AGENT SKILL

barracuda-strategy

BARRACUDA v1.0.1 — Funding Decay Collector. Finds assets where extreme funding has persisted for 6+ hours, confirmed by SM alignment from Hyperfeed and 4H trend structure. Enters to collect funding while riding the trend. Double edge: price appreciation + funding income from trapped traders on the other side. Fixes Croc's -42.7% failure by requiring SM and trend confirmation before entering.

License 许可
MIT
最近更新
2026-07-02
Stars
★ 1
Forks
0

01 前言 Front Matter

name
barracuda-strategy
license
MIT
metadata
{ "author": "jason-goldberg", "version": "1.0.1", "exchange": "hyperliquid", "platform": "senpi" }
description
BARRACUDA v1.0.1 — Funding Decay Collector. Finds assets where extreme funding has persisted for 6+ hours, confirmed by SM alignment from Hyperfeed and 4H trend structure. Enters to collect funding while riding the trend. Double edge: price appreciation + funding income from trapped traders on the other side. Fixes Croc's -42.7% failure by requiring SM and trend confirmation before entering.

02 资源文件 5

03 SKILL.md 正文

? BARRACUDA v1.0.1 — Funding Decay Collector

Collect funding from trapped traders while riding the confirmed trend.

Why BARRACUDA Exists

Croc tried pure funding arbitrage and lost -42.7% on 535 trades. The thesis (collect extreme funding) was sound — the execution was broken. Croc entered funding trades without checking SM direction or trend structure. When funding flipped, Croc was counter-trend and lost on both price AND funding.

Barracuda fixes this with hard gates: extreme funding must be persistent (6+ hours), SM must align, and 4H trend must confirm. You only collect funding when the market agrees with your direction.

Six-Gate Entry Model

  1. Extreme funding — annualized 30%+ (shorts paying longs, or vice versa)
  2. Persistent — same direction for 6+ consecutive hours (not a spike)
  3. SM aligned — Hyperfeed shows SM traders positioned in our direction
  4. 4H trend confirms — SMA20 slope agrees with entry direction
  5. RSI safe — not entering overbought longs or oversold shorts
  6. Leverage >= 5x — need enough leverage for funding to be meaningful

The Double Edge

When all gates pass, you're collecting funding AND riding a trend:

  • Funding income: at 30% annualized and 10x leverage, that's ~8.2% of margin per day
  • Price appreciation: SM-confirmed trend provides directional alpha
  • Trapped traders: the funding rate IS the signal — other side is paying to hold losing positions

DSL Configuration

Patient stops — funding positions need time to accumulate yield:

  • Phase 2 trigger at 5% ROE (earlier than momentum skills)
  • Stagnation TP at 8% ROE / 120 min (very patient — funding accumulates)
  • Dead weight cut at 30 min (don't hold a position that never goes green)
  • Standard 7/12/15/20% tier locks

Notification Policy (STRICT)

ONLY alert: Position OPENED (asset, direction, funding rate, daily yield, persistence hours), position CLOSED (DSL or thesis exit with reason), risk guardian triggered, critical error.

NEVER alert: Scanner found nothing, funding history updated, extreme funding detected but didn't qualify, scanner ran successfully, DSL routine check, any reasoning or analysis. If you didn't open or close a position, the user should not hear from you. Silence means working.

All crons MUST use NO_REPLY for idle cycles. Do not narrate scan results.

Expected Trade Frequency

Barracuda is a PATIENT strategy. Extreme funding that persists for 6+ hours with SM alignment and trend confirmation is rare. Expected:

  • 0-2 trades per day in normal markets
  • 0 trades for multiple days is normal during low-funding periods
  • Max 3 entries per day hard cap
  • If you're taking 5+ trades per day, something is wrong — the persistence gate should prevent this

Files

File Purpose
scripts/barracuda-scanner.py Six-gate funding scanner with persistence tracking
scripts/barracuda_config.py Config helper (from Tiger)
scripts/barracuda_lib.py Technical analysis library (from Tiger)
config/barracuda-config.json Parameters

License

MIT — Built by Senpi (https://senpi.ai).

04 同仓库更多 Skills

enuno
enuno/crewless-capital

supermemory

Supermemory is a state-of-the-art memory and context infrastructure for AI agents. Use this skill when building applications that need persistent memory, user personalization, long-term context retention, or semantic search across knowledge bases. It provides Memory API for learned user context, User Profiles for static/dynamic facts, and RAG for semantic search. Perfect for chatbots, assistants, and knowledge-intensive applications.

后端与接口
★ 1
enuno
enuno/crewless-capital

wolverine-strategy

WOLVERINE v2.0 — HYPE alpha hunter. Entry-only scanner, DSL-exit-only architecture. v1.1 lost -22.7% because the scanner's thesis exit chopped 25/27 trades before DSL could manage them. v2.0 removes thesis exit entirely. Scanner decides entries (score 8+, 4H/1H aligned, SM consensus). DSL manages all exits (wide Phase 1 for HYPE volatility, trailing tiers starting at +15% ROE). Leverage lowered to 7x. Max 4 entries/day. 3-hour cooldown between entries. DSL exit managed by plugin runtime via runtime.yaml.

★ 1
enuno
enuno/crewless-capital

wolf-strategy

WOLF v6.3 — Fully autonomous multi-strategy trading for Hyperliquid perps via Senpi MCP. Manages multiple strategies simultaneously, each with independent wallets, budgets, slots, and DSL configs. 5+N cron architecture: 5 shared wolf crons (Emerging Movers 3min, SM Flip 5min, Watchdog 5min, Risk Guardian 5min, Health Check 10min) plus one DSL v5.2 cron per strategy (native Hyperliquid SL sync via dsl-dynamic-stop-loss skill v5.3.1). Same asset can be traded in different strategies simultaneously. Enter early on first jumps, not at confirmed peaks. Dynamic risk-based leverage per strategy. Requires Senpi MCP connection, python3, mcporter CLI, OpenClaw cron system, and dsl-dynamic-stop-loss skill (provides dsl-cli.py + dsl-v5.py).

Skill与智能体开发
★ 1
enuno
enuno/crewless-capital

wolf-howl

HOWL v2 — Hunt, Optimize, Win, Learn. Nightly self-improvement loop for the WOLF autonomous trading strategy. Runs once per day (via cron) to review all trades from the last 24 hours, compute win rates, analyze signal quality correlation, evaluate DSL tier performance, identify missed opportunities, and produce concrete improvement suggestions for the wolf-strategy skill. v2 adds fee drag ratio (FDR) analysis, holding period bucketing, LONG vs SHORT regime detection, rotation cost tracking, cumulative drift detection, and gross vs net profit factor separation. Use when setting up daily trade review automation, analyzing trading performance, or improving an autonomous trading strategy through data-driven feedback loops. Requires Senpi MCP connection, mcporter CLI, and OpenClaw cron system.

Skill与智能体开发
★ 1
enuno
enuno/crewless-capital

whale-index

Auto-mirror top Discovery traders on Hyperliquid. Scans top 50 traders, scores on PnL rank (35%), win rate (25%), consistency (20%), hold time (10%), drawdown (10%). Creates 2-5 mirror strategies with overlap checks. Daily rebalance with 2-day watch period before swaps. Use when setting up trader mirroring, copy trading, or portfolio auto-rebalancing based on Discovery leaderboard performance.

★ 1
enuno
enuno/crewless-capital

vixen-strategy

VIXEN v1.0 — Dual-mode emerging movers scanner. Built from FOX v1.6 live trading data (+34.5% ROI). Two entry modes: STALKER (steady accumulation, score 6+, catches the SM buildup BEFORE the explosion) and STRIKER (violent FIRST_JUMP, score 9+, with raw volume confirmation to filter blow-off tops). 2-hour per-asset cooldown after Phase 1 exits. DSL High Water Mode mandatory.

★ 1