Japanese NLP Repository Finder
Find new Japanese NLP GitHub repositories missing from awesome-japanese-nlp-resources lists.
Installation
- Make sure Claude is on your device and in your terminal.
Skills load from
~/.claude/skills/when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then runclaudein any terminal to verify.One-time setupnpm i -g @anthropic-ai/claude-codeAlready have it? Skip ahead.
- Paste into Claude Code or into your terminal.
This copies the whole skill folder into
~/.claude/skills/find-new-resources-taishi-i/— the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.Faster alternative (instruction-only skills)
Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.
Quick install (SKILL.md only)Sign up to copy - Restart Claude Code.
Quit and reopen Claude Code (or any other agent that loads from
~/.claude/skills/). New skills are picked up on startup. - Just ask Claude.
Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.
Prefer to read the source first? Open on GitHub.
When Claude uses it
Find Japanese NLP GitHub repositories that are NOT yet in awesome-japanese-nlp-resources. Suggests candidates to add for a given topic using WebSearch + WebFetch, then outputs contribution-ready markdown.
What this skill does
This skill discovers new Japanese natural language processing GitHub repositories that are not yet listed in the awesome-japanese-nlp-resources collection. It uses web search and repository inspection to identify candidate projects, filters them against the existing dataset, and produces contribution-ready markdown formatted for pull requests to the awesome list.
What it does
- Interprets your topic query into targeted English and Japanese search keywords using a domain-specific mapping (morphological analysis, NER, embeddings, LLMs, speech, and more)
- Searches GitHub via WebSearch with 4–6 mixed-language queries to cast a wide net for candidate repositories
- Filters candidates against the pre-built existing-URLs dataset (or derives URLs from
resources.jsonand README scans) to eliminate duplicates - Fetches and validates top candidates in parallel, extracting name, description, language, star count, last-updated date, and archived/fork status
- Drops archived repos, forks, and projects without Japanese/NLP signals; keeps only active, relevant projects with 3+ stars or recent updates
- Groups survivors under appropriate awesome-list section headings (Python library, Pretrained model, Corpus, Tutorial, etc.) and outputs paste-ready bullet-point entries
How to use it
Invoke the skill with a topic or keyword — for example, japanese morphological analyzer, LLM, speech recognition, or even an empty query for general latest Japanese NLP resources. The skill detects whether your query contains Japanese characters and outputs results in the matching language (English or Japanese). Each result bullet includes the repository URL, a short English description, star count, and last-updated date, ready to copy into a pull request.
Related skills
Generative Code Art
anthropics
Create algorithmic art with p5.js using randomness and interactive parameters.
Poster & Visual Design
anthropics
Create original posters and visual art in PNG and PDF formats.
Claude API Helper
anthropics
Build, debug, and optimize Claude API applications with caching and model migration support.
MCP Server Builder
anthropics
Build protocol servers that connect language models to external APIs and services.