agentsclimarketplace

Realtime alert pipeline

Skill mahmoud20138/Tradecraft/plugins/tradecraft/skills/realtime-alert-pipeline

102 Claude Code skills across 7 categories -- trading strategies, Azure, VSCode extensions, AI prompts, and custom automation skills

Install
npx -y skills add mahmoud20138/Tradecraft --skill realtime-alert-pipeline

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 7 stars7 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Condition monitoring, multi-trigger alerts, and notification pipeline for trading signals. Use this skill whenever the user asks about "set an alert", "price alert", "notify me when", "trigger alert", "condition monitoring", "signal pipeline", "push notification trading", "alert system", "watchlist alerts", "multi-condition trigger", "composite alert", or any request to set up automated monitoring and alerting. Works with mt5-chart-browser for data and all analysis skills for condition generation.

SKILL.md

3.8 KB, as published. Nobody here has run it

Real-Time Alert & Signal Pipeline

from dataclasses import dataclass, field
from datetime import datetime
from typing import Callable, Optional
import json

@dataclass
class AlertCondition:
    name: str
    check_fn: Callable  # returns True/False
    priority: str = "MEDIUM"  # HIGH, MEDIUM, LOW
    cooldown_minutes: int = 60
    last_triggered: Optional[datetime] = None

@dataclass
class AlertRule:
    id: str
    name: str
    conditions: list[AlertCondition]
    logic: str = "ALL"  # ALL (AND) or ANY (OR)
    channels: list[str] = field(default_factory=lambda: ["console"])
    message_template: str = ""

class AlertPipeline:

    def __init__(self):
        self.rules: list[AlertRule] = []
        self.triggered_alerts: list[dict] = []

    def add_rule(self, rule: AlertRule):
        self.rules.append(rule)

    def check_all(self, context: dict) -> list[dict]:
        """Check all rules against current market context."""
        triggered = []
        now = datetime.utcnow()
        for rule in self.rules:
            results = []
            for cond in rule.conditions:
                if cond.last_triggered and (now - cond.last_triggered).seconds < cond.cooldown_minutes * 60:
                    results.append(False)
                    continue
                try:
                    results.append(cond.check_fn(context))
                except:
                    results.append(False)

            fire = all(results) if rule.logic == "ALL" else any(results)
            if fire:
                alert = {
                    "rule_id": rule.id, "name": rule.name, "time": now.isoformat(),
                    "priority": max((c.priority for c in rule.conditions), key=lambda p: {"HIGH": 3, "MEDIUM": 2, "LOW": 1}[p]),
                    "channels": rule.channels,
                    "message": rule.message_template.format(**context) if rule.message_template else rule.name,
                }
                triggered.append(alert)
                for cond in rule.conditions:
                    cond.last_triggered = now
        self.triggered_alerts.extend(triggered)
        return triggered

    def format_for_telegram(self, alert: dict) -> str:
        return f"🚨 *{alert['priority']}* — {alert['name']}\n{alert['message']}\n⏰ {alert['time']}"

    def format_for_mt5(self, alert: dict) -> str:
        return f"Alert(\"{alert['name']}\", \"{alert['message']}\");"

# Preset alert conditions
def price_above(symbol: str, level: float):
    return AlertCondition(f"{symbol} > {level}", lambda ctx: ctx.get(f"{symbol}_price", 0) > level, "HIGH")

def rsi_extreme(symbol: str, overbought: float = 70, oversold: float = 30):
    return AlertCondition(f"{symbol} RSI extreme",
        lambda ctx: ctx.get(f"{symbol}_rsi", 50) > overbought or ctx.get(f"{symbol}_rsi", 50) < oversold, "MEDIUM")

def correlation_shift(pair: str, threshold: float = 0.3):
    return AlertCondition(f"{pair} corr shift",
        lambda ctx: abs(ctx.get(f"{pair}_corr_deviation", 0)) > threshold, "HIGH")

Gives 0 of the 12 instructions most monitoring observability skills give

Counted across 481 of the 483 authors here whose files we hold, read 2026-08-06

  • link every alert to a runbookin 43 of 481, across 35 files
  • use structured json loggingin 36 of 481, across 31 files
  • alert on user-facing symptomsin 20 of 481, across 15 files
  • emit structured JSON logs with stable event namesin 18 of 481, across 13 files
  • propagate trace context across boundariesin 16 of 481
  • use histograms for latency trackingin 14 of 481, across 9 files
  • use OpenTelemetry for distributed tracingin 13 of 481, across 8 files
  • include a correlation ID on every log linein 13 of 481, across 8 files
  • Define service level objectivesin 10 of 481, across 7 files
  • Call useAzureMonitor before importing other modulesin 9 of 481, across 2 files
  • stop and ask for clarification if inputs are missingin 9 of 481, across 2 files
  • define on-call questions before adding telemetryin 9 of 481, across 4 files

Said here and by no other author read

  • check all rules against current market context
  • support ALL and ANY logic for rule conditions
  • enforce cooldown minutes between triggers
  • assign priority from highest ranking condition
  • send alerts to specified channels
  • format alerts for telegram

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.