Ncp Damage Calculator logo

Ncp Damage Calculator

Community
pmwl0128
ncp-damage-calculator

Run Pokémon Champions damage and speed-line calculations, or infer an opponent's possible set from observed damage and remaining HP. Use when the request asks for a concrete damage, KO, survival, or speed-order calculation between specified Pokémon, moves, spreads, field states, items, abilities, or stat stages. For broad team-building or tuning, use the team skill first and let it delegate exact calc checks. Chinese examples include "X用Y打Z多少", "X能确一/二确Z吗", "Z吃得下X的Y吗", "X快过Z吗", "多少SP能快过/抗住", "根据这次伤害反推对方配置". English examples include "calc X's move into Y", "does this OHKO/2HKO", "can Y survive this hit", "does X outspeed Y", "infer their spread from this hit". Japanese examples include "XのYでZにどれくらい入る?", "確定一発/二発?", "ZはYを耐える?", "XはZを抜ける?", "ダメージから相手の配分を推定".

Overview

Publisherpmwl0128
Repositoryquark_drive_skills
Skill namencp-damage-calculator
Stars
78
Forks
4
Bundled files
31
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.

  • 31 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 Ncp Damage Calculator 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/ncp-damage-calculator
  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/ncp-damage-calculator .claude/skills/ncp-damage-calculator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ncp Damage Calculator 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 Ncp Damage Calculator 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 Ncp Damage Calculator 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.

NCP Damage Calculator

Compute Pokémon Champions damage ranges and speed lines with the bundled NCP VGC Damage Calculator core. Use exact calculations whenever a claim depends on damage, KO, survival, or move order.

Workflow

  1. Resolve Chinese or Japanese names through $pokemon-champions-dex; the NCP wrapper itself uses English calculator keys.
  2. Run the wrapper's resolve command to align canonical English names to exact NCP keys.
  3. Supply the actual item, ability, nature, SP spread, stat stages, status, and relevant field state.
  4. Use the damage API for a concrete attack, or the speed API for one Pokémon, a table, or a direct comparison.
  5. Report assumptions with the result. A successful calculation does not establish Champions legality.

Damage

Run one calculation with JSON on stdin or use batch with a JSON array:

powershell
@'
{
  "attacker": {
    "name": "Mega Metagross",
    "ability": "Tough Claws",
    "item": "Metagrossite",
    "nature": "Jolly",
    "sps": {"hp": 2, "atk": 32, "def": 0, "spa": 0, "spd": 0, "spe": 32},
    "moves": ["Earthquake"]
  },
  "defender": {
    "name": "Mega Raichu Y",
    "ability": "No Guard",
    "item": "Raichunite Y",
    "nature": "Timid",
    "sps": {"hp": 2, "atk": 0, "def": 0, "spa": 32, "spd": 0, "spe": 32},
    "moves": ["Zap Cannon"]
  },
  "move": "Earthquake",
  "field": {}
}
'@ | python scripts\ncp-calc-api.py

The result includes all rolls, percentage rolls, min/max values, defender HP, and the calculator description.

Speed

Query one speed line:

powershell
@'
{"name":"Mega Staraptor"}
'@ | python scripts\ncp-speedline-api.py

Query a filtered table or compare two complete speed states. compare also reports move order under Trick Room:

powershell
@'
{"filters":{"type":"Flying","speedMin":170},"limit":20}
'@ | python scripts\ncp-speedline-api.py table
@'
{"a":{"name":"Garchomp","nature":"Jolly","sps":{"spe":32}},
 "b":{"name":"Archaludon","nature":"Modest","item":"Choice Scarf","sps":{"spe":32}}}
'@ | python scripts\ncp-speedline-api.py compare

Name Resolution

Do not scan vendored data files manually. Resolve calculator keys through the CLI; --kind defaults to pokemon:

powershell
'["garchomp","Rotom Wash","Mega Charizard X"]' | python scripts\ncp-calc-api.py resolve
'["close combat","earthquake"]'                | python scripts\ncp-calc-api.py resolve --kind move
'["choice scarf","lifeorb"]'                   | python scripts\ncp-calc-api.py resolve --kind item
'["roughskin","intimidate"]'                   | python scripts\ncp-calc-api.py resolve --kind ability

Contract

Treat the executable schemas as authoritative for commands, input fields, output fields, and errors:

powershell
python scripts\ncp-calc-api.py schema
python scripts\ncp-speedline-api.py schema

For opponent set inference, read python scripts/ncp-infer-case.py schema and the case workflow. Obtain a matching inference-prior from meta, then use init → add → status; remove corrects a recorded hit and example gives a surviving configuration without changing the team. Preserve the case file between turns. Record the exact battle frame: opponent HP is integer percent, our HP is exact, and stat stages already include entry effects. Explain impossible readings and joint conflict before drawing conclusions. status --predict reports damage bounds, model-conditional remaining-HP distributions and expected information in bits for the selected member's available moves, in their original order. Compare informationGainBits, not damage variation alone: random rolls can vary without distinguishing builds. These predictions assume a landed hit against a full-HP opponent in projection_frame; possibleAfters remains the initial range. The host chooses observations and when to stop. No distinguishing supported move means this member/frame has no further information, not that the opponent's build is confirmed. Relative nature shares and example spreads never confirm the opponent's true set. The case runtime requires quickjs-ng and the sibling dex; meta is only used to export the initial prior.

For saved Quark Drive Web observations, use import-web with the browser roster/record export and an explicit matching prior; see the browser transfer procedure. It preserves each hit's frozen configuration, format and enabled state. Browser storage does not save the prior: do not claim an old webpage result was reproduced using a different snapshot.

Read references/api.md when field options, batch shapes, speed modifiers, or a complete example are needed. It is explanatory documentation, not a second contract.

Caveats

  • The wrapper vendors, rather than reimplements, the NCP core. Attribution and its upstream license are in references/upstream-LICENSE.
  • The Python CLIs host that vendored JavaScript in-process via quickjs-ng (python -m pip install -r requirements.txt), so no Node runtime is needed. If quickjs-ng is not installed, those same Python entries automatically delegate to the Node CLIs (node scripts\ncp-calc-api.js / ncp-speedline-api.js); calculation and query results are identical.
  • It targets Pokémon Champions at level 50 with Champions stat points; canonical keys are hp/atk/def/spa/spd/spe.
  • NCP contains entries beyond the Champions-legal roster. Use $pokemon-champions-team or the dex for legality.
  • On-field state is resolved before the damage frame: Intimidate, terrain seeds, Trace, Air Lock, Infiltrator, weight and paradox abilities all apply on their own. Pass switch_in_drops: false when the caller already encodes Intimidate in boosts. See references/api.md.
  • Damage results model the fields exposed by the API, not every possible residual or multi-turn effect.
  • Speed defaults are 31 Speed IV, 32 Speed SP, and a positive Speed nature unless explicitly replaced.

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 Ncp Damage Calculator AI skill do?

Run Pokémon Champions damage and speed-line calculations, or infer an opponent's possible set from observed damage and remaining HP. Use when the request asks for a concrete damage, KO, survival, or speed-order calculation between specified Pokémon, moves, spreads, field states, items, abilities, or stat stages. For broad team-building or tuning, use the team skill first and let it delegate exact calc checks. Chinese examples include "X用Y打Z多少", "X能确一/二确Z吗", "Z吃得下X的Y吗", "X快过Z吗", "多少SP能快过/抗住", "根据这次伤害反推对方配置". English examples include "calc X's move into Y", "does this OHKO/2HKO", "can Y survi...

Why use Ncp Damage Calculator on TypingMind?

Because you install it once and use it with any model. Ncp Damage Calculator 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 Ncp Damage Calculator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pmwl0128/quark_drive_skills/tree/main/.agents/skills/ncp-damage-calculator. 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 Ncp Damage Calculator?

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 Ncp Damage Calculator?

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

Is the Ncp Damage Calculator 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 👇