Skill: Trend analysis

Take any numeric time series - a stock's daily close, a FRED macro indicator, a treasury yield history - and run it through the full quantitative workup: descriptives, moving averages, trend line, outliers, optional correlation against a benchmark, and a deterministic forecast forward with a 95% prediction interval. Send POST /api/skill/trend-analysis with the required field series and pay $0.018 per call over x402 or MPP (there is no free tier). It returns a JSON object with pack, args, steps and summary.

Everything an analyst writes a notebook for, in one chain of cheap calls. Trend analysis skill pack: one x402 payment runs 11 underlying tools (stock-history, fred-series, stats-summary, moving-average, linear-regression, outliers, correlation, forecast-eval, forecast-naive, forecast-ses, forecast-holt); partial-success per step.

Category: Skill packs · Tags: skill-pack workflow trend-analysis · Pack overview

TRY IN PLAYGROUND →

Parameters

Example request

curl -i -X POST https://agent402.tools/api/skill/trend-analysis \
  -H "Content-Type: application/json" \
  -d '{"series":"AAPL","horizon":"1y","benchmark":"SPY"}'

Without payment this returns HTTP 402 Payment Required with the exact price for skill-trend-analysis; any x402 v2 or MPP client pays it and retries.

Example response

{
  "pack": "trend-analysis",
  "args": {
    "series": "AAPL",
    "horizon": "1y",
    "benchmark": "SPY"
  },
  "steps": [
    {
      "slug": "stock-history",
      "ok": true,
      "result": {}
    },
    {
      "slug": "fred-series",
      "ok": true,
      "result": {}
    },
    {
      "slug": "stats-summary",
      "ok": true,
      "result": {}
    },
    {
      "slug": "moving-average",
      "ok": true,
      "result": {}
    },
    {
      "slug": "linear-regression",
      "ok": true,
      "result": {}
    },
    {
      "slug": "outliers",
      "ok": true,
      "result": {}
    },
    {
      "slug": "correlation",
      "ok": true,
      "result": {}
    },
    {
      "slug": "forecast-eval",
      "ok": true,
      "result": {}
    },
    {
      "slug": "forecast-naive",
      "ok": true,
      "result": {}
    },
    {
      "slug": "forecast-ses",
      "ok": true,
      "result": {}
    },
    {
      "slug": "forecast-holt",
      "ok": true,
      "result": {}
    }
  ],
  "summary": "11/11 steps succeeded"
}

From an MCP client

catalog.call {
  "slug": "skill-trend-analysis",
  "params": {
    "series": "AAPL",
    "horizon": "1y",
    "benchmark": "SPY"
  }
}

The hosted connector at https://agent402.tools/mcp needs a payment for skill-trend-analysis; the stdio package pays it from a wallet or from AGENT402_CREDITS_KEY. Local install: npx -y agent402-mcp.

Errors and behavior

• Arguments left out fall back to the pack's own defaults. Each step reports on its own; the call succeeds when at least one step does, and a run where every step fails is refused (400 when the input caused it, 502 otherwise).
• A paid call that ends in any status of 400 or above is not charged over x402, MPP or a prepaid credits key: settlement is cancelled when the tool fails. The exception is a Tempo push credential, a transfer the buyer sent before the call: it settles before the tool runs, so if the tool then fails the payment is recorded as a refund owed to the paying wallet.
• Wallet-only: this tool reaches the network or stored state, so it has no proof-of-work tier. A prepaid card-credits key issued earlier (Authorization: Bearer a402_...) also pays it.
• A GET or HEAD to /api/skill/trend-analysis returns the same 402 quote, so the price can be read without a body.
• An Idempotency-Key header makes a retried paid call replay the first 200 instead of charging again (an answer larger than 1 MB is not replayed).

Paid call (JavaScript agent)

import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client();
client.setSpendControls?.(false); // keep your own spending ceiling in code
registerExactEvmScheme(client, { signer: privateKeyToAccount(KEY) });
const payFetch = wrapFetchWithPayment(fetch, client);

const res = await payFetch("https://agent402.tools/api/skill/trend-analysis", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    "series": "AAPL",
    "horizon": "1y",
    "benchmark": "SPY"
  }),
});

Related tools