interactive-graph-exercise

Name: interactive-graph-exercise
Availability: InStock
Author: amazingsyp

Define exercise JSON schemas and validation logic for interactive ontology learning exercises.

26|8|Updated May 22, 2026

Search Tags:#exercise design #validation logic #interactive graphs #SPARQL builder #triple builder #partial credit #ontology learning

Ready to run

npx skills add https://github.com/amazingsyp/pokemon-ontology --skill interactive-graph-exercise

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: interactive-graph-exercise
Source: https://github.com/amazingsyp/pokemon-ontology/tree/main/.claude/skills/interactive-graph-exercise
Command: npx skills add https://github.com/amazingsyp/pokemon-ontology --skill interactive-graph-exercise

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

이 Skill은 챕터별 인터랙티브 온톨로지 학습 실습을 만들 때, 실습 JSON 스키마와 정답 검증 로직(부분 점수/피드백/힌트)을 일관된 방식으로 설계하지 못해 발생하는 구현 시행착오를 줄여줍니다.

Core Features & Use Cases

실습 7종 설계 패턴: graph-build, drag-classify, triple-build, matching, query-build, reasoning-sim, quiz 유형을 표준 형태로 정의합니다.
정답 검증 kind 명세: exact-match, set-match, subset-match, bucket-assignment, graph-isomorphism, query-match, select-correct, custom function:{name} 등 검증 전략을 validation.kind로 연결합니다.
부분 점수 및 힌트 시스템 구조: partialCredit 같은 옵션과 3단계 힌트 흐름을 함께 설계해 즉시 피드백이 가능하게 합니다.
실습 구성 가이드: 챕터당 3~5개 실습(워밍업→핵심 도전) 배치를 통해 학습 동선을 설계합니다.
정답 데이터 출처 연계: 정답이 _workspace/ontology/triples.json 또는 inference-rules.json 기반임을 전제로, 수기 오탈자/불일치를 방지합니다.

Quick Start

이 Skill에 포함된 exercise JSON 예시를 참고해, 새 실습의 type(예: graph-build 또는 query-build), init 데이터, validation.kind와 expected 값을 채운 뒤 사용자가 제출한 답을 validate 함수로 검증하도록 연동하세요.

Frequently Asked Questions about interactive-graph-exercise

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I design interactive ontology learning exercises with validated answers?▼

Interactive ontology learning exercises are designed using standardized JSON schemas that define exercise types like graph building and triple construction, linking validation logic to provide correct, partial, or hint-based feedback.

What validation strategies work for checking graph and triple building exercises?▼

Graph and triple building exercises support deterministic validation strategies including exact-match, subset-match, graph-isomorphism, and query-match to verify learner-submitted structures against expected answers.

Can I give partial credit and hints for SPARQL query building tasks?▼

SPARQL query building tasks support partial credit options and a 3-step hint flow, allowing the system to give immediate feedback and incremental guidance instead of only binary pass or fail results.

How many exercises should I structure per chapter for ontology learning?▼

Chapter-level ontology learning exercises should be structured with 3 to 5 tasks per chapter, progressing from warm-up activities to core challenges to establish a clear learning path.

Does the exercise validation logic require my answers to align with workspace triples?▼

Yes, the validation contract requires expected answers to align with workspace triples and inference rules sources, preventing manual typos and ensuring data consistency across ontology exercises.