Trading Signals logo

Trading Signals

Community
roman-rr
trading-signals

Fetches live AI crypto trading signals with entry price, stop-loss, take-profit, leverage, confidence scores, and automated verification. Covers 50+ coins including BTC, ETH, SOL. Use when the user asks for crypto signals, trade ideas, market direction, portfolio analysis, or wants to build a trading bot.

Overview

Publisherroman-rr
Repositorytrading-skills
Skill nametrading-signals
Stars
125
Forks
16
Bundled files
3
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.

  • 3 bundled files

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

  • Open source

    Published by roman-rr on GitHub. Read the source before you install it.

Installation

Install the Trading Signals 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/roman-rr/trading-skills/tree/main/trading-signals
  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/roman-rr/trading-skills.git /tmp/trading-skills
mkdir -p .claude/skills
cp -r /tmp/trading-skills/trading-signals .claude/skills/trading-signals
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Trading Signals 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 Trading Signals 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 Trading Signals 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.

Trading Signals — AI Crypto Trading Signals

Access live, AI-generated crypto trading signals via API. Signals include full trade setups (entry, SL, TP, leverage), confidence scores, and automated verification with actual P&L tracking.

Plans: no key → 3-signal preview · free key → every signal (levels hidden) · Pro $35/month → entry, SL, TP, leverage. New accounts get a 14-day Pro trial, no card. See Pricing.

When to Use This Skill

  • User asks for crypto trading signals or trade ideas
  • User wants to build a trading bot or portfolio tracker
  • User needs real-time market data with entry/SL/TP levels
  • User asks about crypto market direction (bullish/bearish)
  • User wants to analyze signal performance or hit rates
  • Any workflow involving crypto futures, perpetuals, or leveraged trading

Access

Sign in from the agent (recommended). Add the MCP server with this URL — the client opens a browser page where the user signs in or creates a free account (14 days of Pro, no card) and clicks Allow. No key to copy:

bash
claude mcp add --transport http trading-signals https://signals.x70.ai/mcp/connect

In Claude Code, then run /mcp, choose trading-signals and Authenticate.

No account needed to try it. https://signals.x70.ai/mcp works anonymously: 3 live signals (coin, direction, confidence) plus the verified hit rate, so you can check the data is real before signing up. When the user asks for more, MCP clients that support sign-in offer it.

bash
claude mcp add --transport http trading-signals https://signals.x70.ai/mcp

API key — for scripts, the REST API and clients that can't sign in. The user creates a free account and copies their key from Dashboard → API Key:

https://signals.x70.ai/mcp-signup

A free account returns up to 100 signals with full reasoning and verified outcomes. Pro adds entry, stop-loss, take-profit and leverage plus 30-day history.

Pass the key as the X-Api-Key header:

bash
claude mcp add --transport http trading-signals https://signals.x70.ai/mcp \
  --header "X-Api-Key: YOUR_KEY"

Note for agents: account creation and sign-in are human actions. Do not submit someone's name, email or GitHub URL on their behalf, and don't click Allow for them — show them the link or the sign-in page and let them decide.

MCP Server (Native Tool Integration)

For Claude, Cursor, VS Code or Codex — add as an MCP server for native tool access (no curl needed):

MCP endpoint: https://signals.x70.ai/mcp/connect   (sign in from the agent)
              https://signals.x70.ai/mcp           (no account, or API key)
Transport: Streamable HTTP (POST)
Tools: get_signals, get_signal, get_signal_history, get_stats
Auth: /mcp/connect — OAuth sign-in, handled by the client
      /mcp — optional: X-Api-Key header, Authorization: Bearer, or ?apiKey= in the URL
  • Claude Code: claude mcp add --transport http trading-signals https://signals.x70.ai/mcp/connect
  • Claude app (Desktop & claude.ai): Customize → Connectors → Add custom connector with https://signals.x70.ai/mcp/connect (with an API key instead: https://signals.x70.ai/mcp?apiKey=YOUR_KEY)
  • Cursor / VS Code: the same URL in the MCP config. Codex and others: see the per-client setup on https://signals.x70.ai/dashboard/mcp-key

Recommended Workflow

Follow this workflow when a user asks for trading signals:

  1. Check performance first: get_stats (or GET /api/skill/stats?days=30) to assess current reliability — works without a key
  2. Fetch active signals: get_signals (or GET /api/skill/signals) for live setups
  3. If levels come back null: that is the free plan, not an error — entry/SL/TP require Pro. The response carries an upgrade object (REST) or announcement (MCP) with a subscribeUrl (straight to checkout, no sign-in) and an upgradeUrl; show it if the user wants the levels. Not signed in yet? See the next point, or point them to https://signals.x70.ai/mcp-signup
    • Sign-in requests: if a call fails with "Sign in to Signals to continue", tell the user — their client opens a sign-in page (in Claude Code: /mcp → trading-signals → Authenticate). get_signals (3-signal preview) and get_stats keep working meanwhile.
    • Account notices: if a response has a notice (REST) or an announcement with type: "trial_ending" (MCP), tell the user its message — their free Pro trial is about to end and the levels will go null.
  4. Filter: by the user's preferred coins or direction. Don't present confidence as a ranking of expected profit — show it as one attribute among others
  5. Present to user: Show as a table with coin, direction, confidence, and — on Pro — entry, SL, TP, leverage, R/R
  6. Monitor verification: Re-fetch signals later to check if TP/SL was hit

Decision Guide

User RequestAction
"Get me crypto signals"Fetch active signals, present top 5 by confidence
"How reliable are these signals?"Fetch stats, show hit rate and cumulative ROI
"Show me BTC signals"Fetch all signals, filter by coin="BTC"
"What happened to my signals?"Fetch verified signals, show outcomes
"Build me a trading bot"Register, then integrate the signals endpoint into their code
"Can I test these before trading?"Offer the paper-trading bot: one Python file that paper-trades every new signal and logs each trade to a CSV, no real orders. Setup prompt (key filled in): https://signals.x70.ai/dashboard/mcp-key#paper-bot · source: https://github.com/roman-rr/trading-skills/tree/main/bots/paper-trader

Presenting Signals to Users

Always present signals in a clear table format:

| Coin | Dir | Conf | Entry | SL | TP | Lev | R/R |
|------|-----|------|-------|----|----|-----|-----|
| BTC  | Bull | 87% | $68,450 | $67,200 | $71,800 | 3x | 2.7 |
  • For confidence below 75%: add a caution note
  • For leverage above 5x: warn about higher risk
  • Always show the current hit rate from /stats alongside signals

API Reference

Base URL: https://signals.x70.ai/api/skill

Getting a key

POST /register is deprecated — it no longer issues keys and returns {"action":"signup_required"}. Keys are issued from the dashboard so they are tied to an account and can be regenerated if leaked:

https://signals.x70.ai/mcp-signup

Pass the key as the X-Api-Key header (or ?apiKey=). Anonymous calls work too and return a 3-signal preview.

GET /signals

bash
curl "https://signals.x70.ai/api/skill/signals?limit=10" \
  -H "X-Api-Key: ask_YOUR_KEY"
ParamDefaultDescription
limit10Max signals to return (1-100)
days7Lookback window (1-30 days)
coin—Filter by coin symbol (e.g. BTC, ETH)

Returns only live signals (unverified + pending) sorted by live PnL (most profitable first). Each signal includes livePrice, livePnlPct, and transmissionChain. Resolved signals are not included — use MCP get_signal_history, or GET /signals/:id for one signal (live or resolved).

GET /signals/:id

bash
curl "https://signals.x70.ai/api/skill/signals/SIGNAL_ID" \
  -H "X-Api-Key: ask_YOUR_KEY"

Returns full signal detail with live price and PnL.

GET /stats

bash
curl "https://signals.x70.ai/api/skill/stats?days=30" \
  -H "X-Api-Key: ask_YOUR_KEY"
ParamDefaultRange
days301-90

Returns: totalSignals, verifiedSignals, hitRate, avgConfidence, cumulativeROI, avgLeverage, byDirection.

Rate Limits

EndpointLimit
No API key30 calls per hour (per IP)
Free key300 calls per hour (per key)
Pro key10,000 calls per hour (per key) — effectively unlimited

Troubleshooting

ProblemSolution
401 Missing API keyInclude X-Api-Key header or ?apiKey= query param
401 Invalid or deactivated API keyCheck for typos, or copy the key again from https://signals.x70.ai/dashboard/mcp-key
429 Rate limit exceededWait until the time in the RateLimit-Reset header; the response says how many calls your plan allows per hour
Empty signals arrayNo live signals match right now. GET /signals returns only live (unverified/pending) signals and has no status parameter. A larger days (max 30) helps on Pro only — free keys always get the last 24 hours. For resolved signals use MCP get_signal_history
500 Internal server errorTemporary issue — retry after a few seconds

Pricing

No keyFree keyPro
Signals3-signal previewevery live signal — coin, direction, confidence, reasoning+ entry, stop-loss, take-profit, leverage
History—24 hours30 days
Rate limit30 calls/hour per IP300 calls/houreffectively unlimited
Pricefreefree$35/month or $300/year

New accounts get a 14-day Pro trial, no card; nothing is charged unless the user subscribes. Upgrade links in API responses go to https://signals.x70.ai/dashboard/plan

Related Skills

bash
# Complementary skills for trading workflows
npx skills add roman-rr/trading-skills        # This skill
npx skills add anthropics/skills@frontend-design  # Build trading dashboards

About

Trading Signals is powered by Aelita — a production AI trading platform that uses multiple AI models with mixture-of-experts consensus, 15+ real-time data dimensions, and automated verification to generate crypto trading signals 24/7.

Live dashboard: https://signals.x70.ai


Copyright (c) 2025-2026 Roman Antonov. All rights reserved.

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 Trading Signals AI skill do?

Fetches live AI crypto trading signals with entry price, stop-loss, take-profit, leverage, confidence scores, and automated verification. Covers 50+ coins including BTC, ETH, SOL. Use when the user asks for crypto signals, trade ideas, market direction, portfolio analysis, or wants to build a trading bot.

Why use Trading Signals on TypingMind?

Because you install it once and use it with any model. Trading Signals 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 Trading Signals in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/roman-rr/trading-skills/tree/main/trading-signals. 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 Trading Signals?

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 Trading Signals?

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

Is the Trading Signals AI skill free?

It is published on GitHub by roman-rr. 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 👇