jlpt-doan-van-vua

Generate JLPT "đoạn văn vừa" (medium-passage / 中文読解) reading comprehension passages as styled HTML files and output CSV training data for AI fine-tuning. Each passage is a medium-length Japanese prose text (250–620 characters depending on level) testing the learner's ability to understand causal relations, reasoning, author's ideas, reference phrases, and key vocabulary via 2-3 multiple-choice questions per passage (N1/N2/N5 = 2 câu, N3/N4 = 3 câu). Skill này bao gồm TOÀN BỘ luồng: gen → QC loop (checklist PASS/FAIL) → sửa. Gen từng bài một, kiểm tra đến khi đạt chất lượng mới chuyển sang bài tiếp theo. Output chỉ gồm HTML + CSV (không có screenshot PNG). Skill này chỉ dành riêng cho dạng "đoạn văn vừa" (中文読解). Use this skill whenever the user wants to: gen bài đoạn văn vừa, tạo nội dung đoạn văn vừa, generate medium-passage reading comprehension, create JLPT 中文 passages, produce AI fine-tuning data for the đoạn văn vừa section of JLPT N1-N5, kiểm tra chất lượng, quality check, review bài, QC. Also trigger wh

Safety Notice

This listing is imported from SkillsMP metadata and should be treated as untrusted until upstream source review is completed.

Copy this and send it to your AI assistant to learn

Install skill "jlpt-doan-van-vua" with this command: npx skills add nguyendinhsinh361/skillsmp-nguyendinhsinh361-nguyendinhsinh361-jlpt-doan-van-vua

No markdown body

This source entry does not include full markdown content beyond metadata.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Open in GitHub

Related Skills

Related by shared tags or category signals.

General

jlpt-doc-hieu-tong-hop

Generate JLPT "đọc hiểu tổng hợp" (integrated / comparative comprehension / 統合理解) reading items as styled HTML files and output CSV training data for AI fine-tuning. Each item contains **TWO short Japanese passages A and B (total 600–800 characters)** on the same topic — with contrasting / complementary / debating viewpoints — tested via **2 multiple-choice questions per item that probe comparison and integration across A and B**. All questions use the fixed label `question_comprehensive_understanding`. This skill applies ONLY to N1 (≈600-750 chars total) and N2 (≈600-800 chars total). Other JLPT levels do NOT have this reading type. Skill này bao gồm TOÀN BỘ luồng: gen → QC loop (checklist PASS/FAIL) → sửa. Gen từng bài một, kiểm tra đến khi đạt chất lượng mới chuyển sang bài tiếp theo. Output chỉ gồm HTML + CSV (không có screenshot PNG). Use this skill whenever the user wants to: gen bài đọc hiểu tổng hợp, tạo nội dung integrated / comparative reading, generate JLPT 統合理解 / comparative passages, produce AI f

Repository SourceNeeds Review

-0nguyendinhsinh361

General

Memory Integration

同步 OpenClaw 记忆文件到共现图和语义向量库，支持增量更新及语义加共现的统一搜索接口。

Registry SourceRecently Updated

2580whoisme007

General

Short Video Parser

此技能用于解析短视频链接，支持解析抖音、快手、B站等多个主流平台的短视频和图文链接，并能自动提取语音内容转录为文字。适用于需要批量获取视频元数据或将视频内容转为文本的场景时使用此 skill。

Registry SourceRecently Updated

2981yangbuyiya

General

web-llm-chat

Chat with web-based LLMs through the Chrome Relay extension. Supports Qwen (chat.qwen.ai) and Kimi (kimi.com) via scripts; more sites may be added. Use for w...

Registry SourceRecently Updated

3050godiao