.mdThis skill provides interview resources for the project-interviewer agent to conduct adaptive, learner-centered interviews.
/init-project command execution (without arguments)Interview progression and question templates:
| Resource | Purpose |
|---|---|
| interview-flow.md | 7-round interview flow with multishot examples |
| domain-questions.md | Domain-specific motivation and follow-up questions |
| branching-rules.md | Conditional branching, early exit, and resume logic |
| interview-data-template.md | Template for interview transcript output |
Round 1: Topic Discovery (free input)
↓
Round 2: Domain Discovery (infer + confirm)
↓
Round 2.5: Environment (technology only)
↓
Round 3: Motivation (ARCS Relevance)
↓
Round 4: Background (SDT Competence)
↓
Round 5: Preferences (SDT Autonomy)
↓
Round 6: Volume & Language
↓
Round 7: Validation (Self-Correction Chain)
↓
Output: persona.md + interview-data.md + XML metadata
| Component | Interview Focus | Round |
|---|---|---|
| Attention | Hook with interesting aspects of topic | 1-2 |
| Relevance | Why this matters to the learner | 3 |
| Confidence | Existing knowledge and capabilities | 4 |
| Satisfaction | Expected outcomes and preferences | 5-6 |
| Need | Interview Focus | Round |
|---|---|---|
| Autonomy | Learning style preferences | 5 |
| Competence | Current skill level assessment | 4 |
| Relatedness | Connection to goals/community | 3 |
Generated learner profile containing:
Raw interview transcript containing:
<user_quote> tagsAfter Round 2 (topic + domain confirmed), users may choose "Quick Start":
Applied defaults:
- level: intermediate
- preferences: balanced (theory → practice)
- volume: medium (100 pages)
- lang: ko
These defaults are explicitly shown to the user before proceeding.
Interviews can be resumed if interrupted:
/init-project --resume - Explicit resume flaginterview-data.md exists with in_progress statusresume_state from interview-data.mdagent_idcollected_responsescurrent_roundEach round completion saves to interview-data.md:
current_round: Next round to executecompleted_rounds: List of finished roundscollected_responses: All user answers by roundpending_defaults: Fields that would use defaults on early exitSee branching-rules.md for detailed logic.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.