AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
MCP verified MIT Self-run

Superior Skills

mcp-superior-trade-superior-skills · by Superior-Trade

Open agent skills and tool schemas for Superior Trade — build, backtest, and deploy trading strategies on Hyperliquid

No reviews yet
0 installs
4 views
0.0% view→install

Install

$ agentstack add mcp-superior-trade-superior-skills

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access Used
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/mcp-superior-trade-superior-skills)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo ago

Declared compatibility

Claude CodeClaude DesktopCursorWindsurf

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Superior Skills? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Superior Skills

Trading strategies and intelligence tools for Superior Trade — natural-language strategy authoring, backtesting, and autonomous deployment on Hyperliquid.

Designed for OpenClaw users adding trading capabilities to their agent, and for traders who want validated templates rather than rolling their own.

Website · Discord · Twitter


Validated strategies (with backtest evidence)

These strategies have backtest evidence on real Hyperliquid data. Numbers are full-period (162 days, 2025-11-20 → 2026-05-01) unless noted.

| Strategy | Regime | Pairs tested | Trades | Win | Profit | Max DD | File | |---|---|---|---|---|---|---|---| | Donchian Strong-Regime | Strong directional trend | BTC | 6 | 100% | +6.69% | 0% | [donchian-strong-regime](skills/donchian-strong-regime/SKILL.md) | | Bollinger Reverter 4h | Range / chop (ADX/SKILL.md`).

  • SKILL.md (repo root) — auth/onboarding: request an API key by email and use the x-api-key header. Also served at superior.trade/SKILL.md.
  • skills/superior-trade-hyperliquid/ — Hyperliquid/Freqtrade API reference and agent operating rules; the core trading skill the strategies build on.
  • skills// — one skill per trading strategy (trend, mean-reversion, carry, arb, scalp) — validated drop-ins (donchian-strong-regime, bollinger-reverter-4h) and starting-point templates.
  • skills// — reusable primitives: regime-overlay, dsl-exit-engine, fees-optimizations, backtesting, trade-thesis.
  • skills/aerodrome/ — Aerodrome spot-AMM execution.
  • skills/intelligence/ — opportunity scanner / pair-ranking; detail in references/.
  • skills/polymarket/ — prediction-market trading entry skill (/v3 API); each archetype (probability-momentum, probability-mean-reversion, deadline-drift, related-market-spread, large-fill-pressure, catalyst-confirmation) is its own skill.

Getting started

# List trading accounts
curl https://api.superior.trade/v3/account \
  -H "x-api-key: $SUPERIOR_TRADE_API_KEY"

# Backtest a strategy
curl -X POST https://api.superior.trade/v2/backtesting \
  -H "x-api-key: $SUPERIOR_TRADE_API_KEY" \
  -H "content-type: application/json" \
  -d @config-and-code.json

# Start the backtest (note: action, not status)
curl -X PUT https://api.superior.trade/v2/backtesting/{id}/status \
  -H "x-api-key: $SUPERIOR_TRADE_API_KEY" \
  -d '{"action": "start"}'

# Poll until completion
curl https://api.superior.trade/v2/backtesting/{id} \
  -H "x-api-key: $SUPERIOR_TRADE_API_KEY"

Install

Superior skills follow the open Agent Skills standard — one folder per skill with a SKILL.md. Install through whichever entry point your agent uses:

| Entry point | Command | |---|---| | npx skills (universal — Claude Code, OpenClaw, Cursor, Codex, Gemini CLI, +50) | npx skills add Superior-Trade/superior-skills | | GitHub CLI | gh skill install Superior-Trade/superior-skills donchian-strong-regime | | Claude Code | /plugin marketplace add Superior-Trade/superior-skills then /plugin install superior-skills@superior-trade | | OpenClaw / ClawHub | openclaw skills install superior-skills  ·  or openclaw skills install git:Superior-Trade/superior-skills@main | | From our domain | point any agent at https://superior.trade/SKILL.md | | Manual | clone this repo and copy skills// into your agent's skills folder |

Installing the repo pulls the whole library; grab a single skill with --skill (npx) or by naming it (gh skill install Superior-Trade/superior-skills ).

Hyperliquid skills need a SUPERIOR_TRADE_API_KEY; Polymarket skills use SUPERIOR_TRADE_PM_API_KEY. The root SKILL.md (superior-trade-auth) walks a new user through getting a key by email.

Workflow

The platform emphasizes a structured progression: draft → backtest → review → deploy. No live deployment without explicit user confirmation. Every parameter is logged; every trade is tracked.

Risk disclosure

Trading involves risk. Backtests do not guarantee future performance. The validated strategies above showed positive returns on a single 162-day window (2025-11-20 → 2026-05-01); a strategy that worked then may not work in a different regime. Users remain responsible for strategy choice, deployment decisions, exchange connectivity, and capital risk. Pair every deployment with the [regime-overlay](skills/regime-overlay/SKILL.md) gate or equivalent — strategies without regime confirmation are demonstrably fragile.

Topics

hyperliquid, trading-bot, ai-agents, openclaw, backtesting, fee-optimization, opportunity-scanner, trailing-stop, algorithmic-trading, regime-filter, mean-reversion, trend-following, funding-arbitrage, mcp

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.