From awesome-japanese-nlp-search
Search all Japanese NLP resources (libraries, models, datasets, tutorials, dictionaries, Hugging Face). Accepts keywords or natural language questions in any language.
npx claudepluginhub taishi-i/awesome-japanese-nlp-resources --plugin awesome-japanese-nlp-searchThis skill uses the workspace's default tool permissions.
Search the awesome-japanese-nlp-resources database for: "$ARGUMENTS"
Teaches Japanese via interactive vocabulary practice, grammar explanations, quizzes, roleplay, and parses PDF/DOCX study materials with OCR for guided homework help.
Searches 2500+ curated open-source repositories for ChatGPT, LLM tools, libraries on RAG, agents, LangChain, NLP, AI.
Provides conventions for writing Japanese text across personal diaries, technical articles, and corporate blogs, covering registers, orthography, formatting, and stylistic preferences.
Share bugs, ideas, or general feedback.
Search the awesome-japanese-nlp-resources database for: "$ARGUMENTS"
The user's query is: "$ARGUMENTS"
The data descriptions are in English, so always convert the query intent to English keywords before searching.
Examples:
| User query (any language) | English keywords to search |
|---|---|
| 日本語のNLPを勉強するためのリソース | tutorial, introduction, learning, NLP |
| トークナイザーを探しています | tokenizer, morphology, segmentation |
| 형태소 분석 (Korean) | morphology, tokenizer, segmentation |
| BERTの日本語モデルが欲しい | BERT, japanese, pretrained, transformer |
| what are good NER datasets? | named entity, NER, dataset, corpus |
| mots japonais en vecteurs (French) | word2vec, embedding, word vectors |
Run:
find "${HOME}/.claude/plugins" "${PWD}" -type f -name "resources.json" -path "*awesome-japanese-nlp-search*" 2>/dev/null | head -1
If empty, try:
find "${PWD}" -type f -name "resources.json" -path "*/data/*" 2>/dev/null | head -1
Use the Read tool on the returned path.
The file is a JSON array of 1,212 items. Each item has:
u: GitHub or Hugging Face URLn: repository/model named: English descriptionc: category (e.g. Python library, HuggingFace Model, Corpus, Tutorial, ...)s: subcategoryUsing the extracted English keywords from Step 1, score each item (case-insensitive):
n) exact keyword match: +20 points per keywordd) contains keyword: +5 points per keywords) contains keyword: +3 points per keywordc) contains keyword: +2 points per keywordExclude items with zero score.
Present up to 15 results, sorted by score descending:
## Search results for "$ARGUMENTS"
*(Searched for: keyword1, keyword2, ...)*
Found N result(s).
### 1. [repository-name](url)
**Category:** category > subcategory
Description text here.
### 2. ...
If no results, suggest alternate keywords and link to: https://github.com/taishi-i/awesome-japanese-nlp-resources