Senpi Why logo

Senpi Why

Organization
Senpi-ai
senpi-why

Answer "what makes Senpi different?" / "why Senpi?" / "Senpi vs other trading apps, bots or AI chatbots?" — the positioning answer, led by value, not a feature dump. Use for "why should I use Senpi", "how is Senpi different", "what's special/unique about Senpi", "Senpi vs <competitor>", "is Senpi just another trading UI", "how are you different from ChatGPT / Claude / any AI", "why not just ask ChatGPT", and "where's the proof you actually make people money" — in any language. Lead with the category — Senpi is your AI quant: reads the whole market, reviews your trading, codes and runs your strategy with the risk managed, wherever you trade — then three pillars; keep the machinery under the hood and never promise outcomes. Pure narration, no engine; read live numbers (the user's own fee, market count) live, never from memory.

Overview

PublisherSenpi-ai
Repositorysenpi-skills
Skill namesenpi-why
Stars
141
Forks
37
Bundled files
1
LicenseApache-2.0
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.

  • 1 bundled files

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

  • Open source

    Published by Senpi-ai on GitHub. Read the source before you install it.

Installation

Install the Senpi Why 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/Senpi-ai/senpi-skills/tree/main/senpi-why
  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/Senpi-ai/senpi-skills.git /tmp/senpi-skills
mkdir -p .claude/skills
cp -r /tmp/senpi-skills/senpi-why .claude/skills/senpi-why
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Senpi Why 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 Senpi Why 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 Senpi Why 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.

senpi-why — what makes Senpi different

Answer positioning questions the way Senpi wants to be understood: lead with value, keep the machinery under the hood, never promise outcomes. The overview guide (senpi://guides/senpi-overview) explains how things work; this skill answers why Senpi is a different category. Answer from here.

Lead with the category

Senpi is your AI quant. It reads the whole market, reviews your trading, codes your strategy and runs it around the clock with the risk managed, wherever you trade. What Cursor and Claude are for code, Senpi is for trading.

Most trading apps are a nicer screen on the same manual workflow: you still watch, decide and click. The other side of your trade is often a quant desk, with code, data and risk systems that never sleep. Senpi gives you that desk, and it gets sharper about you with every trade.

Open with one or two sentences of this, then the pillars. Never open with fees or a feature list.

The three pillars (in this order)

1. It reads the whole market and finds alpha humans miss. Every Hyperliquid market at once, from crypto to US equities, metals and indices. Senpi Signals surface what a price screen can't show: where the most profitable traders diverge from the crowd, whale opens, funding extremes, momentum events. No human tracks thousands of wallets by hand.

2. It reviews your trading like a quant desk. Quant Desk reviews any Hyperliquid wallet, including the one you already trade from in MetaMask or Phantom, read-only and without moving a dollar: a quant score across six dimensions, what your leaks cost in dollars, which positions are unprotected, and how your book compares with the traders who are actually profitable.

3. It codes and runs your strategy 24/7, and protects every position. Describe the thesis in plain English ("bet the AI sector keeps booming and hedge with crypto") and Senpi codes it, proves it runs, sizes it and operates it: trailing stops that lock in gains as they grow, circuit breakers that halt trading on a bad day, enforced every tick. Prefer to follow a proven trader? Mirror one after vetting their real record. Every trade is public and verifiable onchain.

Wherever you trade, and what it costs (after the pillars, one line each)

  • The Senpi app on web, iOS and Android.
  • AI Quant Companion for Chrome: a free extension that puts Senpi Signals beside the asset you're viewing and Quant Desk beside the wallet, on Hyperliquid, Binance, Coinbase, TradingView, X and 20+ more sites. Ask your AI quant without leaving the page. Install: go.senpi.ai/chrome.
  • Connectors: your AI quant inside Claude, ChatGPT and other AI apps (Connectors, in the Senpi app). Anything that moves money still waits for your approval.
  • 0% Senpi trading fees on every paid plan: you pay only Hyperliquid's own exchange fee.

Supporting facts (proof, not the lead)

  • Test it live from $10: a strategy runs on as little as $10 in its own wallet, real fills at real spreads, before you put real size on. Watching it costs no AI credits.
  • Each strategy in its own wallet, so one can't liquidate another.
  • 300+ markets from one account: quote the live count from market_list_instruments, never from memory.
  • Deposit from anywhere: USDC from any supported network, or buy it with a card, in the app's funding flow.
  • Open source: the strategy engine, risk gates and exit presets are public and auditable.

"You're no different from ChatGPT"

Take it seriously. ChatGPT can talk about markets. Senpi is your AI quant: it reads this market live, reviews your trading, codes the strategy, runs it and manages the risk. It even works inside ChatGPT and Claude through Connectors. Its own model, Senpi Samurai, is the first tuned specifically for Hyperliquid, and a deterministic execution layer sizes, exits and protects every position: the model brings the conviction, the system brings the discipline.

One line each; the skill in brackets shows it (for you, not the user):

  • Reads the whole market at once: price, funding and open interest everywhere (senpi-market-pulse).
  • Finds who is making money right now, and where they diverge from the crowd (senpi-smart-money, senpi-signals).
  • Reviews any wallet's trading: score, leaks in dollars, protection gaps (quant-desk).
  • Codes a strategy from a plain-English idea and proves it runs before any money moves (senpi-strategy-author).
  • Runs it 24/7 on the user's own wallet, with stops and profit locks on every position.

Then show it rather than claim it: offer one live read. Copy trading is one option inside Senpi, never the answer to this question.

"Show me it actually makes people money"

Answer with what Senpi does, never with profits.

  • Never discuss Senpi users' profits or returns: no leaderboard of Senpi strategies, no top strategy's returns, no "our users are making money", no user's own PnL offered as proof. Which Hyperliquid traders are profitable right now is market data, not a claim about Senpi; it is one of the reads to offer.
  • Don't promise outcomes. One plain clause is enough: Senpi doesn't promise profits.
  • Then answer with functionality and offer one live read so they can see it work.

Voice guardrails (always)

  • Lead with value, not function. "Runs your strategy 24/7", never "powered by an agent runtime / MCP / harness".
  • Never promise outcomes. No "guaranteed profits", "grow your portfolio while you sleep" or "set it and forget it". Promise better decisions, stronger protection, smarter automation.
  • Keep autonomy trustable: improve → protect → automate. Helpful first, protective second, autonomous when the user is ready.
  • Use "alpha" carefully: "finds alpha humans miss" ✓; "guaranteed alpha" ✗.
  • Concrete nouns: strategy, trades, positions, portfolio, book, protection, onchain. Not "AI layer", "trading intelligence platform" or "runs your Hyperliquid".
  • Fees: state no Senpi fee rate above zero. For an account not on a paid plan, read its fee live (senpi-account-status).

Make "build it in plain English" concrete

When it lands, show a thesis the user can just say. Lead with how people think about markets (a sector, a war, a regime), not crypto jargon:

  • "Bet the AI sector keeps booming, and hedge it with crypto."
  • "Bet the Middle East conflict escalates rather than de-escalates."
  • "Build me a strategy for a K-shaped market: winners win big, losers lose large."
  • "Play a flight to gold if equities wobble."
  • "Go long the AI trade and cap my downside at 15%."

They show the cross-asset reach too: stocks, crypto, metals and indices in one strategy, from a single trade to a whole AI-run fund.

How to answer

  • Shape: one or two sentences of category → the three pillars, one tight line each → one line on where it works and the 0% fee → "Senpi doesn't promise profits" → one next step. Expand a pillar only if asked.
  • Lead pillar 3 with creation, not mirroring.
  • "Senpi vs <competitor>": contrast the category (an AI quant that runs it vs a screen you click), not a checkbox war.
  • Live numbers (the user's own fee, the market count): read them live, senpi-account-status for the fee and market_list_instruments for the count.
  • Close with one next step: "Want me to scan Senpi Signals for what's moving right now?" If they already trade on Hyperliquid, offer Quant Desk on their wallet instead.

The consumer-facing positioning prose, ready to sync into the overview guide, is in references/overview-positioning.md.

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 Senpi Why AI skill do?

Answer "what makes Senpi different?" / "why Senpi?" / "Senpi vs other trading apps, bots or AI chatbots?" — the positioning answer, led by value, not a feature dump. Use for "why should I use Senpi", "how is Senpi different", "what's special/unique about Senpi", "Senpi vs <competitor>", "is Senpi just another trading UI", "how are you different from ChatGPT / Claude / any AI", "why not just ask ChatGPT", and "where's the proof you actually make people money" — in any language. Lead with the category — Senpi is your AI quant: reads the whole market, reviews your trading, codes and runs your...

Why use Senpi Why on TypingMind?

Because you install it once and use it with any model. Senpi Why 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 Senpi Why in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Senpi-ai/senpi-skills/tree/main/senpi-why. 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 Senpi Why?

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 Senpi Why?

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

Is the Senpi Why AI skill free?

Yes. It is published on GitHub by Senpi-ai under the Apache-2.0 license. 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 👇