Menu

#882 by GitHub stars

taishi-i/awesome-japanese-nlp-resources

A curated list of resources for Japanese natural language processing (NLP): Python libraries, LLMs, dictionaries, corpora, and datasets. Includes Claude Code and Codex skills to search resources.

Claude CodeEngineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

plugins/awesome-japanese-nlp-resources/skills/compare/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

d609b0d4cbce → 99cfc44d4724

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → d609b0d4cbce

No earlier version was observed for comparison.

Compare on GitHub

plugins/awesome-japanese-nlp-resources/skills/discover/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

d609b0d4cbce → 99cfc44d4724

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → d609b0d4cbce

No earlier version was observed for comparison.

Compare on GitHub

plugins/awesome-japanese-nlp-resources/skills/research/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

d609b0d4cbce → 99cfc44d4724

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → d609b0d4cbce

No earlier version was observed for comparison.

Compare on GitHub

plugins/awesome-japanese-nlp-resources/skills/search/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

d609b0d4cbce → 99cfc44d4724

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → d609b0d4cbce

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 99cfc44d47243498abb06d755fbdfa0b60c775f2

git clone --filter=blob:none --no-checkout https://github.com/taishi-i/awesome-japanese-nlp-resources.git .hotskills/taishi-i-awesome-japanese-nlp-resources && git -C .hotskills/taishi-i-awesome-japanese-nlp-resources checkout --detach 99cfc44d47243498abb06d755fbdfa0b60c775f2 # Copy each selected skill directory from .hotskills/taishi-i-awesome-japanese-nlp-resources into .claude/skills/<skill-name>/
1kGitHub stars
2stars in 7 days
4skills in this repository
36commits in 30 days

Heat

3.0
  • Star growth, last 7 daysAhead of 50% of tracked repositories
  • Star growth, last 24 hoursAhead of 2% of tracked repositories
  • Rank movement, last 7 daysAhead of 1% of tracked repositories
  • Commits, last 30 daysAhead of 88% of tracked repositories
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Aug 1, 2026Nov 4, 20261,027

Individual skills in this repository

  • compare plugins/awesome-japanese-nlp-resources/skills/compare
  • discover plugins/awesome-japanese-nlp-resources/skills/discover
  • research plugins/awesome-japanese-nlp-resources/skills/research
  • search plugins/awesome-japanese-nlp-resources/skills/search

How it works

compare

When your agent uses it

Compare several Japanese NLP libraries, models, or datasets for a keyword (a specific tool name, or a function/task like '形態素解析') across a handful of criteria chosen for that comparison, rendered as a ○/△/✕ table. Use when the user wants a side-by-side comparison of multiple Japanese NLP tools/libraries/datasets, not just the single best one. Trigger phrases include 'X と Y と Z を比較して', '形態素解析ライブラリを比較', 'MeCab と Sudachi どっちがいい', 'どのツールを使うべき', 'compare japanese tokenizers', 'mecab vs sudachi vs janome', 'which embedding model should I use', '日本語NERライブラリの比較表', 'pros and cons of japanese OCR tools'. For a single ranked list use search; for alternatives to one specific tool (or contribution candidates) without a multi-axis table, use discover.

What it loads into context

Frontmatter

224 tokens

Always available to the agent

SKILL.md

4,465 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Claude Code and Codex
  2. Instructions

Files

  • ../../../../.claude-plugin/marketplace.jsonasset1,166 bytes
  • ../../.claude-plugin/plugin.jsonasset654 bytes
  • SKILL.mdcore16,693 bytes
  • SKILL.mdcore16,693 bytes
  • SKILL.mdcore16,693 bytes
  • SKILL.mdcore16,693 bytes
  • agents/openai.yamlasset232 bytes
Read SKILL.md

Compare Japanese NLP resources for the user's query across a few criteria, as a table.

## 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:compare`, appended at the end of this skill as `ARGUMENTS: …`. Codex: the user's message that invoked `$awesome-japanese-nlp-resources:compare`, minus that `$…` mention. If the skill was picked automatically rather than invoked by name, use the user's request as the query.
- **Plugin root** — Claude Code: `${CLAUDE_PLUGIN_ROOT}`. Codex: the directory two levels above this `SKILL.md` (use its absolute path).
- **Shell** — run the commands below with Claude Code's `Bash` tool or Codex's shell tool. Copy each Python script in full and run it as written, changing only its placeholders (`RESOURCES_PATH`, `SEED`, the keyword list) — don't shorten it, drop passes, or alter its scores and thresholds.
- **Web** — Claude Code: `WebSearch` to search and `WebFetch` to read a page. Codex: the built-in web search tool (search, then open the page). Do not use the `gh` CLI, `curl`, or other network commands from the shell.
- **Commands** — write any command you show the user in the current tool's form: `/awesome-japanese-nlp-resources:<skill>` in Claude Code, `$awesome-japanese-nlp-resources:<skill>` in Codex.

Candidates come from the bundled data (Step 3), topped up from the web only as Step 4 describes. 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 building the comparison from memory alone.
View the complete source on GitHub

Skills included

  • compare
  • discover
  • research
  • search

Repository facts

License
CC0-1.0
Created
Jun 8, 2022
Last pushed
Nov 2, 2026
Forks
59
Open issues
0
Project activity
Active

Rank over the last 12 weeks

Now #882 · best #607 · down 197 in 30 days

  1. #860 on Nov 2
  2. #866 on Nov 3
  3. #871 on Nov 4
  4. #872 on Nov 5
  5. #875 on Nov 6
  6. #882 since Nov 7
29 earlier periods
  1. #591 on Aug 1
  2. #543 on Aug 9
  3. #561 on Aug 10
  4. #565 on Aug 11
  5. #566 on Aug 13
  6. #621 on Aug 28
  7. #607 on Aug 31
  8. #639 on Sep 8
  9. #627 on Sep 9
  10. #627 on Sep 13
  11. #654 on Sep 17
  12. #655 on Sep 18
  13. #662 on Sep 21
  14. #674 on Sep 22
  15. #644 on Sep 24
  16. #691 on Sep 30
  17. #654 on Oct 1
  18. #673 on Oct 4
  19. #678 on Oct 5
  20. #685 on Oct 6
  21. #720 on Oct 15
  22. #727 on Oct 16
  23. #739 on Oct 19
  24. #832 on Oct 25
  25. #841 on Oct 28
  26. #844 on Oct 29
  27. #848 on Oct 30
  28. #852 on Oct 31
  29. #855 on Nov 1

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 7, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 16 notes
  • plugins/awesome-japanese-nlp-resources/skills/compare/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/awesome-japanese-nlp-resources/skills/compare/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/awesome-japanese-nlp-resources/skills/compare/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/awesome-japanese-nlp-resources/skills/discover/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/awesome-japanese-nlp-resources/skills/discover/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/awesome-japanese-nlp-resources/skills/discover/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/awesome-japanese-nlp-resources/skills/discover/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/awesome-japanese-nlp-resources/skills/discover/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/awesome-japanese-nlp-resources/skills/discover/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/awesome-japanese-nlp-resources/skills/research/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/awesome-japanese-nlp-resources/skills/research/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/awesome-japanese-nlp-resources/skills/research/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/awesome-japanese-nlp-resources/skills/research/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/awesome-japanese-nlp-resources/skills/research/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/awesome-japanese-nlp-resources/skills/search/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/awesome-japanese-nlp-resources/skills/search/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 49 signals by file

.claude-plugin/marketplace.json

  • Network accessline 1
    {   "$schema": "https://code.claude.com/schemas/marketplace.json",
  • Network accessline 2
    "$schema": "https://code.claude.com/schemas/marketplace.json",
  • Network accessline 14
    "name": "taishi-i"       },       "homepage": "https://github.com/taishi-i/awesome-japanese-nlp-resources",
  • Network accessline 15
    },       "homepage": "https://github.com/taishi-i/awesome-japanese-nlp-resources",       "repository": "https://github.com/taishi-i/awesome-japanese-nlp-resources",
  • Network accessline 16
    "homepage": "https://github.com/taishi-i/awesome-japanese-nlp-resources",
  • Network accessline 17
    "repository": "https://github.com/taishi-i/awesome-japanese-nlp-resources",

plugins/awesome-japanese-nlp-resources/.claude-plugin/plugin.json

  • Network accessline 6
    "name": "taishi-i"   },   "homepage": "https://github.com/taishi-i/awesome-japanese-nlp-resources",
  • Network accessline 7
    },   "homepage": "https://github.com/taishi-i/awesome-japanese-nlp-resources",   "repository": "https://github.com/taishi-i/awesome-japanese-nlp-resources",
  • Network accessline 8
    "homepage": "https://github.com/taishi-i/awesome-japanese-nlp-resources",
  • Network accessline 9
    "repository": "https://github.com/taishi-i/awesome-japanese-nlp-resources",

plugins/awesome-japanese-nlp-resources/skills/compare/SKILL.md

  • Broad permissionsline 1
    Bash WebSearch WebFetch
  • Network accessline 20
    Candidates come from the bundled data (Step 3), topped up from the web only as Step 4 describes. 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-
  • Network accessline 253
    WebFetch url="https://github.com/<owner>/<repo>" prompt="Extract as JSON: license, key features relevant to <the chosen axes>, install/setup complexity, and any explicit limitations mentioned. If a field is unavailable, set it to null."
  • Network accessline 281
    Sources (if you searched the web or fetched pages): - [Title](https://...)
  • Network accessline 282
    - [Title](https://...)

plugins/awesome-japanese-nlp-resources/skills/discover/SKILL.md

  • Broad permissionsline 1
    Bash WebSearch WebFetch
  • Network accessline 20
    The "Already in the list" results and the "not yet in the list" check both 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/aw
  • Network accessline 54
    (a) **A direct identifier** — a full GitHub URL (`https://github.com/owner/repo`), a full Hugging Face URL (`https://huggingface.co/owner/name` or `https://huggingface.co/datasets/owner/name`), an `owner/repo` pair, or a bare tool/model nam
  • Network accessline 269
    WebFetch url="https://github.com/<owner>/<repo>" prompt="Extract as JSON: name, one-line description, primary language, the NLP task it performs, star count, and whether it targets Japanese. If a field is unavailable, set it to null."
  • Network accessline 273
    WebFetch url="https://huggingface.co/<owner>/<name>" prompt="Extract as JSON: name, one-line description / model card summary, pipeline or task tag, whether it is a model or a dataset, downloads count, likes count, and whether it targets Ja
  • Network accessline 299
    Run the queries from Step 5 (6–9 of them). From each result, extract every URL matching: - `https://github.com/<owner>/<repo>` (ignore deeper paths like `/issues`, `/pull/`, `/blob/`, `/tree/`)
  • Network accessline 300
    - `https://github.com/<owner>/<repo>` (ignore deeper paths like `/issues`, `/pull/`, `/blob/`, `/tree/`)
  • Network accessline 301
    - `https://huggingface.co/<owner>/<name>` for models, `https://huggingface.co/datasets/<owner>/<name>` for datasets (ignore deeper paths)
  • Network accessline 311
    RESOURCES_PATH = "RESOURCES_PATH"   # from Step 2 CANDIDATES = """ https://github.com/owner/repo
  • Network accessline 312
    CANDIDATES = """ https://github.com/owner/repo https://huggingface.co/owner/name
  • Network accessline 313
    https://github.com/owner/repo
  • Network accessline 314
    https://huggingface.co/owner/name
  • Network accessline 323
    if path.endswith(".git"):         path = path[:-4]     return f"https://{m.group(1)}/{path}"
  • Network accessline 325
    return f"https://{m.group(1)}/{path}"
  • Network accessline 340
    scan_files += [os.path.join(p, "README.md"), os.path.join(p, "docs", "huggingface.md")]         break url_pattern = re.compile(r"https://(?:github\.com|huggingface\.co)/(?:datasets/)?[A-Za-z0-9_.-]+/[A-Za-z0-9_.-]+")
  • Network accessline 341
    break url_pattern = re.compile(r"https://(?:github\.com|huggingface\.co)/(?:datasets/)?[A-Za-z0-9_.-]+/[A-Za-z0-9_.-]+") for scan_file in scan_files:
  • Network accessline 342
    url_pattern = re.compile(r"https://(?:github\.com|huggingface\.co)/(?:datasets/)?[A-Za-z0-9_.-]+/[A-Za-z0-9_.-]+")
  • Network accessline 362
    WebFetch url="https://github.com/<owner>/<repo>" prompt="Extract as JSON: name, one-line description, primary language, star count, last-updated date (YYYY-MM), whether archived, whether a fork, and what NLP task it performs. Note if it tar
  • Network accessline 367
    WebFetch url="https://huggingface.co/<owner>/<name>" prompt="Extract as JSON: name, one-line description / model card summary, pipeline or task tag, whether model or dataset, downloads count, likes count, last-updated date (YYYY-MM), and wh
  • Network accessline 419
    #### Python library * [repo-name](https://github.com/owner/repo) - One-line English description. (⭐ 123, last updated: YYYY-MM)
  • Network accessline 420
    * [repo-name](https://github.com/owner/repo) - One-line English description. (⭐ 123, last updated: YYYY-MM)
  • Network accessline 422
    #### Hugging Face model * [model-name](https://huggingface.co/owner/name) - 📥 {downloads} / ⭐ {likes} / One-line English description.
  • Network accessline 423
    * [model-name](https://huggingface.co/owner/name) - 📥 {downloads} / ⭐ {likes} / One-line English description.
  • Network accessline 432
    Sources: - [Title 1](https://...)
  • Network accessline 433
    - [Title 1](https://...)

plugins/awesome-japanese-nlp-resources/skills/research/SKILL.md

  • Broad permissionsline 1
    Bash WebSearch WebFetch
  • Network accessline 187
    WebFetch url="https://..." prompt="Extract: publication/release date, name, key contribution or problem statement, proposed solution if any, GitHub/HuggingFace URL if any, and a 1-sentence summary. Note if it cites Japanese-specific issues.
  • Network accessline 246
    Sources: - [Title 1](https://...)
  • Network accessline 247
    - [Title 1](https://...)
  • Network accessline 248
    - [Title 2](https://...)

plugins/awesome-japanese-nlp-resources/skills/search/SKILL.md

  • Broad permissionsline 1
    Bash
  • Network accessline 19
    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
  • Network accessline 287
    If no results, suggest alternate keywords and link to: https://github.com/taishi-i/awesome-japanese-nlp-resources
  • Network accessline 288
    https://github.com/taishi-i/awesome-japanese-nlp-resources

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 39 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeNativeManifest .claude-plugin/marketplace.json.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md plugins/awesome-japanese-nlp-resources/skills/compare/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md plugins/awesome-japanese-nlp-resources/skills/compare/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md plugins/awesome-japanese-nlp-resources/skills/compare/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md plugins/awesome-japanese-nlp-resources/skills/compare/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md plugins/awesome-japanese-nlp-resources/skills/compare/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

nanaism/yomiyasu

AIが生成した日本語を推敲するスキル。利用者が yomiyasu の名前を出して頼んだとき（「/yomiyasu」、「$yomiyasu:yomiyasu」、「yomiyasu で推敲して」など）と、スキルを使った日本語の推敲…

2.9kGitHub stars

epoko77-ai/im-not-ai

AI가 쓴 한글을 사람 글처럼 윤문하는 Claude 스킬 — Korean AI-text humanizer: detects and rewrites translationese, mechanical parallelism, and 71 other AI tells

6.4kGitHub stars

ContextJet-ai/awesome-llm-observability

50+ curated LLM observability tools PLUS 26 Agent Skills (several with runnable, unit-tested scripts) to build, evaluate, debug, secure & monitor reliable LLM apps. Tracing, evals…

46GitHub stars

JayRHa/agent-skills

A collection of Agent Skills with instructions, scripts, references and examples for coding agents.

12GitHub stars

bergside/awesome-design-skills

List of 67 awesome DESIGN.md and SKILL.md design skill files for agentic tools like Claude Design, Google Stitch, Codex, Cursor, and other AI tools

3.6kGitHub stars

coji/natural-japanese

仕事の日本語文書を、自然で読みやすく、わかりやすい日本語で書く・直すためのスキル。議事録、調査レポート、顧客向けのレポート、社内ガイド、技術記事、PR の説明文、リサーチメモ、企画書…

2kGitHub stars

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

taishi-i/awesome-japanese-nlp-resources: #882 on hotskills, 1k stars

[![taishi-i/awesome-japanese-nlp-resources on hotskills](https://hotskills.dev/badge/taishi-i-awesome-japanese-nlp-resources.svg)](https://hotskills.dev/skill/taishi-i-awesome-japanese-nlp-resources/)