/search

name: search
description: "Search all Japanese NLP resources (libraries, models, datasets, tutorials, dictionaries, Hugging Face). Accepts keywords or natural language questions in any language. Use whenever the user asks which Japanese NLP resource to use, or wants to find one: tokenizers / morphological analyzers, BERT or LLM models, embeddings, NER, text classification, datasets / corpora, dictionaries, tutorials, or Hugging Face models. Trigger phrases include '日本語の形態素解析ライブラリ', 'おすすめの日本語tokenizer', '日本語BERTモデル', '日本語の感情分析データセット', '日本語LLM 一覧', 'which Japanese embedding model', 'Japanese NER library'."
argument-hint: [query]
allowed-tools: Bash

Search the awesome-japanese-nlp-resources database for the user's query.

Claude Code and Codex

This skill is shared by the Claude Code and Codex versions of the plugin. The steps are the same in both tools; only these details differ:

• **Query** — Claude Code: the arguments of `/awesome-japanese-nlp-resources:search`, appended at the end of this skill as `ARGUMENTS: …`. Codex: the user's message that invoked `$awesome-japanese-nlp-resources:search`, minus that `$…` mention. If the skill was picked automatically rather than invoked by name, use the user's request as the query.
• **Plugin root** — Claude Code: `${CLAUDE_PLUGIN_ROOT}`. Codex: the directory two levels above this `SKILL.md` (use its absolute path).
• **Shell** — run the commands below with Claude Code's `Bash` tool or Codex's shell tool. Copy each Python script in full and run it as written, changing only its placeholders (`RESOURCES_PATH`, the keyword lists) — don't shorten it, drop passes, or alter its scores and thresholds.
• **Commands** — write any command you show the user in the current tool's form: `/awesome-japanese-nlp-resources:<skill>` in Claude Code, `$awesome-japanese-nlp-resources:<skill>` in Codex.

Results must come from the bundled data. If the data file can't be read (for example, shell commands are blocked or fail to start), say so and link https://github.com/taishi-i/awesome-japanese-nlp-resources instead of answering from memory or web search.

Instructions

Step 0 — Validate input

If the query is empty or blank, **stop immediately** and output (in Codex, write the commands with `$` instead of `/`):

Usage: /awesome-japanese-nlp-resources:search <query>

Examples:
  /awesome-japanese-nlp-resources:search morphological analysis
  /awesome-japanese-nlp-resources:search BERT
  /awesome-japanese-nlp-resources:search named entity recognition
  /awesome-japanese-nlp-resources:search text classification dataset
  /awesome-japanese-nlp-resources:search sentence embedding

Please pass the keyword(s) you want to search for as the argument.

---

使い方: /awesome-japanese-nlp-resources:search <query>

クエリ例:
  /awesome-japanese-nlp-resources:search 形態素解析
  /awesome-japanese-nlp-resources:search BERT
  /awesome-japanese-nlp-resources:search 固有表現認識
  /awesome-japanese-nlp-resources:search テキスト分類 データセット
  /awesome-japanese-nlp-resources:search 文埋め込み

検索したいキーワードを引数に指定してください。

Do **not** proceed to Step 1 if the query is empty.

Step 1 — Interpret the query

The data descriptions are in **English**, so always convert the query intent to English keywords before searching.

**Keyword rules — read before choosing keywords:** 1. **Use stems, not full words.** Substring match is used, so `morpholog` catches "morphology", "morphological", "morphological analyzer". Other examples: `embed` → embedding/embeddings, `classif` → classification/classifier, `translat` → translation/translate, `generat` → generation/generative, `segment` → segmentation/segmenter, `recogni` → recognition/recognizer, `extract` → extraction/extractor, `retriev` → retrieval/retrieve. 2. **Add domain-specific tool names.** When the query maps to a known NLP domain, include the well-known tool names present in the database:

| Domain (Japanese query hint) | Stem keywords | Tool names to add | |---|---|---| | 形態素解析 / morphological analysis | `morpholog`, `segment` | `mecab`, `janome`, `sudachi`, `kytea`, `kuromoji`, `jumanpp`, `nagisa` | | 固有表現認識 / NER | `named entit`, `NER`, `recogni` | `ginza`, `spacy`, `knp` | | 係り受け解析 / dependency parsing | `depend`, `parse`, `syntax` | `cabocha`, `knp`, `ginza`, `spacy` | | 文章分類 / text classification | `classif`, `sentiment`, `categor` | `bert`, `fasttext` | | 感情分析 / sentiment analysis | `sentiment`, `emotion`, `opinion` | `oseti`, `wrime` | | 埋め込み / word vectors / embeddings | `embed`, `vector`, `represent` | `word2vec`, `fasttext`, `bert`, `sbert` | | 事前学習モデル / pretrained model | `pretrain`, `language model`, `bert`, `gpt` | `bert`, `gpt`, `llama`, `rinna`, `elyza`, `calm`, `swallow` | | テキスト生成 / text generation | `generat`, `language model` | `gpt`, `llm`, `llama`, `rinna`, `elyza` | | 機械翻訳 / machine translation | `translat`, `machine translation` | `opus`, `marian`, `fairseq` | | 音声認識 / speech recognition | `speech`, `recogni`, `audio`, `asr` | `whisper`, `julius`, `espnet` | | 音声合成 / text-to-speech | `speech`, `synthesis`, `tts` | `voicevox`, `espnet` | | 質問応答 / QA | `question`, `answer`, `qa` | `bert`, `t5` | | 要約 / summarization | `summari`, `abstract` | `bart`, `t5`, `pegasus` | | 辞書・IME / dictionary | `dict`, `lexicon`, `ime` | `mecab`, `sudachi`, `mozc` | | コーパス・データセット / corpus | `corpus`, `dataset`, `annot` | *(rely on stems)* | | チュートリアル / learning | `tutorial`, `introduc`, `learn` | *(rely on stems)* | | OCR / 光学文字認識 | `ocr`, `optical character`, `recogni` | `manga-ocr`, `donut`, `tesseract` | | RAG / 検索拡張生成 | `retriev`, `rag`, `embed` | `ruri`, `glucose`, `faiss` | | ファインチューニング / fine-tuning | `fine-tun`, `finetun`, `lora`, `peft` | `lora`, `peft`, `qlora` | | ベンチマーク・評価 / benchmark | `benchmark`, `evaluat`, `jglue` | `llm-jp-eval`, `jglue`, `nejumi` |

3. **When the query contains Japanese text, also keep 2–4 raw Japanese terms/phrases** lifted directly from the query (not translated) as a separate `ja_keywords` list. Aliases and som