Pokemon Champions Dex logo

Pokemon Champions Dex

Community
pmwl0128
pokemon-champions-dex

Offline-first Pokémon Champions battle dex lookup with trilingual aliases (Chinese / English / Japanese), batch queries, and multi-condition reverse search. Use when the request asks for a canonical dex fact about a Pokémon/form/move/ability/item/nature/name, not for popularity trends or damage arithmetic. Chinese examples include "X能学Y吗", "谁会Y", "X是什么属性/种族值/特性", "X的中文/日文/英文名", "这个名字对应谁", "这个Mega石给谁用". English examples include "can X learn Y", "who learns Y", "what are X's types/stats/abilities", "resolve this name", "which form/item is this". Japanese examples include "XはYを覚える?", "Yを覚えるポケモン", "Xのタイプ/種族値/特性", "この名前はどのポケモン?", "このメガストーンの対応先は?". Use it while building or reviewing teams whenever a factual dex claim or name normalization is needed.

Overview

Publisherpmwl0128
Repositoryquark_drive_skills
Skill namepokemon-champions-dex
Stars
78
Forks
4
Bundled files
7
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 7 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by pmwl0128 on GitHub. Read the source before you install it.

Installation

Install the Pokemon Champions Dex AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/pmwl0128/quark_drive_skills/tree/main/.agents/skills/pokemon-champions-dex
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/pmwl0128/quark_drive_skills.git /tmp/quark_drive_skills
mkdir -p .claude/skills
cp -r /tmp/quark_drive_skills/.agents/skills/pokemon-champions-dex .claude/skills/pokemon-champions-dex
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pokemon Champions Dex in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pokemon Champions Dex on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pokemon Champions Dex is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Pokémon Champions Dex

Query the bundled Pokémon Champions battle dex before making factual claims about a Pokémon, form, move, ability, item, nature, or learnset. This skill answers "what exists and what can it learn?"; metagame popularity belongs to $pokemon-champions-meta, and damage arithmetic belongs to $ncp-damage-calculator.

Workflow

  1. Use resolve to normalize free-form Chinese, English, or Japanese names. It is batch, typo-tolerant by default, understands multilingual Mega affixes, X/Y/Z qualifiers (full-width letters included) and spoken nicknames such as 地龙/x喷/y喷, and preserves 1:1 input order.
  2. Use the entity commands or batch when full records are needed; they use the same exact → Mega composition → fuzzy order as resolve. --strict disables fuzzy guessing while retaining deterministic Mega composition and ambiguity refusal.
  3. Use find / find-move for reverse search; use --where for OR, NOT, or nested conditions.
  4. Prefer --format json for downstream processing. Use --lang zh|ja|en only for human-readable Markdown output.

Commands

Normalize names first when the input is free-form:

bash
python scripts/champdex.py resolve Mega耿鬼 超级雪妖女 牛蛙君 咆哮虎
python scripts/champdex.py resolve 灭亡之歌 地震 保护 --kind move
python scripts/champdex.py resolve 地面 フェアリー Fire --kind type --format json

Query one or many full records:

bash
python scripts/champdex.py pokemon 姆克鹰 Mega-Staraptor 巨金怪
python scripts/champdex.py move 近身战 Close-Combat
python scripts/champdex.py ability 唱反调 Contrary
python scripts/champdex.py item 耿鬼进化石 Gengarite
python scripts/champdex.py nature 固执 Adamant
python scripts/champdex.py batch pokemon 姆克鹰 巨金怪 弃世猴 洗衣机

Reverse-search Pokémon or moves:

bash
python scripts/champdex.py find move 近身战 type 飞行
python scripts/champdex.py find type 水 type 地面 stat spe>=70
python scripts/champdex.py find-move type Fire category Special power ">=90"
python scripts/champdex.py find --where '{"and":[{"type":"Dragon"},{"not":{"mega":true}}]}'

Names accept Chinese, English, and Japanese aliases. Exact aliases win; typo fallback is conservative, reports its correction, and refuses ambiguous ties. Use --strict when validation requires exact-only resolution. find and reverse are always exact. The full positional and boolean grammars are exposed by the CLI schema.

Contract And Output

Treat the executable schema as the authority for commands, fields, canonical stat keys, and errors:

bash
python scripts/champdex.py schema
python scripts/champdex.py names --format json

Canonical JSON is language-independent: English name is the cross-skill join key; stat keys and type values remain canonical English. Human-readable output language precedence is --lang, then POKEMON_CHAMPIONS_LANG, then en.

names exports the official {kind,name,name_zh,name_ja} vocabulary for presentation and bounded text checks. It includes Pokémon, moves, abilities, items and natures, without aliases or combat data.

Read references/schema.md only when database fields, name-resolution behavior, or reverse-query semantics are relevant. It supplements the executable schema rather than replacing it.

Boundaries

  • The bundled SQLite database and JSON mirror are read-only; the skill performs no network access.
  • Report dex facts and legality-relevant learnset facts, not popularity or strategic role labels.
  • A valid dex lookup is not a metagame recommendation. Use the sibling skills for usage and damage.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Pokemon Champions Dex AI skill do?

Offline-first Pokémon Champions battle dex lookup with trilingual aliases (Chinese / English / Japanese), batch queries, and multi-condition reverse search. Use when the request asks for a canonical dex fact about a Pokémon/form/move/ability/item/nature/name, not for popularity trends or damage arithmetic. Chinese examples include "X能学Y吗", "谁会Y", "X是什么属性/种族值/特性", "X的中文/日文/英文名", "这个名字对应谁", "这个Mega石给谁用". English examples include "can X learn Y", "who learns Y", "what are X's types/stats/abilities", "resolve this name", "which form/item is this". Japanese examples include "XはYを覚える?", "Yを覚えるポケモ...

Why use Pokemon Champions Dex on TypingMind?

Because you install it once and use it with any model. Pokemon Champions Dex is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pokemon Champions Dex in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pmwl0128/quark_drive_skills/tree/main/.agents/skills/pokemon-champions-dex. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Pokemon Champions Dex?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pokemon Champions Dex?

As many as you like. As long as a model supports skills, you can use Pokemon Champions Dex with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pokemon Champions Dex AI skill free?

It is published on GitHub by pmwl0128. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇